Hey guys, here’s this week’s edition of the Spatial Edge, a place where nobody ever loses their projection… Anyway, the aim as usual is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Income Mapping: Google Maps pins predict São Paulo neighbourhood incomes.

• Urban Cooling: Canals cool nearby streets by nearly a degree.

• Wildfire Risk: AlphaEarth embeddings transfer between regions without retraining.

• Crop Forecasts: Sequence models predict wheat canopy a month ahead.

• Vector Mapping: One click draws a building polygon in QGIS.

Research you should know about

1. Estimating neighbourhood income from Google Maps pins

A new study from Bowdoin College and PUC-Campinas asks whether the businesses listed on Google Maps can stand in for a census when it comes to mapping income across São Paulo. Brazil’s census runs every ten years, so for most of the decade policymakers are working from stale numbers at the neighbourhood level. Points of interest, on the other hand, update constantly and cost almost nothing to pull.

The researchers queried Google Places for 47 theoretically chosen anchor categories, which surfaced 386 distinct subtypes across São Paulo’s 26,625 census sectors, with a median of 57 POIs per sector. They reduced the counts with PCA and non-negative matrix factorisation, then tested 77 configurations across seven regression models, from ridge regression to XGBoost, against household income from the 2022 IBGE census.

The best setup, NMF with 50 components feeding gradient boosting, reached a held-out R² of 0.646, so POIs alone explain close to two thirds of the variation in sector income. Churches and bars cluster in lower-income sectors, while doctors, dentists and parking lots track affluence. The model over-predicts the poorest areas and under-predicts the richest, and the residuals are spatially clustered (Moran’s I of 0.334), so there’s still room for spatial modelling. The code is on GitHub.

2. Canals are quietly cooling Britain’s cities

A new study in Nature Communications from the University of Manchester models the thermal effect of every urban canal in Great Britain and Ireland, and finds they cool the air around them by about 0.8°C on a typical day. Urban greenspace gets a lot of attention as a heat fix, with trees and parks shown to cut daytime temperatures by roughly 0.94°C. Bluespace, meaning rivers, lakes and canals, has had far less scrutiny, partly because micrometeorological simulations only ever cover a handful of sites for a day or two, while satellite land surface temperature products are too coarse to see what a 15 metre wide canal does to the street next to it.

The team built an energy balance model that compares the radiative, evaporative and convective fluxes of canal water against an equivalent surface of asphalt, and ran it at 15-minute intervals for the whole of 2022 across 2,356 canal sections. Inputs are canal geometries and depths from the Ordnance Survey and the Canal and River Trust (OpenStreetMap for Ireland), building heights for shading, and hourly OpenWeather data. Modelled water temperatures were checked against Canal and River Trust sensors at six sites, with residuals mostly within 1 to 2°C.

The median annual daytime cooling is 0.77°C within roughly 20 to 50 metres of the banks, rising to 1.2 to 1.4°C in spring and early summer and 1.5 to 2.3°C during the three 2022 heatwaves, including the one that produced the UK’s 40.3°C record. The flip side is a small nighttime warming of about 0.16°C, because water holds its heat. Regionally the daytime effect ranges from 0.32°C to 1.37°C depending on cloud and wind, and the area that benefits is around 12.4 km² in Birmingham, 8.1 km² in London, 4 km² each in Manchester and Liverpool, and 2 km² each in Glasgow and Dublin.

3. Mapping wildfire risk with AlphaEarth embeddings

A new study from UNSW Sydney and the University of Wisconsin-Madison tests whether Google’s AlphaEarth Foundations embeddings can replace the usual stack of hand-built predictors in wildfire susceptibility mapping. The conventional approach means harmonising dozens of layers, from slope and land cover to fire weather indices and soil moisture, and the resulting models tend to fall apart when you move them to a new region.

The team used MODIS active fire detections for Victoria, Australia from 2017 to 2025, giving 18,140 fire cells on a 1 km grid (about 8% of the state) matched 1:1 with pseudo-absences. They trained random forests, XGBoost, LightGBM, an MLP, TabPFN and CNNs on 9, 17 and 25 km patches of embeddings, and compared them against the same models fed 22 physical predictors screened from an initial pool of 35.

The embedding models scored ROC-AUC above 0.92 in Victoria, and when transferred without retraining the AUC rose about 4% in Canberra and fell only about 2% in the Western Sydney and Blue Mountains region, whereas the physical-variable models lost around 25%. High and very high susceptibility concentrated in eastern Victoria along the Great Dividing Range, the Victorian Alps and Gippsland, plus parts of southwestern and central Victoria. The authors pitch it at government agencies and insurers who need risk maps that travel.

4. Forecasting wheat growth a month ahead from Sentinel-2

A new study from Agroscope and the Swiss Data Science Center shows that satellite time series plus weather can forecast how a wheat canopy will develop up to 32 days ahead, at 10 metre resolution, across an entire country. Most crop monitoring is backward looking: you see what the leaf area index did, not what it’s about to do. Clouds make it worse, leaving the satellite record full of gaps that models tend to fill with implausible wiggles.

The team assembled 20.6 million pixel-level Sentinel-2 LAI time series for winter wheat across Switzerland over five seasons (2021 to 2025), paired with daily temperature, sunshine and precipitation. They trained a bidirectional GRU sequence-to-sequence model and a transformer encoder-decoder against MLP and LightGBM baselines, and added a lightweight unimodal shape regulariser that penalises valleys in the predicted trajectory so it keeps the rise-peak-decline shape a wheat season should have.

In leave-one-year-out tests the GRU reached a mean R² of 0.823 and RMSE of 0.731 LAI units, with the transformer close behind at 0.803, and both comfortably beat the non-sequential baselines. The regulariser cost almost nothing in accuracy while making the trajectories biologically sensible. The setup is crop and region agnostic, so the same recipe should port to other crops where LAI is available.

5. One click to draw a building polygon in QGIS

A new paper from LuxCarta, accepted at IGARSS 2026, introduces Click2Poly, a vision-language model that lets a mapper click once on a satellite image and get a clean building polygon or wall line back. Automated building extraction has got good, but production mapping still ends with a human fixing the outputs by hand, and that correction step is where most of the time goes.

Click2Poly extends Microsoft’s Florence-2 with three tools: draw a building, split a connected block into separate buildings, and trace a wall or fence. It was trained on 377,207 building polygons across 202 areas (about 1,344 km²) and 197,234 wall linestrings across 117 areas, all on 30 cm Pléiades Neo imagery cut into 768 pixel patches, with user clicks simulated by sampling random points inside each building during training. It ships as a QGIS plugin talking to a server that caches image encodings.

In a timing study with four operators across four test areas, Click2Poly cut editing time from 303.5 to 199 minutes, a 1.53x speed-up overall, reaching 2.30x in the Philippines and 1.78x in Angola, though it was marginally slower (0.93x) in a dense São Paulo scene. Agreement between operators stayed at 90.7 to 96.5% IoU, and inference runs at about 1.3 seconds to encode an image and 0.8 seconds per polygon on an RTX 3060.

Geospatial Datasets

1. Four decades of global forest fire patches from Landsat

GlobMap FFP is a global inventory of 11.97 million individual forest fire patches mapped at 30 m from Landsat between 1984 and 2022, covering all forest with more than 25% tree cover. You can read the paper here and access the data here.

2. Global forest disturbance regimes inferred from satellite biomass

A Max Planck Institute for Biogeochemistry dataset of four disturbance regime parameters (disturbance rate, gap-size distribution, severity and background mortality) for the world’s forests, derived by inverting the spatial pattern of ESA GlobBiomass 2010 with random forests trained on more than 8 million synthetic forest simulations. It comes as 25 km tiles in CSV and a 0.25° global grid in NetCDF, with reliable predictions for roughly 90% of forest regions. You can read the paper here, access the data here and the code here.

3. Snowmelt runoff onset from Sentinel-1, 2015 to 2024

A University of Washington dataset of the date snowmelt runoff begins each year at 80 m resolution for almost all seasonal snow on Earth (60°S to 81.1°N), for water years 2015 to 2024, plus ten-year median and variability composites. You can read the paper here, access the data here and the code here.

4. Thirty years of paddy rice maps for South and Southeast Asia

Maps of paddy rice extent and cropping intensity (single, double or triple season) at 30 m for India, Pakistan, Bangladesh, Myanmar, Thailand, Laos, Cambodia and Vietnam, for nominal years 1995, 2005, 2015 and 2024, each built from multi-year Landsat and Sentinel-2 composites. You can read the paper here, access the data here and the Earth Engine code here.

5. Using a community wireless network as a rain gauge in New York

OpenMesh is eight months (29 October 2023 to 1 July 2024) of one-minute received signal level measurements from 103 wireless sublinks across 75 hops of NYC Mesh, a community-run network in lower Manhattan and Brooklyn covering about 10 km², in the 5 to 6 GHz, 24 GHz and 58 to 70 GHz bands. You can read the paper here, access the data here and the code here.

Other useful bits

• Europe’s next weather satellite, MTG-I2, launches on 27 August on an Ariane 62 from French Guiana, the first Ariane 6 flight to geostationary transfer orbit. Built by a Thales Alenia Space, OHB and Leonardo consortium for ESA and EUMETSAT, it carries the Flexible Combined Imager and a Lightning Imager, scans the full disc every 10 minutes and Europe every 2.5 minutes, and will pair with Meteosat-12 to produce at least 50 times more data than the Meteosat Second Generation satellites.

• The Copernicus Land Monitoring Service has released 2024 croplands, grasslands and tree cover and forests layers from its High Resolution Vegetated Land Cover Characteristics suite, covering the EEA-38 countries and the UK. The full 2017 to 2023 archive has moved to the Copernicus Data Space Ecosystem at the same time, so the whole time series is now in one place and browsable in Copernicus Browser.

• Schneider Electric is buying AiDASH for USD 350 million in enterprise value. The Palo Alto company uses satellite imagery and AI to flag vegetation, storm and wildfire risk to power lines for utilities, and will slot into Schneider’s One Digital Grid platform. Schneider’s venture arm had put USD 10 million into the company back in 2022.

• Verisk has acquired McKenzie Intelligence Services, a UK geospatial intelligence firm that does real-time post-event damage assessment for catastrophes and conflict events. It joins Verisk’s Catastrophe and Risk Solutions division, where its imagery-derived damage data will feed the existing risk models. The price wasn’t disclosed.

• Intermap has agreed to acquire the rest of PCI Geomatics, the Canadian company behind the CATALYST imagery processing software, for USD 11 million in cash. PCI’s 750-odd algorithms handle imagery from more than 500 satellites across roughly 30,000 licences, and the plan is to pair them with Intermap’s 3D elevation models.

• NASA’s Earth Observatory has a nice piece on reading Adélie penguin diets from the colour of their guano in Landsat imagery. Krill-heavy diets leave pink stains and fish-heavy ones don’t, and across more than 100 Antarctic colonies the colour tracks sea ice: warmer, less icy regions like the Antarctic Peninsula eat krill, while East Antarctic colonies with more ice eat more fish, and fish-fed chicks grow and survive better.

Jobs

• Muon Space is looking for a Senior Remote Sensing Data Scientist for calibration and validation, fully remote.

• Overstory is looking for a Staff Data Scientist working on wildfire, remote in the US or Canada.

• Mapbox is looking for a Senior or Lead Software Data Engineer on its Roads team based in Helsinki, Finland.

• Mapbox is also looking for a Senior Software Engineer for its Rust routing engine based in the United States.

• IUCN is looking for a Director of its Global Information Systems Group based in Gland, Switzerland.

• European Space Agency (ESA) is looking for a Copernicus Sentinel-2 NG Lead Instrument End-to-End Data Chain Engineer based in Noordwijk, Netherlands.

Just for Fun

This all-sky composite stacks the footage from four meteor-monitoring cameras at an observatory in Czechia over the night of 12 to 13 August, when the Perseid shower was at its peak. The cameras logged 1,706 meteors that night, and nearly all of the trails trace back to a single radiant in Perseus at the upper right. Look closer and you can pick out the fainter showers hiding underneath, including the Kappa Cygnids radiating from Cygnus and the antihelion complex near Aquarius, the weak source that sits directly opposite the Sun.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge, a place where the errors are always spatially autocorrelated. Anyway, the aim as usual is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Cyclone Forecasts: Google’s AI buys forecasters an extra day.

• Mobile Networks: Climate hazards threaten millions of base stations.

• Foundation Models: Nearly a third ship code with no weights.

• Image Matching: One model aligns imagery across six continents.

• Riverfronts: A fifth of the world’s riverfronts are modified.

Subscribe now

Research you should know about

1. Google’s AI can now forecast cyclones a day earlier

A new study published in Nature introduces WeatherNext Cyclones, an AI model that produces ensemble forecasts for the track, intensity and size of tropical cyclones anywhere in the world. Cyclones are among the most dangerous and costly weather events there are, and forecasting them well has stayed stubbornly hard. The conventional route is regional physics models run at very high resolution, which is expensive and still leaves intensity forecasts shakier than track forecasts.

The model was trained on a combination of global analysis data and a global database of historical cyclones, and it generates large ensembles of possible global weather and cyclone scenarios out to 15 days. Two things stand out about how it’s built. It runs on inputs that are orders of magnitude coarser than regional models, which suggests high resolution isn’t a strict prerequisite for state of the art intensity forecasting, and it scales to 1,000-member ensembles rather than the conventional 50, which captures rare events much better.

Evaluated on cyclones from 2023 to 2025, the track, intensity and wind radii predictions gave an average of a day or more of extra lead time over leading operational models, which the authors compare to a decade of conventional operational progress. Adding it to a weighted-average consensus ensemble improves that ensemble’s skill too. Google DeepMind says the US National Hurricane Center used the model during the 2025 season on Hurricane Melissa’s rapid intensification and landfall in Jamaica, and the code and weights are now on GitHub under Apache 2.0.

2. What climate change will do to mobile phone networks

A new study in Nature Communications puts numbers on how exposed the world’s mobile networks are to floods and cyclones. Climate risk assessments usually cover roads, power grids and buildings. Telecommunications gets left out, which is odd given that mobile networks are the thing everyone depends on during a disaster.

The researchers built a global, event-based geospatial assessment of roughly 17 million mobile base stations, combining crowdsourced open asset data with global climate hazard models. They ran it under historical conditions and two future scenarios, RCP4.5 and RCP8.5, and estimated both exposure and direct damage across a range of extreme-event return periods.

Under RCP8.5 in 2050, a tropical cyclone event with a 0.1% annual probability affects an estimated 3.7 million base stations and causes USD 4.22 billion in direct damage. Under RCP8.5 in 2080, the equivalent coastal flooding event affects 268,000 stations and causes USD 6.44 billion in damage. Riverine flooding touches more assets globally, around 2.8 million, though damages there stay broadly stable at USD 46 to 47 billion. The practical takeaway is that telecoms assets belong in climate risk assessments as standard, and there’s now open crowdsourced data good enough to do it.

3. Most geospatial foundation models are hard to actually use

A new study from the University of Cambridge asks a question the geospatial foundation model literature mostly skips, which is whether anyone outside the lab can actually run these things. Most evaluations are model-centric and stop at architecture and benchmark accuracy. That tells you nothing about whether an ecologist can pick a model up and get a result out of it.

The team ran a pilot survey with ecology and conservation scientists, turned what they heard into a seven-dimension usability rubric grounded in HCI theory, then had two raters score 89 GeoFMs against it. The dimensions are access and deployment, interaction and customisation, trust and transparency, community and support, scientific permanence, multilingual support, and offline usability.

Nearly 29% of the 89 models scored Level 0 on access, meaning no public weights at all, and another 21% ship weights with minimal guidance, so over half (50.6%) require you to either pre-train from scratch or build a complex environment on your own. Only six models (6.7%) offer a hosted API or a graphical interface: MOSAIKS, Google’s AlphaEarth, Prithvi, AIEarth, SatLas and Tessera. Trust is the bigger gap. Of the accessible models, 96.8% provide replicable benchmarks, exactly one has built-in explainability, and none document uncertainty quantification, which is the feature the surveyed experts ranked highest. It is getting better though: 54% of 2025 releases reached Level 3 or above, against 27% in 2024.

4. Matching satellite images from anywhere on Earth

A new study from Beihang University takes on dense image matching at global scale, where two images of the same place can differ in acquisition time, season, viewpoint, resolution and land cover. Dense matching establishes pixel-wise correspondences and underpins a lot of photogrammetry and change work. The trouble is that large geometric offsets, partial overlap and regions that genuinely can’t be matched make direct dense prediction both unreliable and slow.

The fix is to reformulate matching as localisation-and-registration: first find the matchable overlap and its affine geometry, then refine dense residuals inside the aligned frame. The resulting model is LoRetta. They also released LEVIR-GM, a global multi-temporal optical matching benchmark with matchability labels built in: 103,000 aligned pairs, 827,000 after augmentation, spanning six continents, five years and resolutions from 0.5 m to 1,024 m.

LoRetta scores 83.3% AUC on LEVIR-GM, 1.6 points above the RoMa v2 baseline, with percentage of correct keypoints up 6.5 points at 1 pixel and 8.2 points at 2 pixels, and it runs 47.8% faster. They also demo it on cross-domain geolocalisation, matching astronaut photography and UAV imagery back to satellite scenes. The code is on GitHub and the weights are on Hugging Face.

5. A fifth of the world’s riverfronts have been reshaped by people

A new study in Nature Communications maps 7.52 million kilometres of riverfront, the strip where land meets water along a river, and finds nearly 20% of it has been modified by people. Most river fragmentation research is about dams, which cut rivers lengthwise. The lateral edge, where farming and building press right up against the channel, has been much harder to see at global scale.

The researchers used satellite imagery and deep learning to build a high-resolution global map of riverfront land cover. Agriculture accounts for 13.43% of global riverfront and built-up areas for 6.29%. The rest breaks down as wooded (43.27%), semi-barren (16.03%), grassy or tundra (14.95%) and barren (6.03%).

A distinct modification belt running across parts of Africa and Eurasia accounts for around 60% of all global alterations, with imprint densities six times higher than everywhere else. The authors link this lateral fragmentation to deteriorating water quality and biodiversity threats, and argue it’s a fundamentally different pressure from the longitudinal fragmentation dams cause. Environmental limits and region-specific socio-economic dependencies explain a lot of where the imprints land.

Geospatial Datasets

1. Forty years of gridded hydrology for 9,067 US basins

BASINGRID is a spatially distributed hydrology dataset covering 9,067 basins across the contiguous United States from 1985 to 2024, harmonised to a roughly 1 km Daymet reference grid. You can read the paper here and access the data here.

2. Bias-corrected CMIP6 projections for India

This is a daily, non-stationary, multivariate bias-corrected dataset of precipitation and maximum, minimum and mean temperature for India at 0.25° resolution, derived from 13 CMIP6 global climate models. The paper is here and you can access the data here.

3. A global inventory of landslides studied with DInSAR

A geo-referenced inventory of landslides that have been investigated using satellite differential SAR interferometry, compiled from a systematic review of the literature from 1995 to 2024. The team screened 2,739 contributions and geo-tagged the resulting 1,480 point identification numbers, distinguishing site-specific from area-wide analyses. China, Italy and the US dominate the case studies, and the positions were validated against the global landslide susceptibility map and independent inventories. The paper is here and you can access the data here.

4. A century of Chinese hydropower stations

A century-scale inventory of 2,918 georeferenced hydropower stations in mainland China covering 1909 to 2025, compiled from international databases, national statistics and archival sources. The paper is here and you can access the data here.

Other useful bits

• Google Maps Platform has opened a private preview of Custom Satellite Embeddings, powered by DeepMind's AlphaEarth Foundations. Instead of the annual global embedding layer, you can request 10 m, 64-band embeddings for your own region and time window at intervals as short as five days. Academic researchers can apply for free sample datasets through Earth Engine until 1 September 2026.

• A new open-source Python package called DefoEye wraps GMTSAR into a single time-series InSAR workflow for Sentinel-1, with parallel job execution, interferogram network pruning and a graphical interface, so you don't need to hand-hold every step. Tested across Bologna, Gotland and Houston it matched GNSS stations with RMSE of 4.3 to 11.9 mm and correlations of 0.63 to 0.95, and the code is on GitHub.

• Microsoft has released Aurora 1.5, an update to its open Earth system foundation model that goes from 4 to 26 predicted variables, adds hourly resolution and supports probabilistic ensembles. It beats ECMWF ensemble forecasts on 88.9% of the evaluated variable-and-lead-time targets, and cuts tropical cyclone track error by roughly a third against the original Aurora at day 5. Checkpoints are on Hugging Face and the code is open source.

• PAHO and Esri have wrapped up an advanced GIS training series for public health emergency management across the Americas, covering spatial statistics, risk modelling and geospatial data management. It ran through 2025 and 2026 and finished with a virtual session on 17 June, with 100 participants from 21 countries completing the training.

Jobs

• Planet is looking for a Senior Engineering Manager for its AI Geospatial Assistant team based in San Francisco.

• Muon Space is looking for a Senior Applied Scientist, Geospatial, fully remote.

• Overstory is looking for a Staff Machine Learning Engineer working on wildfire, remote in the US or Canada.

• Esri is looking for a Product Engineer II for 3D Reality Mapping based in Stuttgart, Germany.

• Zipline is looking for a Senior Software Engineer on Maps Routing based in South San Francisco.

Just for Fun

The corona of a total solar eclipse normally looks white, but observers in Spain on 12 August saw a distinctly golden one. Two things did it. Totality happened with the Sun near the horizon, so the light travelled through a lot of atmosphere and lost most of its blue, and smoke from nearby forest fires acted as a second filter that deepened the gold further. The one thing that stayed off-palette was a hydrogen-glowing prominence on the Sun's left edge, which kept its bright pink. This HDR-processed, multiple-exposure image was captured from Benavente, Spain.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge. If you’ve ever considered calling your next kid, ‘WGS84’, we have one thing to say to you: welcome home… In any case, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Self-Play AI: Self-training model masters geospatial reasoning without labels.

• Crop Mapping: AlphaEarth embeddings replace manual feature engineering.

• Street Generation: Diffusion models create controllable urban street designs.

• Robustness Benchmark: EarthShift tests real-world satellite model generalisation.

• Earth Dataset: WorldTensor unifies global environmental and socioeconomic data.

• Climate Data: Bias-corrected global climate projections through 2050.

Subscribe now

Research you should know about

1. Self-playing AI masters geospatial reasoning without human labels

Training vision-language models to understand satellite and aerial imagery usually requires massive, human-curated datasets. But complex geospatial reasoning (such as analysing object adjacency, counting instances, or comparing areas) creates a combinatorial explosion of possible questions that manual annotation simply can’t cover. To bypass this problem, a new paper introduces GeoX, an autonomous self-play framework that masters spatial reasoning without using any human-annotated question-answer pairs. Instead of relying on static labels, GeoX alternates a single model between two roles: a proposer that programmatically constructs geospatial problems over unlabeled remote sensing images, and a solver that attempts to answer them.

The framework structures these problems as executable Python programs using an underlying library of geometric, topological, and aggregation primitives, alongside an open-vocabulary segmentation tool. To build robust structural comprehension rather than simple pattern recognition, the system forces the model to interrogate each proposal under three distinct reasoning modes: abduction (inferring the input arguments from observed outputs), deduction (predicting outputs from given parameters), and induction (synthesising the underlying program code from input-output examples). A programmatic verifier then executes the code to supply an objective reinforcement learning reward, which incentivises the proposer to create learnable, frontier-pushing challenges and the solver to derive correct answers.

When evaluated zero-shot across multiple remote sensing visual question answering and object counting benchmarks (including RSVQA-HR, EarthVQA, and GEOBench-VLM), GeoX consistently outperformed its base foundation models by an average of up to 5.5 points. Interestingly, despite using zero curated training pairs, the self-play model matched or exceeded domain-specific vision-language models fine-tuned on millions of human-annotated examples, achieving particularly strong gains in complex spatial relation classification and object counting.

2. Ready-made embeddings for field-scale crop mapping

The old school way of doing crop mapping using machine learning involved a bunch of time spent on feature engineering. You’d have to manually clean optical satellite data, mask clouds, and calculate stuff like NDVI over a growing season. To save the pain of all this, a new study explores whether we can skip the manual preprocessing entirely by using Google DeepMind’s AlphaEarth geospatial foundation model embeddings. Instead of raw spectral bands, AlphaEarth provides analysis-ready, annual 64-band “embeddings” (I did a deep dive explainer on this here).

To test this approach, researchers focused on mapping processing tomatoes across California. They extracted AlphaEarth embedding chips for 9,484 agricultural fields (split evenly between tomato and diverse non-tomato crops based on LandIQ 2018 records) and trained a U-Net deep learning segmentation model. On a spatially independent test set of 1,424 fields, the model achieved an exceptional 99.19% pixel accuracy and a 98.11% intersection over union (IoU), cleanly tracing tomato field boundaries with minimal confusion against visually similar annual crops.

The team also used Monte Carlo dropout during inference to map predictive uncertainty. By running each field chip through the model 100 times, they found that uncertainty was consistently quite low within the interiors of well-defined fields and spiked around borders, irregular edges, and mixed margins. This provides a practical safeguard, flagging ambiguous boundary pixels where human review might be needed. While the study relies on reference data from a single year (2018), it shows how foundation model embeddings can be used as an operational alternative to manual feature engineering for field-scale crop mapping.

3. Generating alternative urban streetscapes with diffusion models

While street-view imagery is pretty commonly used by urban planners to measure and evaluate existing built environments, such as calculating greenery, sky, or building view indices, these observational tools can’t generate alternative or non-existing urban scenarios. To address this, a new paper introduces a controllable generative AI framework that combines realistic, alternative streetscapes conditioned on targeted visual metrics and text descriptions. Using a curated multimodal dataset of 32,000 images from Chicago and Orlando, the researchers aligned street-view imagery with text descriptions, object counts, and semantic segmentation maps (specifically road masks) to allow for fine-grained manipulation of urban scenes. By fine-tuning Stable Diffusion and ControlNet models, the framework directly translates abstract planning intentions, such as increasing tree canopy coverage while preserving existing road geometry, into concrete visual street environments.

The results demonstrate that incorporating imagery controls via ControlNet significantly improves both visual realism and semantic consistency compared to text-only diffusion baselines. Using explicit road segmentation masks reduced perceptual dissimilarity (LPIPS) by approximately 6% and boosted overall semantic alignment (mIoU) by 23.7% in Orlando and 46.4% in high-density Chicago. The framework also supports complex, multi-element trade-off scenarios; when language prompts instructed the model to increase tree canopy coverage while reducing sky or building proportions, the generated greenery naturally expanded along sidewalks and foregrounds without encroaching on roadways or distorting building geometry.

Interestingly, when text prompts and visual road masks were intentionally set to conflict, the imagery controls exerted a dominant influence over the generated streetscape. Even when language prompts requested a six-fold variation in road proportions (from 5.71% to 35.71%), the generated streetscapes strictly adhered to the geometry and layout of the input road mask. This reveals a clear control hierarchy where spatial masks anchor the geometric backbone of a scene, while text prompts provide high-level compositional guidance when masks aren’t available.

4. Benchmarking distributional shift in Earth observation

Current satellite machine learning models can be brittle when deployed in out-of-distribution contexts (e.g. new geographies, time periods, or sensors, etc.). However, most benchmarks only test generalisation to new samples drawn from the same in-distribution training set. This leaves a bit of a blind spot for deploying geospatial models in real-world scenarios. To address this, researchers introduce EarthShift, a public testbed for benchmarking distributional robustness across five common natural remote sensing shifts: spatial scale, time, geographic location, sensor modality, and data source. The benchmark pairs established datasets across 11 tasks (e.g. shifting from Sentinel-2 to Sentinel-1 for flood mapping, or testing across countries with vastly different field structures).

To avoid conflating model capability with robustness, EarthShift uses an “effective robustness” metric. Rather than just ranking models by out of distribution performance, effective robustness measures an architecture’s out of distribution performance relative to a baseline predicted by its ID capability. The team evaluated 13 models, including 8 specialized geospatial foundation models (GFMs), generic vision foundation models (VFMs), and standard fully-supervised architectures; across 10,000 experiments. The results actually show that across all architectures and training setups, models suffer an average 15-20% drop in performance when encountering real-world distribution shifts. While models were surprisingly resilient to temporal shifts (such as season-to-season agricultural changes), they degraded severely under sensor and geographic shifts.

Most surprisingly, domain-specific pre-training on Earth observation archives provided no distributional robustness advantage over generic vision models pretrained on ImageNet, or even over randomly initialised fully-supervised models. In fact, generic ImageNet-pretrained ResNet-50 architectures frequently proved to be the most distributionally robust models tested. Full fine-tuning of model encoders often failed to improve, and sometimes even worsened, effective robustness compared to simply freezing the pre-trained backbone…

Geospatial Datasets

1. Earth system foundation model dataset

The WorldTensor dataset harmonises hundreds of global environmental and socioeconomic variables onto a standardised 0.25-degree spatial grid and an annual temporal framework spanning 1900 to 2025. Access the data here and the code here.

2. Bias-corrected high-resolution climate dataset

The BC-HiRMIP dataset provides globally bias-adjusted climate projections derived from four HighResMIP models at a 0.5° spatial and daily temporal resolution, spanning from 1979 to 2050. Access the data here and the code here.

3. Upper reach transboundary river hydrological dataset

The Mainland Southeast Asia International River Upper Reach Hydrological Dataset (MSAIRHD) compiles historical daily streamflow, sediment concentration, and water level records across 119 monitoring stations in the upper reaches of the Irrawaddy, Salween, Mekong, and Red River basins from 1958 to 1987. You can access the data here and the code here.

4. Remote sensing traffic object segmentation dataset

The NWPU-Traffic dataset provides an optical remote sensing collection containing 1,479 high-resolution images and 31,628 instance-level annotated targets across four major transportation categories: cars, airplanes, ships, and trains. Access the data and code here.

Other useful bits

• NASA’s Jet Propulsion Laboratory has completed the first in-orbit test of an untuned vision-language model, running Google’s Gemma 3 on a satellite. By analysing imagery onboard to generate text descriptions, the system bypasses bandwidth limits by downlinking brief summaries rather than massive raw image files.

• A machine learning study used Google Maps Platform’s Places Insights dataset in BigQuery to account for nearly 86% of home value variation across census tracts in Austin, Texas. The analysis revealed that the quality of nearby commercial amenities (gyms, spas, cafes, etc) served as a primary positive predictor of residential property values, whereas industrial sites like storage facilities and auto-repair corridors significantly depressed local valuations.

• The US Federal Communications Commission has introduced new regulations requiring satellite operators to share real-time location data to mitigate collision risks in increasingly congested orbits. The move has reignited a jurisdictional dispute with US lawmakers who argue that authority over space safety and traffic management should reside with the Department of Commerce.

Jobs

• UFZ is looking for an Environmental Computer Scientist in Leipzig, Germany

• The Allen Institute is looking for a Senior Software Engineer (AI For Planet) in Seattle, US.

• The World Bank is looking for an Extended Term Consultant (Associate Geospatial Platform Engineer) in Washington DC, US.

Just for Fun

ESA’s Euclid space telescope has discovered 31 of the most ancient quasars ever found, including two dating back to when the cosmos was just 670 million years old, setting a new cosmic record and more than doubling the known population of these ultra-early supermassive black holes.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — we put the ‘special’ in geospecial data science… As usual, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Urban Food Security: Graph AI optimises hydroponic nutrient dosing.

• Crop Yield Prediction: Interpretable deep learning improves harvest forecasts.

• European Mobility: Seven mobility types reshape regional policy.

• Forest Height Mapping: Radar and optical data improve accuracy.

• Macroeconomic Data: Global statistics spanning nearly a millennium.

Subscribe now

Research you should know about

1. A graph-based approach to urban food security

As anyone who’s read the news knows, traditional soil-based agriculture is increasingly vulnerable to various issues like extreme weather, soil degradation, and water shortages. Taken together, this leads to a rise in global food insecurity. In response, ‘soilless’ (or is it ‘soil-free’?) methods like hydroponics and aeroponics are gaining popularity for urban food production. However, these controlled-environment systems rely on precise, real-time nutrient dosing. Current systems often use rigid/static dosing rules that don’t really account for the complex, non-linear interactions between dynamic environmental conditions (e.g. temperature or humidity) and a plant’s physiological response. This inflexibility can essentially lead to nutrient waste and increased crop stress.

A new study from Scientific Reports addresses this by introducing the Optimised Multi-Scale Adaptive Graph Neural Network (OMSA-GNN). The framework uses a Raspberry Pi-based network of sensors to monitor conditions like pH, dissolved oxygen, electrical conductivity, and visual plant health. Rather than treating these as isolated metrics, the system treats them as localised geospatial data points. The OMSA-GNN model, fine-tuned by an Improved Sparrow Search Algorithm (ISSA), builds adaptive graphs to map the relationships between these variables, allowing it to predict plant stress and adjust nutrient dosing vectors dynamically.

When evaluated on a dataset of hydroponic lettuce growth, the OMSA-GNN framework outperformed the older, more traditional static models, as well as several other neural network architectures, in both forecasting accuracy and nutrient efficiency. By treating individual sensor nodes as micro-spatial intelligence units, the model was able to detect early signs of physiological stress and automatically adjust the nutrient mix, reducing waste and stabilising yields. This approach offers a highly adaptable, data-driven solution for securing urban food systems against the unpredictability of climate-stressed environments.

You can access the dataset here.

2. An interpretable deep learning model for crop yield prediction

Accurate crop yield prediction is pretty important for global food security and smart agriculture, but it’s a notoriously difficult problem. Agricultural yields are determined by a complex mix of weather, soil, and management practices that all interact over time. Deep learning models have shown promise in this area, but they do struggle with “gradient instability” in the face of early-season weather anomalies (like a spring drought). I.e. these events lose their impact in the model’s memory by the time it predicts the final harvest.

To tackle this, a new paper from Scientific Reports introduces the MHCNN-LSTM-MHA model, a hybrid architecture that tackles agricultural data in a highly structured way. Rather than mixing weather and soil data together at the start, the model uses parallel Multihead Convolutional Neural Networks (MHCNN) to process them separately, preserving their unique characteristics. This data is then fed into a Long Short-Term Memory (LSTM) network to track temporal changes across the growing season. Finally, a Multi-Head Attention (MHA) mechanism acts as the model’s focus, dynamically prioritising specific time steps to ensure critical events aren’t lost.

When tested on a comprehensive 39-year dataset of US soybean yields, the proposed model achieved an impressive 9.86% improvement over the previous best benchmark. They conducted a SHAP analysis and confirmed that the model’s logic aligned with established agronomic principles, heavily weighting factors like solar radiation, maximum temperature, and precipitation. The conclusion, according to the authors, then is this might be more reliable or ‘trustworthy’ than other approaches.

3. Rethinking spatial mobility across Europe

It’s August in Europe (and for the rest of the world for that matter), which means that everyone is on holidays and travelling around - usually in a caravan or a train of some sort (no gross over-generalisations here…). Anyway, a new study from Nature Communications argues that we need to stop treating all movement as the same. The researchers combined data from the Labour Force Survey, Erasmus+ student exchanges, and geotagged X posts to map out seven distinct types of spatial mobility. This included everything from short-term student exchanges and seasonal agricultural work to cross-border commuting and multilocal living, where people actively split their time between multiple residences.

By running these different mobility flows against a huge variety of regional characteristics, the team found that the factors attracting one type of person often repel another. For instance, an increase in a region’s GDP per capita generally leads to an influx of long-term students and permanent migrants, but it actually causes a drop in seasonal workers and long-distance commuters. Digital infrastructure also plays a fascinating role. Faster mobile internet speeds at an origin location tend to boost cross-border commuting and multilocal living, likely because good connectivity makes flexible work arrangements easier. Conversely, at the destination, faster internet is associated with a decrease in seasonal manual labour.

The findings highlight that a one-size-fits-all approach to regional development just doesn’t work. Rather than simply trying to stop outmigration or blindly attract permanent residents, policymakers might be better off leaning into their region’s specific strengths to attract seasonal workers or digital nomads.

You can access the data here.

4. Combining radar and optical data for better forest mapping

Estimating forest height accurately across large areas is a massive challenge in remote sensing, but it can be pretty important for understanding biomass and carbon storage. While SAR techniques like Polarimetric SAR Interferometry (Pol-InSAR) are widely used for this, their performance can suffer when the underlying physics models struggle with complex terrain slopes and varied canopy structures. A new study from IEEE tackles this by expanding on a recently developed hybrid model that combines machine learning with a physical radar model. The researchers realised that while radar data from satellites like TanDEM-X is great for capturing physical structures, adding multispectral optical data from Landsat could provide the extra missing clues about vegetation types and density needed to resolve tricky structural ambiguities.

To put this to the test, the team took an earlier hybrid model that relied solely on TanDEM-X radar features (Model C) and upgraded it by adding four Landsat optical bands: Red, Near-Infrared (NIR), and two Short-Wave Infrared bands (SWIR1 and SWIR2). They trained and tested this new version (Model D) over the diverse, hilly terrain of the Lopé National Park in Gabon, comparing the results against high-precision airborne LiDAR measurements from the AfriSAR campaign. The optical boost made a remarkable difference. Model D reduced the Root Mean Square Error (RMSE) by 13.5% and the Mean Absolute Error (MAE) by 16.6% compared to the radar-only version.

What’s particularly impressive is how well the new model handled difficult topography. The radar-only approach consistently underestimated forest heights on slopes facing away from the sensor, but the inclusion of Landsat spectral data allowed the machine learning component to correct this bias almost entirely on moderate slopes.

Geospatial Datasets

1. Global macroeconomic statistics dataset

The Global Macro Database compiles 46 macroeconomic variables across 239 countries, harmonising 160 historical and contemporary sources into continuous country-level series. The data runs from 1086 to 2025 with forecasts extending to 2030. Access the data here and code here.

2. Abyssal ocean temperature dataset

The Stratus Ocean Reference Station dataset provides a 13-year continuous time series (2012 to 2025) of deep ocean temperature observations at abyssal depths between 4,191 and 4,526 m in the Southeast Pacific. Access the data here and the code here.

3. Global snow-free leaf area index dataset

The Global Snow-free Leaf Area Index dataset provides monthly global leaf area index (LAI) and stem area index (SAI) fields at a 500-m spatial resolution spanning from 1985 to 2020. Access the code here. The links to the datasets for each year (1985-2020) can be found under Data Records of the article.

4. Hybrid global river discharge dataset

The GLORIF1 dataset provides a monthly global river discharge inventory spanning 1979 to 2019 at a 30-arcminute spatial resolution (approximately 50 km at the equator). Access the data here and the code here.

Other useful bits

• Google’s Isochrones API generates reachable area polygons from an origin point based on actual road network travel times rather than simple straight-line distances. This allows developers to measure true accessibility for practical applications like delivery logistics, real estate commute planning, and urban service mapping.

• Sentinel-2 Paint is an open-source web app that reconstructs user-uploaded images as mosaics using real, geolocated satellite imagery patches from the Sentinel-2 archive. It indexes nearly 93,000 unique surface colours extracted from global imagery.

• NASA has mandated that its 11 billion dollar Habitable Worlds Observatory will be engineered for robotic in-space servicing, assembly, and maintenance. Situated at the Sun-Earth Lagrange point 2, the flagship telescope will feature modular components and standardised interfaces so robotic spacecraft can upgrade and repair its systems in orbit.

• A non-profit is investing in open-source geospatial AI tools to help humanitarian organisations like the WFP predict supply chain disruptions and reroute food aid more efficiently. By identifying structural bottlenecks and road closures in vulnerable regions like Afghanistan before they occur, the initiative aims to mitigate hunger and ensure timely delivery amidst growing global food insecurity.

Jobs

• Mercy Corps are looking for a remote GIS Intern

• The Nature Conservatory is looking for a Natural Climate Solutions Data Scientist in the US

• The FAO is looking for a bunch of Geospatial Data Science Consultants

Just for Fun

A daytime telescopic image captured from British Columbia, Canada, highlights the moment Venus re-emerged from behind the bright limb of a crescent Moon following a one-hour lunar occultation on 17 June.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge. We’re like the geospatial newsletter equivalent of Gemini - we used to be cool last year, but we’re slightly less cool with each passing month... In any case, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Population Mapping: Foundation models improve population estimates in data-poor regions.

• Annotation-Free AI: Self-training model eliminates manual geospatial labels.

• Mobility Modelling: Hierarchical approach accelerates large-scale movement simulations.

• Foundation Models: Audit exposes major benchmarking and reproducibility issues.

• Settlement Data: Global 10 metre settlement dynamics dataset released.

Subscribe now

Research you should know about

1. Rethinking population mapping with foundation models

When planning infrastructure or responding to disasters, having accurate, up-to-date population estimates is obviously pretty important. However, as anyone who’s used survey data before, it can be outdated or spatially imprecise, especially in rapidly developing countries. Traditionally, demographers have filled these gaps by estimating populations using a bunch of hand-picked geospatial covariates like satellite imagery of nighttime lights, road networks, and building density. While effective, assembling these datasets is a pain. A new paper tests whether we can skip the manual assembly and instead use the Population Dynamics Foundation Model (PDFM). This model generates embeddings by compressing a bunch of different data, such as search trends, maps, and local activity levels, into a single, reusable mathematical representation of a place (btw, I did a deep dive on embeddings here).

To benchmark this, the researchers compared the predictive power of PDFM embeddings against 23 standard geospatial covariates for estimating subnational populations in Brazil, Nigeria, and the United States. They found that PDFM successfully improved predictive fit, reducing unexplained variance by a median of 20.1% across various machine learning models. However, the performance was pretty uneven. PDFM provided the biggest boost in large, less-developed regions where traditional markers like building density and road networks were weak or absent. In highly developed areas where traditional covariates already captured settlement patterns perfectly, PDFM added very little value.

The study also uncovered a major limitation regarding scale. While PDFM embeddings were highly accurate at the specific spatial resolution they were trained for (e.g., zip codes), their performance broke down predictably when the researchers attempted to aggregate them to larger areas like counties. In contrast, standard geospatial covariates proved much more flexible across different spatial scales. The researchers conclude that while embeddings are useful tools for data-poor environments, they shouldn’t outright replace traditional methods. Instead, the future of population modelling likely lies in hybrid approaches that combine the nuanced, human-activity signals of embeddings with physical geospatial covariates.

2. Eliminating manual annotations for geospatial reasoning

Geospatial reasoning (or I guess any reasoning for that matter) requires models to understand fuzzy, abstract user queries and map them to precise physical locations, like finding the best area to set up emergency shelters after an earthquake. Recent advances in Multimodal Large Language Models (MLLMs) have made it possible for AI to autonomously generate the logical steps to answer these queries. However, the big issue is that teaching these models to actually output the correct geographic coordinates still requires massive amounts of human-annotated bounding boxes. This reliance on labels prevents these models from freely learning and self-evolving using the petabytes of unlabelled satellite imagery currently available.

To address this, a new study introduces RemoteZero, a training framework that requires absolutely zero human bounding-box annotations. The researchers noticed that MLLMs are much better at verifying if a given cropped image matches a text description (the “Eye”) than they are at generating raw coordinates from scratch (the “Hand”). So, RemoteZero uses a “Generate-Crop-Verify” loop. The model basicaly guesses a location, crops that area from the image, and then uses a verifier to check if the crop semantically matches the query. This semantic yes/no score is then fed back into the model as a reward using Group Relative Policy Optimization (GRPO), teaching it to find the right locations without ever seeing a human label.

Interestingly, RemoteZero enables the model to teach itself. Instead of relying on a larger, external model to act as the verifier, RemoteZero can use its own frozen policy from a previous training round to verify its current guesses, creating a continuous loop of self-evolution. When tested against fully supervised baselines that rely on thousands of manual annotations, the self-evolving RemoteZero model actually outperformed them, scoring 71.29% accuracy on the EarthReason benchmark. This proves that intrinsic semantic verification is a viable path forward, potentially unlocking the ability to train powerful geospatial AI using entirely unlabelled satellite data.

3. A smarter way to model mobility

Simulating how users move around in large-scale networks, like fog computing environments, can be pretty difficult without good real-world data. When researchers try to build mobility models from scratch, they often run into massive computational bottlenecks because tracking every single access point in a large area is overwhelming. A new study tackles this issue by proposing a hierarchical method that groups Wi-Fi access points based on their geospatial features. Rather than treating every access point as an isolated spot, they’ve organised them into nested levels, such as moving from an entire building down to a specific wing, then a floor, and finally the individual access point. This top-down approach means it’s a lot easier to track user trajectories and simulate realistic movement without getting bogged down by the sheer volume of network data.

The team analysed wireless access logs from the University of the Balearic Islands campus, using tracking data from the Aruba Location Engine. By applying clustering algorithms to profile user behaviour at different granularities, they generated transition matrices that accurately mapped out where people were likely to go next. The results were pretty impressive. Compared to flat, non-hierarchical models, they layered approach massively reduced the computational complexity. It actually slashed the execution time needed for clustering from several hours down to just a few minutes, while drastically cutting the optimal number of clusters required.

4. The messy state of geospatial foundation models

I know, I know. Another Spatial Edge newsletter, another foundation model paper… But as long time readers may know, I’m still a bit skeptical about how useful they are (more info on this here). But a massive audit of 152 papers reveals a pretty big problem, which is that nobody actually knows what the state of the art is. The researchers found that the current literature is a bit of a mess when it comes to standardising evaluations and testing protocols. E.g. they documented 46 cases where different papers reported wildly different scores (sometimes off by tens of points) for the exact same model and benchmark. Without shared controls or a common evaluation harness, comparing these models is nearly impossible.

The issues go deeper than just mixed-up scorecards though. The audit discovered that 39% of papers do not even release their model weights 🤯. On top of that, researchers are frequently tweaking both the model architecture and the pretraining data at the same time without isolating the variables. This means when a new model claims a massive leap in accuracy, you can’t really tell if the improvement came from a new design or just a massive new dataset. It creates a confusing environment where weak models can hide behind massive datasets, and actual architectural progress gets lost in the noise.

Geospatial Datasets

1. Global settlement exposure dataset

The World Settlement Footprint dataset provides global 10-m resolution settlement dynamics published as a cloud-native GeoZarr layer. Access the data here and the platform here.

2. Urban rooftop reflectivity dataset

The Heat Resilience dataset provides high-resolution, building-level rooftop reflectivity data across more than 50 global cities to support urban heat mitigation. Produced by fusing 10-metre Sentinel-2 satellite observations with 30-centimetre commercial satellite imagery, the model reconstructs granular albedo profiles for individual structures. Access the data and documentation here.

3. Small-area global election returns dataset

The Small-Area Global Elections (SAGE) dataset compiles lower-house parliamentary and presidential election returns for 110 countries at the smallest unit published by local electoral authorities. The repository contains roughly ten billion votes across more than eight million geocoded units, with candidate and political party identifiers harmonised across multiple languages. Access the data here and the code here.

Other useful bits

• I really loved this article from Bruno Sanchez. He argues that Europe consistently loses its home-grown space innovations to foreign buyers because public funding focuses on de-risking supply rather than de-risking market demand. To bridge the downstream investment gap, ESA must act as a committed anchor customer through fixed-price contracts that de-risk future commercial demand and keep scaling companies rooted in Europe.

• SkyFi has launched SkyFi for ArcGIS, bringing on-demand satellite imagery directly into Esri workflows via a native Experience Builder widget and live WMTS streaming. The integration allows users to search archives, task satellites, and stream map layers across ArcGIS platforms without switching applications or manually downloading files.

• The 2026–2027 World Bank Country Income Classifications reveal that six countries advanced to higher income categories through different economic mechanisms, including export-led expansion, broad-based domestic growth, and recovery from financial crisis. Non-growth factors such as statistical revisions to national accounts and downward population census adjustments also played decisive roles in pushing certain economies past the per-capita income thresholds.

• UNESCO has launched an open-learning course on Flood Hazard and Exposure Mapping to train participants in flood modeling, risk assessment, and exposure analysis. Featuring hands-on exercises and real-world case studies from Mozambique, the program equips learners to evaluate urban, coastal, and riverine flood impacts for informed decision-making.

Jobs

• Arsenal FC is looking for a Research Engineer under their Data Analytics team.

• The World Bank is looking for a Data Scientist (Consultant) based in Washington.

• WSC is looking for a remote Data Management Specialist based in Canada.

• UNDP is looking for a Data Assistant based in Rio de Janeiro.

• Esri Netherlands is looking for an Analytics Consultant based in Rotterdam.

Just for Fun

A new Smithsonian exhibition marks the US 250th anniversary by mapping the country through its natural contours, such as watersheds, biomes, and fossil beds.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — a newsletter that’s as anticipated as The Odyssey. The aim, as usual, is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Fine-Grained Damage Assessment: Drone AI improves post-disaster mapping.

• Remote Sensing Agents: RS-Claw streamlines AI tool selection.

• Cross-Border Generalisation: Foundation models struggle across countries.

• Night-Time Dataset: Sentinel-2 releases high-res nighttime imagery.

Subscribe now

Research you should know about

1. Fine-grained damage assessment from drone imagery

Rapid and accurate damage assessment is pretty important after natural disasters, but manual field surveys are often too slow or can be too dangerous to conduct. So automated semantic segmentation models offer a faster alternative, yet they frequently struggle to provide the fine-grained detail required for effective emergency response. When researchers feed high-resolution drone imagery into these models, they typically downsample the images to fit into memory, which actually has the effect of destroying subtle textures that distinguish minor roof damage from major structural collapse. Furthermore, the datasets are heavily imbalanced, with vast amounts of background scenery and very few examples of critically damaged buildings, which often causes standard models to ignore these rare but important hazards.

DA-SegFormer, an adaptation of the SegFormer architecture, is specifically tuned to extract disaster data from high-resolution drone imagery. Instead of aggressive downsampling, the authors use a resolution-preserving protocol where the model processes images in sliding windows, keeping native details intact so it can accurately identify fine-grained damage. To combat the severe class imbalance, they introduced a sampling strategy that forces the model to focus on rare damage cases. They also combined Online Hard Example Mining with Dice Loss, which effectively forces the network to concentrate on the visually subtle decision boundaries between different levels of damage rather than just the easy-to-identify background.

The model shows real promise for emergency responders, as it outperformed the baseline on the RescueNet benchmark with a 74.61% mean intersection over union. Interestingly, it delivered double-digit gains for critical damage classes, identifying minor and major damage far more accurately than standard models. These granular improvements allow for much more reliable automated assessments that help responders allocate help where it is needed most.

2. OpenClaw for Remote Sensing

If you go on X these days, you’re going to be drowning in all the chatter about AI agents. And it’s no surprise that the remote sensing community is also looking at agents. One of the ongoing problems though, is how these agents select their tools. Most current setups just dump the entire list of available tools into the system prompt. Since the remote sensing tool ecosystem is massive, this leads to context bloat and can oftentimes lead to the agent choosing the wrong tool. It creates a major trade-off where agents either struggle to fit everything in their memory or end up omitting critical tools entirely, as they are essentially passive recipients of a flat, static list.

To solve this, researchers introduce RS-Claw. Rather than being passive recipients of a static tool list, RS-Claw agents navigate a hierarchical skill tree. The model essentially discovers and loads tools on demand, moving from a high-level skill summary down to detailed execution documents only when necessary. This progressive disclosure approach keeps the reasoning space clean and free of semantic noise. When tested on the Earth-Bench benchmark, RS-Claw outperformed existing passive baselines across various reasoning tasks, successfully filtering out irrelevant information while slashing input token requirements by up to 86%.

The results show that treating tool acquisition as a dynamic process rather than a static setup significantly improves agent reliability in complex, long-horizon tasks. This is a pretty big shift for geospatial AI, as it allows for much larger, more diverse tool libraries to be used effectively without overwhelming the model.

3. Do foundation models really generalise across borders?

Researchers often hope that foundation models trained on massive satellite archives will provide universal visual features that work anywhere in the world. A new study puts this to the test by using a Leave-One-Country-Out evaluation protocol to see if these models can accurately predict smallholder maize yields across different countries in sub-Saharan Africa. By training models in four countries and testing them on a fifth, the author aimed to find out if geospatial foundation models, like IBM and NASA’s Prithvi-EO, could overcome the usual struggles of cross-country yield transfer.

The results were pretty interesting. While models performed reasonably well when tested on data from the same country, they completely collapsed when asked to predict yields in a new, unseen country, often performing worse than a naive baseline that simply predicts the training set average. Surprisingly, the frozen embeddings from the Prithvi foundation model didn’t provide any meaningful advantage over a standard set of 10-band spectral medians. The author argues that this isn’t necessarily a failure of the foundation models themselves, but rather a reflection of fundamental data distribution shifts in yield across different national contexts that satellite imagery alone cannot easily bridge.

This study serves as a necessary reality check for the field, demonstrating that geospatial pre-training alone can’t close the generalisation gap when yield statistics vary wildly between regions. It establishes a clear, reproducible negative benchmark that should push future research toward more robust domain adaptation and meta-learning techniques.

Geospatial Datasets

1. Sentinel-2 night-time campaign dataset

The Sentinel-2 night-time campaign dataset provides a collection of 56 night-time satellite acquisitions captured during a dedicated observation campaign in December 2025. You can access the data here.

2. Southeast Asian high-resolution climate dataset

The MSEA-Daily dataset provides a high-resolution, gridded daily climate inventory at a 4-km 1/24° spatial scale for mainland Southeast Asia, covering Myanmar, Thailand, Laos, Cambodia, and Vietnam from 1981 to 2014. You can access the data here and the code here.

3. Climate Data Store expanded dataset

The Copernicus Climate Change Service (C3S) has expanded its Climate Data Store (CDS) with a bunch of new open-access climate records and sectoral indicators spanning the atmosphere, land, ocean, cryosphere, and water cycle. You can access CDS here.

4. Cross-platform flood detection dataset

The Sen2GF3Floods dataset provides a multi-source flood mapping resource consisting of 21,483 standardised 10-m resolution image patches (256 × 256 pixels) covering nine major global flood events. You can access the data here and the code here.

Other useful bits

• Google Research found that in 10 major US cities, systematically rerouting under 2% of navigation app users away from bottlenecks can measurably improve traffic speeds and reduce carbon emissions for all road users. By dispersing traffic across underutilised peripheral roads, this is a scalable approach to enhancing network-wide efficiency and urban sustainability.

• Planet Labs is advancing its "Planetary Intelligence" initiative by embedding AI across its satellite hardware, data processing, and user applications to deliver near-real-time Earth observation insights. By integrating edge compute into satellites, sharpening image resolution via AI, and testing a natural-language mapping agent, the company aims to make complex global monitoring accessible to non-technical users.

• European Southern Observatory says that surpassing 100,000 satellites in orbit could render ground-based telescopes obsolete by causing irreversible light pollution and image corruption. The research notes that proposed megaconstellations, including thousands of highly reflective orbital mirrors, threaten to brighten the night sky by up to 300% and permanently disrupt global astronomical observations.

Jobs

• Esri Netherlands is looking for an Analytics Consultant based in Rotterdam.

• UNOPS is looking for an ICT Officer based in Valencia.

• UNDP is looking for a Spatial Planning and GIS Expert based in Malaysia.

• ESA is accepting applications for their mid-year internship opportunities under:

  • Spaceship EAC Team

  • Spaceship ECSAT Team

  • LUNA Analog Facility Team

  • Vulcan Team

Just for Fun

ESA has marked the 1000th image of its "Earth from Space" series with a Copernicus Sentinel-3 satellite capture of Florida, Cuba, and the Bahamas, returning to the exact region featured in the programme's inaugural 2004 edition.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — the GPT-5.6 Sol of geospatial news. We’re not as impressive as some other news outlets, but we’ll get you where you need to go… In any case, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• US Census: Harmonising 30 years of housing data.

• Green Growth: Satellites track cleaner economic growth.

• Africa’s Power: Mapping future electricity expansion.

• Methane Trends: Wetlands mask emission reductions.

• Earthquake Damage: Satellite dataset for building damage.

Subscribe now

Research you should know about

1. Fixing the fragmented history of US census data

For researchers trying to track long-term socioeconomic trends in the United States, the decennial census can be a pain... Every ten years, the census redrawing process updates the boundaries of ‘block groups’ to reflect population shifts and urban development. While this keeps current data accurate, it basically fractures the historical record, creating geographic gaps and mismatches that make it almost impossible to directly compare modern housing statistics against those from past decades. A new study published in Scientific Data tries to address this exact problem, presenting a geospatial framework that successfully reconstructs lost or misaligned historical housing data and harmonises it to modern census boundaries.

Using California as a primary test case, the researchers pulled block-group level housing data from the 1990, 2000, 2010, and 2020 censuses. To fix the thousands of missing or incompatible data points across the older datasets, they employed Ordinary Kriging (an interpolation method that essentially estimates missing values by analysing the spatial patterns of the surrounding data). Once these historical gaps were filled, the team used zonal statistics to map the repaired historical data onto the most recent 2020 census block group boundaries. The end result is a single, seamless dataset that allows for direct, apples-to-apples comparisons of California’s median housing values across a 30-year span.

This framework resolves a major blind spot in longitudinal research, providing urban planners and policymakers with a reliable, continuous view of historical housing trends without the noise of shifting administrative borders.

2. Tracking green growth from space

Cities generate over 60% of the world’s GDP and roughly 70% of its greenhouse gas emissions, making them the ultimate battleground for the concept of “green growth”. The problem is that measuring this at a local level has always been a nightmare. Relying on self-reported city emission inventories is messy, and global models are too broad to capture what’s actually happening block by block. A new paper from Nature Cities tackles this by turning to space, using satellites to directly monitor nitrogen dioxide (NO₂) pollution across 5,435 cities worldwide between 2019 and 2024.

The researchers combined this high-resolution satellite pollution data with fine-grained local GDP estimates, and fed both into an advanced statistical model that stripped away the “noise” of local weather patterns. This allowed them to map the “decoupling” of economic growth from fossil fuels. The results show a massive shift: roughly 80% of the 2,475 cities with significant trends successfully achieved relative decoupling, acting as “cleaner + richer” hubs. This trend was heavily concentrated in China, Europe, and North America, where cities managed to grow their economies while driving down their NO₂ footprints, likely through a combination of strict regulations, electrification, and a shift away from heavy industry.

However, the data also highlighted a concerning counter-trend. Around 16% of cities (mostly located in India, Iran, and Russia) fell into the “dirtier + richer” category, locking themselves into a trajectory where economic expansion remains fundamentally tied to fossil-fuel-burning infrastructure and unregulated industrial growth. This new satellite-based framework provides a highly objective, globally consistent tool for policymakers to monitor the real-time effectiveness of green interventions.

3. A look at Africa's power future

Africa’s electricity sector is growing rapidly to meet massive demand, but keeping track of exactly where and how this power is being generated has been surprisingly difficult. A new study from Nature Communications changes that by introducing a detailed spatial database of African power plants. The researchers spent huge amounts of time data mining open access sources to map out 3,139 operational, under construction, and planned power facilities across the continent. By tracking this expansion up to 2030, they have given us a pretty incredible look at how the continent’s energy landscape is shifting over the next few years.

The numbers point to a massive boom in energy generation. The researchers forecast a 57% increase in electricity production between 2023 and 2030. While fossil fuels are still set to dominate, renewables are picking up serious momentum and are expected to grow from 19% to 34% of the total energy mix. However, this growth comes with some pretty big trade-offs. The surge in new hydropower dams will require a massive amount of water, which is going to put intense pressure on already stressed river basins like the Zambezi, Nile, and Congo. At the same time, the ongoing reliance on coal and natural gas means carbon emissions will continue to climb, even though the continent’s current build rate is actually falling slightly short of its international climate commitments.

4. Natural wetlands drive global methane rebound

Methane is a greenhouse gas that has been rapidly accumulating in our atmosphere, with growth rates hitting record highs in 2020 and 2021 before slowing down in 2023. While international agreements, like the Global Methane Pledge, aim to slash anthropogenic methane emissions by 30% by 2030, one of the big challenges is untangling human-made emissions from natural ones. A new paper from Nature Communications addresses this by using a blend of satellite data to track global methane budgets from 2019 to 2024, revealing that massive fluctuations in the Earth’s natural wetlands and atmospheric chemistry are actively masking human mitigation efforts.

The team used an advanced atmospheric inversion system called GONGGA, feeding it high-resolution satellite imagery from TROPOMI and GOSAT. They found that during the 2020–2022 La Niña period, the “methane sink” (i.e. the chemical process where hydroxyl radicals naturally scrub methane from the atmosphere) weakened significantly, driving up global methane levels. However, as the El Niño weather pattern took hold in 2023, the sink recovered and massive droughts across South America suppressed wetland emissions, bringing the atmospheric methane growth rate back down to 2019 levels. But in 2024, as La Niña returned and the droughts broke, wetland emissions rebounded violently. This massive natural release of methane effectively offset the recovering atmospheric sink, resulting in a near-baseline growth rate that hid the underlying surge in emissions.

The study highlights a pretty big problem for global climate policy. The natural variability of wetland emissions and the atmospheric sink combined to create an annual swing of 12.6 million tonnes of methane. This is essentially a figure large enough to entirely erase a full year of the emission cuts promised under the Global Methane Pledge. The researchers stress that as climate change makes weather patterns like La Niña more frequent, these natural methane releases will likely intensify. This means that tracking progress on global emission targets will require sophisticated satellite monitoring systems that can explicitly separate natural wetland surges from actual human emission reductions.

Geospatial Datasets

1. Paleoclimate reconstruction dataset

The DPastCliM-NA dataset provides a bias-corrected, high-resolution monthly reconstruction of temperature and precipitation for North America over the past 2,000 years, featuring explicit uncertainty estimates. You can access the data here and the code here.

2. Earthquake building damage dataset

The Turkey Earthquake change detection dataset (TUE-CD) comprises 1,656 pairs of bi-temporal satellite images captured by the WorldView-2 satellite to assess building damage after the February 2023 earthquake. You can access TUE-CD here and MSI-Net here.

3. Vectorised building footprint dataset

The PCFootprint dataset provides the first large-scale public baseline for extracting vectorised building footprints from airborne laser scanning point clouds. You can access the data here.

4. Disaster risk knowledge graph dataset

An AI-powered data pipeline transforms millions of global news articles from 2014 to 2024 into structured disaster risk knowledge graphs. You can access the data here, the code here, and the interactive dashboard here.

Other useful bits

• Google’s Gemini 3.1 model allows organisations to automate the transformation of unstructured street-level imagery into structured spatial databases through multimodal visual reasoning. By using bounding box detection and integrated code execution, this approach removes the need for training bespoke computer vision models and streamlines complex infrastructure analysis.

• Fine-scale vegetation mapping in West Kalimantan reveals that high-res data is critical for identifying fragmented forests and community agroforestry systems often obscured by conventional land-use planning. This mapping project provides local communities and policymakers with an accurate evidence base to protect biodiversity and prevent illegal plantation expansion into protected peatlands.

• Innovators are tackling the energy supply bottleneck created by AI power demands by developing space-based solar technologies that beam continuous energy directly to terrestrial grids. Rather than necessitating new infrastructure, this method uses near-infrared light to augment the output of existing solar farms, significantly increasing their operational value and reliability.

Jobs

• Vantor is looking for a (1) Geospatial Data Scientist and a (2) Senior Geospatial Data Engineer based in McLean.

• The University of Illinois is looking for a Research Specialist (GIS Analyst) under their Department of Paediatrics based in Chicago.

• Planet is looking for a Pre-Sales Solutions Architect based in Latin America (preferably Colombia).

• ESA is accepting applications for their mid-year internship opportunities under:

  • Spaceship EAC Team

  • Spaceship ECSAT Team

  • LUNA Analog Facility Team

  • Vulcan Team

Just for Fun

South Korean map service Kakao Map has gone viral for providing unexpectedly detailed geographical data on North Korea, including labels for mountains, universities, and railway stops that remain largely obscured on competing platforms.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — your weekly map to the latest geospatial news. The aim, as always, is to make you a better geospatial data scientist in less than five minutes a week.

First up, I’ll be heading to the AI For Good Summit in Geneva next Tuesday, so hit me up if you’ll be around. I’m always up for a coffee and a geospatial chat.

In today’s newsletter:

• Rural Markets: Satellites track weekly market activity.

• Urban Hazards: Geospatial models flag danger zones.

• Groundwater Loss: Urban sprawl threatens aquifers.

• Urban Weather: Atlanta gets high-res meteorology data.

• AI Economy: Stanford tracks AI’s economic impacts.

• 5G Networks: Glasgow releases urban performance data.

Subscribe now

Research you should know about

1. A new way to measure rural economic activity

In many rural areas, weekly markets are where a lot of the local economy actually happens. Farmers sell crops, traders move goods around, and households buy what they need. But these markets are often informal, scattered across remote areas, and poorly recorded in official data. A new Nature Communications study shows that satellites can help fill this gap. The basic idea is that outdoor markets look different on market days than on other days, because of stalls, crowds, vehicles, and temporary structures. A single satellite image might barely show this, but a long time series of images can reveal a repeated weekly pattern.

The authors use PlanetScope imagery to compare each image with nearby non-market-day reference images, then look for places where brightness and colour change on a regular day-of-week cycle. They validate the approach using known marketplace data from Kenya, Malawi, and Mozambique, where the method achieves high precision, generally above 90% across a broad range of signal strengths. They then apply it across Ethiopia, excluding Addis Ababa, and map 1,776 periodic markets between 2017 and 2024. The resulting map is pretty revealing: around 70% of Ethiopia’s population lives within 10 km of one of these detected markets, and 63% of the markets sit in places with no measurable night-time light emissions. So this picks up a kind of rural economic activity that nightlights would mostly miss.

The activity data is also interesting. Market activity rises and falls with the agricultural calendar, increasing around harvest periods and responding to rainfall shocks. A one standard deviation increase in growing-season rainfall is associated with a roughly 4.2 point increase in harvest-season market activity. The authors also use the data to track disruption during Ethiopia’s recent conflict, finding that periods with more conflict events generally line up with lower market activity. The method has limits, especially where markets are covered, hidden by trees, very cloudy, or not operating around the satellite overpass time. But as a way to monitor rural economic life at high frequency, especially where surveys are sparse or unsafe, this is a pretty neat addition to the geospatial toolkit

2. Spotting urban danger zones with geospatial models

A new Scientific Reports paper looks at a pretty useful problem in urban remote sensing: how to monitor several hazards at the same time. Most satellite-based hazard studies focus on one thing, like floods, wildfire risk, or land movement. This paper tries to bring these together by combining AI with several sources of satellite imagery to map four hazards across two areas in Puglia, southern Italy: floods, land displacement, sediment connectivity, and urban wildfires.

The authors used a mix of Sentinel-1, Sentinel-2, COSMO-SkyMed, and SAOCOM data, alongside environmental and human-made features like elevation, slope, rainfall, soil stability, road distance, land cover, and population density. They trained separate random forest models for each hazard on 100 x 100 m grid cells, then used SHAP analysis to see which factors were actually driving the predictions. This is the interesting bit: the model shows why a place is being flagged. For example, flood risk was strongly linked to drainage position, elevation, soil thickness, and satellite-derived flood probability, while wildfire risk was mainly explained by fuel availability, land cover, and fire climate conditions.

The results were fairly strong, especially for land displacement, sediment connectivity, and wildfires. The multi-source approach generally beat single-hazard models, with big gains for land displacement in both study areas. The SHAP analysis also picked up some useful local patterns. In Gargano, steep slopes and post-wildfire conditions helped explain land instability and sediment movement. In Bari, land displacement was more closely linked to roads, pointing to the role of construction, altered drainage, and other human pressures. The broader takeaway is that multi-hazard mapping works best when it treats hazards as connected systems, rather than separate layers on a map.

3. The toll of urban sprawl on groundwater

As cities continue to expand rapidly around the globe, they transform the natural landscape by replacing soil and vegetation with concrete and asphalt. This unchecked urban sprawl poses a bit of a threat to underground aquifers, which rely on permeable land to soak up rainfall and replenish their stores. However, the exact impact of this urban growth on groundwater recharge and quality has been difficult to map and quantify on a city-wide scale. A new paper from Scientific Reports addresses this gap by focusing on Nnewi, a rapidly expanding industrial city in southeastern Nigeria, using a combination of remote sensing satellites and GIS to analyse changes over the past decade.

The researchers used Landsat imagery from 2013 and 2024 to map the changing landscape, feeding the data into a GIS model to calculate groundwater recharge potential. The results were pretty big. Over the eleven-year period, dense vegetation plummeted by 71%, while impervious, built-up surfaces expanded significantly to cover over 11% of the total area. Crucially, the model revealed that areas capable of recharging the aquifer now make up just 28% of the city. Furthermore, the expansion of concrete and loss of vegetation not only starved the aquifers of water but directly caused water quality to plummet, with industrial and high-density residential areas showing dangerous spikes in nitrates, heavy metals, and dissolved solids.

The study proves that as a city paves over its natural landscape, it effectively suffocates its own water supply while simultaneously trapping and funnelling pollutants directly into the remaining water table. These findings serve as a bit of a warning for rapidly urbanising cities, especially in Sub-Saharan Africa, where groundwater is often the primary source of drinking water. The authors stress that city planners must urgently incorporate “green infrastructure,” such as permeable pavements and urban parks, to restore the natural water cycle before the damage to local aquifers becomes irreversible.

Geospatial Datasets

1. High-res urban meteorology dataset

The HUMID-Atlanta dataset provides a 1-square-kilometre resolution hourly meteorological record covering the Atlanta metropolitan area from 2010 to 2023. Access the data here and the code here.

2. AI economic indicators

Stanford Digital Economy Lab’s AI Economic Indicators provide a comprehensive framework to monitor the macroeconomic and labour market impacts of AI across the US. It combines three measurement tools: the Canaries Dashboard for payroll employment tracking, the Takeoff Tracker for explosive economic growth indicators, and the Adoption Monitor for firm-level survey results. Access the indicators here.

3. Land-atmosphere coupling metrics dataset

The Global Observationally-Based Land-Atmosphere Coupling Metrics (GOLAM) dataset provides global fields of land-atmosphere interaction parameters at spatial resolutions of 0.1° and 0.25°. Access the data here and the code here.

4. Urban 5G network performance dataset

The Glasgow Public and Private 5G Performance Dataset provides 720 empirical outdoor network measurements collected across 15 Glasgow neighbourhoods over a three-day period in April 2025. Access the data and code here.

Other useful bits

• A comparative satellite analysis has highlighted 10 global water bodies suffering from severe "continental drying" caused by climate change and unsustainable land use. Long-term imagery reveals that critical freshwater sources, including Argentina's Parana River, Iran's Lake Urmia, and the South Aral Sea, have experienced drastic volume reductions that threaten local ecosystems and regional water security.

• Google Research has developed a high-res deep learning framework that converts pixel-based satellite imagery of agricultural landscapes into a vectorised dataset of fine-scale ecological features. This automated pipeline uses Google Earth AI and Google Earth Engine to programmatically classify and map millions of small-scale vegetation structures across England, providing a precise inventory to support nature restoration without compromising food security.

• The open-access Harvest2Market platform, developed by NASA Harvest, centralises satellite imagery, market indicators, shipping data, and global crop reports to bridge information silos in agricultural monitoring. This web-based system enables analysts to evaluate food supply chain risks by mapping how regional events, such as severe weather or trade disruptions, impact interconnected global markets.

• A satellite has successfully utilised a vision-language model in orbit to identify specific environmental features and infrastructure from natural language queries without ground-based human analysis. The demonstration, conducted on Loft Orbital's YAM-9 spacecraft using a streamlined version of Google DeepMind’s Gemma 3 model, proves the viability of on-orbit data triage and paves the way for autonomous, real-time monitoring constellations.

Jobs

• EIB is looking for (1) a Data Warehouse Officer and (2) an Associate DevSecOps Engineer, both based in Luxembourg.

• UNOOSA Germany is looking for a GIS / Remote Sensing Expert based in Bonn.

• Médecins Sans Frontières UK is looking for (1) a Missing Maps Coordinator and (2) a GIS Specialist (Maternity Cover) based in London

• IOM is looking for a Data and Research Intern based in Vienna

Just for Fun

Back-on-Track.eu has launched an interactive 2026 European night train map tracking 205 regular sleeper lines, highlighting five new routes alongside ten closures.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — we’re sort of like the R of the geospatial world. Free, intuitive, but for some reason people still keep going back to Stat…In any case, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Earthquake Risk: Bayesian models predict building-level damage.

• Disaster Tracking: High-frequency satellites monitor fires and storms.

• Wind Siting: AI identifies optimal wind farm locations.

• Smart Farming: Decentralised AI improves pest management.

• Field Mapping: Three billion agricultural fields mapped globally.

Subscribe now

Research you should know about

1. Predicting earthquake damage with physics and statistics

Earthquakes pose a massive threat to dense urban areas, but predicting exactly how a city will hold up during a major tremor can be pretty complex. Standard risk assessments often rely on simplified charts or historical data, which can miss the nuanced structural differences between individual buildings. A new paper from Scientific Reports presents a large-scale seismic risk framework that combines rigorous physics-based structural modelling with the predictive power of Bayesian networks. By focusing on District 2 of Tehran as a case study, the team managed to evaluate thousands of buildings to map out precise zones of vulnerability.

The researchers categorised the district’s buildings based on their age, number of storeys, and structural materials (such as steel or reinforced concrete). They then ran intensive simulations to see how each building type would react to varying earthquake intensities. Because it’s obviously impossible to perfectly predict every variable in a sprawling city, the team fed their simulation results into a Bayesian probabilistic network, which is a statistical model that excels at handling uncertainty. The results revealed that newer buildings generally fare better, but specific vulnerabilities stood out. For instance, reinforced concrete structures were more prone to damage from horizontal shifting (drift), while steel buildings suffered more from raw shaking acceleration. Alarmingly, the model pinpointed two specific zones in the district facing up to a 59% chance of complete destruction in a severe earthquake.

This granular, data-driven approach gives city planners and emergency responders a bit more of a sharper tool for identifying weak points in urban infrastructure before disaster strikes.

2. Tracking fast-moving disasters from space

As climate-related disasters like wildfires and flash floods become more frequent and severe, the need for real-time monitoring from space has never been greater. Earth Observation (EO) models powered by artificial intelligence have made massive leaps recently, with developers building geospatial foundation models (more on that here and here), that are trained on vast amounts of unlabelled satellite imagery. However, nearly all of these existing models are trained on imagery from polar-orbiting satellites, which provide incredibly detailed, high-resolution pictures but only pass over the same spot on Earth every few days. This makes them entirely unsuitable for tracking fast-moving, dynamic events like a rapidly spreading forest fire or a developing storm system.

A new study introduces HighFM, a new foundation model explicitly designed for high-frequency environmental monitoring. Instead of using highly detailed but infrequent images, the team trained their model on more than 2 terabytes of imagery from the Meteosat Second Generation platform. These geostationary satellites provide lower-resolution images but update every 15 minutes, offering a near-constant view of the Earth. To handle this unique data, the researchers adapted a masked autoencoder architecture to retain fine-grained, minute-by-minute temporal information that other models typically discard.

To test HighFM, the researchers asked the model to identify active fires and map cloud cover. When benchmarked against traditional AI models and even other state-of-the-art EO foundation models, HighFM consistently proved superior. The model’s ability to understand the rapid, short-term variability between images allowed it to detect fires and clouds with greater accuracy and fewer false alarms. The researchers noted that while HighFM was specifically tested on fire and cloud detection, the architecture could easily be adapted for tracking other rapid phenomena, like storm development or solar energy forecasting, offering a powerful new tool for civil protection and disaster response agencies.

3. Optimising wind farm locations in data-scarce regions

Wind power is a pretty important part of the global transition to renewable energy, but building a wind farm is an incredibly expensive long-term investment. To ensure a wind farm is economically viable, planners need to carefully select sites based on a bunch of technical, environmental, and socio-economic factors. Typically, researchers use Multi-Criteria Decision-Making (MCDM) tools, which rely on expert opinions to weigh factors like wind speed, terrain slope, and proximity to roads. However, these methods are pretty static, pretty subjective, and unable to predict the suitability of locations that haven’t been directly sampled. A new paper from Scientific Reports introduces a new framework that uses expert knowledge, objective efficiency analysis, and predictive machine learning to identify the best wind farm locations in the data-scarce Amhara Region of Ethiopia.

The framework operates in three stages. First, a Fuzzy Analytic Hierarchy Process (FAHP) was used to gather and weight expert opinions, identifying wind speed and proximity to power grids as the most critical factors while smoothing out the vagueness inherent in human judgment. Second, Data Envelopment Analysis (DEA) was applied to objectively measure the efficiency of these candidate zones, pinpointing the North Shewa zone as the absolute best location for converting available land and wind into energy output. Finally, the researchers trained three machine learning models (Random Forest, SVM, and XGBoost) on the FAHP-DEA data. The Random Forest model proved to be the most accurate, learning the complex spatial patterns to predict wind farm suitability across a massive 31-million-pixel map of the region.

This integrated approach successfully delineated 1,698 square kilometres of high-priority land within North Shewa, divided into two distinct development corridors. These findings were strongly corroborated by independent engineering assessments and the Ethiopian government’s own development pipeline. By successfully combining subjective expert weighting, objective efficiency screening, and machine learning generalization, this framework provides a highly accurate, scalable blueprint for strategic wind energy planning that can be easily adapted for other developing regions worldwide.

4. A smart farming framework for pest management

Sustainable agriculture faces massive challenges from unpredictable climate changes, varying soil conditions, and sudden pest outbreaks. Precision agriculture aims to solve these problems by using sensors and AI to manage farms efficiently. However, models like Convolutional Neural Networks (CNNs) struggle to understand the complex, real-world relationships between weather, soil, and crops. Furthermore, centralising data from multiple farms onto a single server creates privacy and bandwidth issues. To tackle these challenges, a team of researchers developed GNN-ML-FRL, a highly advanced, decentralised AI framework designed to identify pests and model environmental factors across diverse farming regions.

This new framework combines three techniques. First, Graph Neural Networks (GNNs) map out the spatial relationships between different sensors and farm plots, allowing the system to understand how a pest outbreak in one area might affect a neighbouring field. Second, Federated Learning (FL) enables different farms to collaboratively train the AI without ever sharing their private, raw data with a central server. Finally, Meta-Learning (ML) and Reinforcement Learning (RL) allow the system to rapidly adapt to new, unseen environmental conditions and make real-time decisions, such as optimising irrigation or pesticide use.

When tested against a massive dataset containing over 52 million environmental sensor readings and 75,000 images of insect pests, the GNN-ML-FRL framework outperformed all standard AI baselines. It achieved an 89.3% accuracy rate in pest identification and demonstrated a significant reduction in prediction errors across geographically unseen farms. The researchers also used the framework to analyse genetic crop data, proving its versatility. Ultimately, this scalable, privacy-preserving AI system offers a robust blueprint for the future of sustainable, data-driven farming. You can access the code here.

Geospatial Datasets

1. Global agricultural monitoring and field boundary dataset

The collection integrates a multi-source framework that combines high-resolution spatial mapping with continuous biophysical tracking to capture field-level dynamics and macro-scale crop conditions. This maps over 3 billion agricultural field units at a 10-metre resolution across 241 countries and territories. You can access the FOTW project here and the GEOGLAM Crop Monitor here.

2. High-resolution canopy height dataset

The NAIP-CHM dataset provides a continuous 0.6-metre resolution canopy height and vertical structure model across the US. Derived from National Agriculture Imagery Program aerial imagery spanning 2012 to 2023, the dataset characterizes the full vertical profile of the landscape, mapping both natural vegetation heights and human-made infrastructure. You can access the data here and the code here.

3. Text-guided object counting dataset

The Cross-domain Large-scale Object Counting (CLOC) dataset is a text-guided object counting collection designed to evaluate generalist vision models across diverse imaging conditions and density distributions. It unifies multi-source heterogeneous annotations from public repositories into a standardized category-specified format, containing approximately 220,000 images, 619 categories, and 15 million instance point annotations. You can check out the project page here and the code here.

4. Earthquake high-frequency magnitude catalogue

The Italian Catalog of Earthquakes based on the high-frequency earthquake Magnitude m3Hz (ICEM) provides high-frequency magnitude records for 1,951 historical and recent Italian earthquakes spanning from 1117 to 2020. You can access the data here.

Other useful bits

• Google Earth has introduced new artificial intelligence-powered data layers that extract infrastructure assets like fire hydrants and storm drains directly from Street View imagery. Available for Professional and Professional Advanced users on web and Android, these layers combine with updated building footprints and land parcels to allow remote inspection of utility access and site constraints.

• An open-source tool called SplatAnalyzer utilises cloud inference to convert 3D Gaussian splats into structured data by generating 3D bounding boxes and object labels in under a minute. Designed for applications in VFX, gaming, digital twins, and physical AI, the interactive kit allows users to isolate, highlight, and manipulate specific assets within a scene without needing local compute.

• The Environmental Defenders Office has launched an interactive map on World Oceans Day to help the Australian public track offshore fossil fuel expansion in their waters. The tool outlines the environmental risks of deep-sea drilling and seismic blasting to marine biodiversity, while providing users with information on how to exercise their legal rights in environmental decision-making.

Jobs

• SEI is looking for a Mid–senior Researcher in data systems and digital governance based in Stockholm.

• EIB is looking for a Data Warehouse Officer based in Luxembourg.

• PAHO is looking for a remote GIS and Information Products Consultant.

• Vizzuality is looking for a remote Software Engineer based in either Spain, Portugal or UK.

• GiveDirectly is looking for a Remote Sensing Analyst based in New York.

Just for Fun

Hold on to your horses, NASA’s Voyager 1 will cross the 1 Light-Day threshold on November 18, 2026. That’s about 16 billion miles from Earth. If you use marathons as your unit of measurement, that’s like 610 million marathons.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — we’re sort of like Playboy for geospatial nerds. In any case, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Rice Monitoring: Drones improve crop health estimation.

• Generative Earth Observation: COP-GEN captures real-world variability.

• Damage Assessment: 3D disaster dataset for structural damage.

• Levee Erosion: Multi-scale wave overtopping dataset.

• Ocean Nutrients: Warming seas increase nutrient stress.

Subscribe now

Research you should know about

1. Taking precision agriculture to new heights

If, like me, you live in Asia, then you know that rice is kinda a big deal. Monitoring the Leaf Area Index (LAI) of rice crops is an important part of understanding their health and water use efficiency. Farmers and researchers traditionally measure this by hand, which is incredibly slow, labour-intensive, and difficult to scale across massive agricultural operations. To speed things up, scientists are increasingly turning to drones equipped with advanced cameras. However, standard drone imagery often struggles with changes in lighting or gets confused by the soil background when the crop canopy is either too thin or too dense. A new paper from Scientific Reports tries to address this by blending multiple types of drone data to create a highly accurate monitoring framework specifically tailored for rice during its critical booting stage.

The research team flew drones equipped with both standard RGB and multispectral cameras over rice fields at altitudes of 30 and 60 metres. Instead of just looking at basic colours, they extracted a complex mix of colour indices, spectral vegetation indices, and spatial texture features. They also developed new texture feature indices that specifically couple spatial patterns with spectral data. When they fed this fused data into six different machine learning models, the results were highly impressive. They found that flying at a lower 30-metre altitude and combining colour, vegetation, and the new texture indices yielded the best outcomes. Using this specific combination, a Convolutional Neural Network and a Random Forest model achieved an accuracy score of over 90%, proving that blending spatial and spectral data easily overcomes the blind spots of using just one type of sensor.

These findings provide a pretty interesting solution for those looking to implement precision agriculture. By confirming the ideal flight altitude and the exact mix of data features needed, the researchers have created a reliable blueprint for tracking crop health from the sky. Interestingly, the study also noted that standard machine learning models like Random Forest performed incredibly well given the relatively small sample size, sometimes even outpacing more complex deep learning networks.

2. Cop-Gen: A generative approach to Earth observation

In the geospatial space (or ‘geospace’, if you will), satellites gather petabytes of data daily, capturing everything from optical imagery and radar to terrain elevation and land cover. The challenge lies in integrating these diverse “modalities” into a single, cohesive system. Traditionally, we’ve relied on deterministic models, which take a set of inputs and produce a single, averaged “best guess” output. However, the real world is obviously pretty ambiguous. A single type of terrain or land cover could look pretty different depending on the weather, the season, or the lighting. By forcing a single output, these models fail to capture the true variability of Earth’s physical systems.

Researchers built COP-GEN to address this: a new multimodal generative model designed to handle the massive influx of data from the Copernicus satellite program. COP-GEN uses a “latent diffusion transformer” architecture, which allows it to process all the different types of satellite data at their native resolutions simultaneously. Instead of producing one averaged image, COP-GEN acts as a stochastic model, meaning it generates multiple, physically plausible versions of a scene based on the input data. The model can even perform “zero-shot” translation, meaning it can fill in missing data (e.g. generating a realistic optical image using only radar and elevation data) without needing to be retrained for that specific task.

When tested against a massive global dataset, COP-GEN proved pretty good at capturing the natural variance of the Earth’s surface. In a head-to-head comparison with a leading deterministic model, COP-GEN was able to cover 90% of the possible real-world variations of a scene, whereas the competing model collapsed to just 2.8%, producing the same image over and over. You can access the code here.

Geospatial Datasets

1. Post-disaster structural damage 3D dataset

The 3DAeroRelief dataset provides the first 3D benchmark dataset specifically designed for large-scale outdoor post-disaster structural damage assessment. It comprises dense 3D point clouds reconstructed via Structure-from-Motion and Multi-View Stereo techniques using optical RGB imagery captured by low-cost unmanned aerial vehicles over hurricane-damaged areas. You can access the data here and the code here.

2. Levee erosion and wavefront velocity dataset

The collection provides a multi-scale dataset compiled from four experimental field campaigns and corresponding laboratory tests designed to evaluate the spatiotemporal erosion resistance of earthen levee cohesive clay covers under wave overtopping loads. You can access the data here and the code here.

3. Glacier inventory dataset

The Tajikistan Glacier Inventory (TGI) provides a national-scale glacier dataset for Tajikistan derived from 3-metre resolution PlanetScope satellite imagery acquired in 2024. The collection maps 12,325 glaciers covering a total area of 7,720.26 square kilometres. You can access the data here and the code here.

Other useful bits

• A new study combining two decades of NASA Aqua satellite data with global ocean surveys has mapped nutrient stress in marine microorganisms caused by warming waters. By tracking shifts in the carbon-to-chlorophyll ratio of phytoplankton alongside genetic markers, researchers found that ocean stratification is increasingly limiting nutrient availability, particularly in subtropical gyres.

• The EU is investing billions of dollars in several large-scale rail tunnels to bypass natural geographic barriers and shift passenger and freight traffic from air and road to rail. While mega-projects like the Gotthard, Brenner, and Mont Cenis base tunnels promise to significantly reduce travel times across the continent, they face substantial construction delays, ballooning costs, and a lack of completed connecting lines from neighboring countries.

• A recent article addresses the challenge of building machine learning models in geospatial applications where satellite data is abundant but accurate field labels are rare and expensive. The author outlines a practical workflow for small environmental datasets, highlighting that rigorous spatial validation and transparent mapping of uncertainty are critical to avoid artificial inflation of model accuracy.

• ESA has awarded a contract to Thales Alenia Space and Airbus Defence and Space to build two Copernicus Sentinel-1 Next Generation satellites to ensure long-term continuity for Europe’s radar Earth observation capabilities. The new satellites will feature advanced C-band synthetic aperture radars that extend coverage to the polar regions and offer a fourfold improvement in geometric resolution compared to the first-generation mission.

Jobs

• PAHO is looking for a remote GIS and Information Products Consultant.

• Vizzuality is looking for a remote Software Engineer based in either Spain, Portugal or UK.

• IOM is looking for a GIS Manager based in Berlin.

• GiveDirectly is looking for a Remote Sensing Analyst based in New York.

• UNITAR is looking for (1) Geospatial Analysts - Satellite Imagery and GIS and (2) Geospatial Quality, Assurance, Training and Analytical Support Specialists based in Geneva.

• WFP is looking for a Geospatial Data Engineer based in Rome.

Just for Fun

A time-lapse captured from a SpaceX Dragon spacecraft shows a spectacular southern aurora caused by a recent solar event, with the phenomenon dancing directly below the vehicle.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — a safe space for the cartographically curious. As usual, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Poverty Mapping: Tempov updates wealth maps using satellites.

• Thermal Imaging: Dual AI models sharpen infrared imagery.

• Satellite Training: Pixel diversity improves foundation model performance.

• Weather Extremes: AI forecasts struggle beyond past records.

• Nightlights: NASA reveals shifting global illumination patterns.

Subscribe now

Research you should know about

1. Stanford’s foundation model for predicting poverty

Traditional methods for measuring poverty in developing nations rely on household surveys and census data. These methods can be expensive, slow, and infrequent, which leaves policymakers working with outdated information when deciding where to allocate resources or build infrastructure. Over the last decade, researchers have started using daytime satellite imagery to try to measure economic activity, looking for visual proxies like new roads or agricultural expansion. While this works well for a static snapshot of an area, these models often struggle to track changes in wealth over time, confusing seasonal changes like fields turning brown in the winter for actual economic decline.

To fix this, a team of researchers built Tempov, a new geospatial foundation model specifically designed to track long-term economic changes (more info on foundation models here). The model was trained on a massive dataset of three million satellite images spanning two decades. Interestingly, the researchers intentionally fed the model ‘bi-temporal’ pairs, i.e. pictures of the exact same location taken during different seasons of the same year. This forced the model to ignore transient, seasonal changes like snow or dead crops and focus entirely on permanent, human-made changes like new buildings or roads.

Tempov proved to be pretty effective. The researchers demonstrated that if Tempov was given a decade-old census from a country, it could accurately predict the modern wealth distribution using only 5% of modern survey data. In resource-strapped nations, this means governments can achieve highly accurate poverty mapping at a fraction of the cost of a full census. To prove its scalability, the team deployed Tempov to map the entire continent of Africa, producing a high-resolution, 6km-by-6km grid showing the exact changes in wealth from 2015 to 2025. This open-source tool could dramatically change how we monitor and combat global poverty.

2. Sharpening the world of thermal imaging

Enhancing the resolution of remote sensing imagery can be pretty important for applications like autonomous driving and environmental monitoring. But Super-resolution for infrared or thermal images brings a specialised set of challenges. Unlike standard visible light photographs, thermal images lack rich textures and rely heavily on clear object outlines and stable regional temperatures. If a super-resolution system sharpens the image too aggressively, it can create fake hot spots or unstable temperature readings that ruin the utility of the data.

To tackle this, a team of researchers developed a dual-branch framework for the NTIRE 2026 Infrared Image Super-Resolution Challenge. Instead of forcing one neural network to do everything, they combined two different architectures to capture the best of both worlds. The first branch uses a transformer model called HAT-L to focus on sharpening local edges and fine contours. The second branch employs a state-space model named MambaIRv2-L to handle the big picture, ensuring long-range temperature consistency across the entire scene. The system processes the low-resolution images through both branches independently, applies specific test-time enhancements to each, and simply averages the two outputs together to create the final image.

This collaborative approach proved pretty successful in generating clear and accurate thermal imagery. By blending the aggressive edge recovery of the transformer with the global stability of the state-space model, the fused output comfortably beat either model working on its own. The researchers evaluated their system using the official NTIRE 2026 development and hidden test sets, alongside a custom evaluation batch derived from the Caltech Aerial RGB-Thermal dataset.

3. Mapping out the best data for satellite AI

As I mentioned above, in recent years, developers have built massive ‘foundation models’ designed to analyse satellite imagery for tasks like mapping populations, tracking floods, or estimating crop yields. To train these models, researchers use huge datasets of unlabelled satellite images, a process known as pretraining. However, there are no real standards for how this data is collected. Some models are trained exclusively on images of European cities, some are trained on a perfectly even grid of the entire Earth, and others focus heavily on specific biomes like deserts or forests. Until now, no one had rigorously tested how these different geographic sampling strategies actually affect the AI’s final performance.

To solve this, researchers built seven distinct pretraining datasets (six covering individual continents and one global mix) and used them to train identical foundation models. They then tested these models on a variety of global and local mapping tasks. The results were highly surprising. The model trained exclusively on images of Europe consistently outperformed all the others, including the globally trained model, across almost every single task. Even when the AI was asked to map farms in Africa or populations in South America, the Europe-trained model proved to be the most accurate.

To figure out why the European dataset performed so well, the researchers measured the ‘diversity’ of all the datasets across different metrics. They discovered that simply having a wide variety of continents, biomes, or landcover types in the training data didn’t actually boost performance. What mattered most was ‘spectral diversity’, which measures the sheer complexity and variety of colour and light values within each individual image. Because the European images happened to have the highest spectral complexity, they provided the best training ground for the AI, proving that when it comes to training satellite models, the richness of the pixels matters far more than the geographic coordinates they came from.

4. AI vs Physics: Forecasting extreme weather

Geospatial models have begun to target weather forecasting, often outperforming leading physics-based numerical models on standard benchmarks. Models like GraphCast and Pangu-Weather are faster, more energy-efficient, and generally provide more accurate daily forecasts. However, scientists have questioned whether these data-driven models can reliably predict unprecedented, record-breaking weather events. Unlike physics-based models that calculate the actual laws of thermodynamics and fluid dynamics, AI models rely entirely on finding patterns in historical training data. A new study from Science Advances put this to the test by evaluating how well leading AI models could predict record-breaking heatwaves, cold snaps, and windstorms compared to the gold-standard physics-based model, the European Centre for Medium-Range Weather Forecasts’ HRES.

The researchers built a massive dataset of record-breaking weather events from the years 2018 and 2020. These events were specifically chosen because they exceeded any measurement recorded in the AI models’ training data (which covered 1979-2017). When tested on these unprecedented extremes, the AI models consistently failed, significantly underperforming the physics-based HRES model. The AI models not only failed to predict the frequency of these record-breaking events, missing many of them entirely, but they also severely underestimated their intensity.

Importantly, the researchers found that the larger the extreme event was compared to historical records, the worse the AI’s prediction became. It was as if the AI models hit a soft “ceiling” based on their training data and simply could not imagine an event being any worse.

These findings highlight a dangerous “extrapolation” problem in current AI weather models. Because they are not grounded in the actual laws of physics, they struggle to predict events that fall outside of their historical training data. While AI offers incredible speed and general accuracy, this study proves that we cannot solely rely on them for early warning systems or disaster management, particularly in a rapidly warming climate where unprecedented extremes are becoming the new normal. For now, physics-based models remain essential for keeping communities safe from the worst that nature can throw at them.

Geospatial Datasets

1. European agricultural land use systems map

This collection provides a harmonised, Europe-wide agricultural land use systems map at a 10-m spatial resolution covering the period from 2017 to 2021. You can access the data and code here.

2. Global sea and sea-Ice surface temperature dataset

This dataset introduces a 43-year Climate Data Record providing daily, gap-free global fields of combined sea surface temperature and sea-ice surface temperature at a 0.05-degree spatial resolution from 1982 to 2024. You can access the data here and the code here.

3. Pan-Arctic super-resolved land surface temperature dataset

A new 42-year climate data record offers twice-daily, clear-sky land surface temperature (LST) data for the entire pan-Arctic region at a 1-km spatial resolution from 1982 to 2023. You can access the data here.

4. Global coastal soil carbon accumulation dataset

A new global dataset provides a comprehensive inventory of soil organic carbon accumulation rates within coastal wetlands. This open-access resource contains 8,998 standardised field observations derived from a systematic review of 247 peer-reviewed articles published between 1981 and 2025. You can access the data and code here.

Other useful bits

• New imagery from the NISAR satellite has revealed that Mexico City is sinking at an alarming rate of up to 0.8 inches a month due to the over-pumping of its underlying aquifer. It captures subtle ground movements in detail, providing some pretty shocking insights to help the city manage its infrastructure and pressing water crisis.

• As the number of active satellites skyrockets, the science academies of G7 countries have called for the creation of an Intergovernmental Panel on Space Sustainability (IPSS). This initiative aims to establish international standards and global thresholds to protect the night sky, manage orbital space debris, and balance commercial innovation with environmental safety before a critical tipping point is reached.

• By analysing a decade of data from its "Black Marble" program, NASA revealed that the Earth's nighttime lighting is highly dynamic and flickers with industrial shifts. The study shows how changes in artificial light trace real-world human stories, from economic booms and urban development to energy crises and green policy shifts. And if you’re a nightlights nerd, you might want to check this out.

Jobs

• WFP is looking for a Geospatial Data Engineer based in Rome.

• UNICEF is looking for a GIS Lead based in Florence.

• GiveDirectly is looking for a Remote Sensing Analyst based in New York.

• UNITAR is looking for (1) Geospatial Analysts - Satellite Imagery and GIS and (2) Geospatial Quality, Assurance, Training and Analytical Support Specialists based in Geneva.

• WWF is looking for a Senior Conservation Data Analyst/Engineer based in Washington, DC.

Just for Fun

Jupiter and Venus, on 9 June, had the appearance of being pretty close together. This is known as a ‘planetary conjunction.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — your weekly map to the latest geospatial news. We buffer out the noise, snap to the most interesting features, and provide geospatial puns that are even worse than the GeoDA UI. In any case, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Trade Deaths: Global trade shifts pollution deaths abroad.

• Political Violence: Conflict scars the next generation.

• EO Embeddings: Compact vectors streamline satellite analysis.

• SAR Matching: Off-the-shelf AI aligns disaster images

• Climate Pledges: ClimActor tracks subnational climate action.

Subscribe now

Research you should know about

1. The hidden health costs of global trade

If you’ve ever been to a city, or read about cities in books, or seen a city in a movie, then you might have experienced the joys of air pollution from fine particulate matter (PM2.5). It causes around 5.1 million deaths a year. While it’s easy to blame the countries where this pollution is emitted, the reality of global economics paints a bit more of a complicated picture. When a wealthy country imports cheap, manufactured goods, it’s effectively outsourcing the dirty, dangerous industrial work required to make them. This is basically the idea of ‘imported emissions’. Until now, scientists have struggled to map exactly how this international trade shifts the health burden of air pollution from wealthy nations to poorer ones on a country-by-country basis.

A new study from Nature Communications quantifies this by combining global economic data, air pollution transport models, and epidemiological studies. The researchers discovered that roughly 40% to 48% of all economy-related PM2.5 deaths are caused by the production of goods meant for export. Most shockingly, 14% to 18% of all global air pollution deaths occur when a wealthy country (with a high GDP) imports goods from a poorer country (with a GDP at least 50% lower). This means that high-income nations like the US and the UK are effectively exporting thousands of pollution-related mortalities to countries like China, India, and Bangladesh in exchange for cheaper goods.

This massive imbalance exposes a major flaw in how governments currently calculate the ‘externality costs’ of pollution. In countries like the US, the economic cost of pollution is only calculated based on the lives of its own citizens. If a US policy causes pollution deaths in another country, those lives are valued at zero, essentially incentivising companies to offshore their most toxic practices to the poorest nations. The researchers propose a new ‘Fair Trade in Pollution’ model that forces wealthy nations to value the lives lost in producing countries as highly as their own citizens, a shift that would drastically alter the math behind international trade policies. You can access the code for this study here.

2. The generational toll of political violence

We all know that armed conflict and political violence cause massive, immediate suffering. However, much less is known about the ripple effects these events have on the daily lives of children and young adults long after the dust settles. When a community experiences political violence, the resulting trauma, economic instability, and breakdown of local services can create a culture of insecurity. In these high-stress environments, violence is often normalised as a way to resolve disputes, leading to an increase in interpersonal violence within families and romantic relationships.

To measure this phenomenon, researchers built a massive dataset combining the Violence Against Children and Youth Surveys (VACS) with the Armed Conflict Location and Event Data (ACLED) project. By cross-referencing these two databases, they were able to track the history of political violence across nine African nations and compare it directly to self-reported instances of interpersonal violence against adolescents and young adults. The results showed a stark, long-term connection. If a community experienced a significant increase in political violence over a 15-year period, the local youth were 5.5% more likely to experience emotional violence from family members and 3.0% more likely to suffer physical violence from an intimate partner. Notably, the study found no significant link between short-term political violence and increased youth violence, proving that this is a generational, slow-burning issue.

The study also highlighted how economic factors exacerbate these dangers, with young people in poorer households being 16.9% more likely to experience sexual violence following long-term political instability. These findings prove that the scars of political violence extend far beyond the battlefield, infecting the homes and relationships of the next generation. You can access the data and code here.

3. Optimising Earth observation with compact embeddings

Earth observation satellites capture petabytes of multispectral imagery every day, which researchers increasingly analyse using large Geospatial Foundation Models. Instead of constantly feeding raw data through these massive models for every new task, scientists are shifting towards an embedding-centric approach. In this setup, models process the imagery once to create compact, reusable vector representations known as embeddings. However, deciding exactly how to compress this data, such as which layers of the model to use or how to pool the information, significantly impacts performance. A new study from IBM systematically evaluates these design choices to help developers build highly efficient Earth observation pipelines without sacrificing accuracy.

Using an evaluation framework called NeuCo-Bench, the researchers tested various embedding configurations across multiple tasks, including land cover classification, biomass estimation, and cloud cover prediction. They discovered that Vision Transformers consistently outperformed traditional convolutional networks like ResNet when dealing with continuous environmental variables. Furthermore, simply taking the average of the spatial features, a technique known as mean pooling, proved to be the most robust aggregation strategy across the board. The team also noted that while transformer models perform best at their final layers, convolutional networks actually produce their most useful embeddings at intermediate stages, meaning the default practice of using the final layer is often a mistake.

The findings show that carefully designed, fixed-size embeddings can compress raw satellite data by over 500 times while remaining incredibly useful for a wide range of analytical tasks. The study also highlights that different training methods excel at different tasks, meaning that combining embeddings from multiple models can further boost overall reliability. By following these design guidelines, developers can create scalable, lightweight systems for monitoring our planet.

4. Can off-the-shelf AI match optical and SAR satellite imagery?

When a disaster like a hurricane strikes, thick cloud cover often makes standard optical satellite imagery useless. In these situations, responders rely on Synthetic Aperture Radar (more info on SAR here) which can see through clouds but produces grainy, distorted images that look radically different from regular photos. To quickly assess damage, analysts need to perfectly align, or “register,” these new SAR images with older optical basemaps. It’s a pretty notoriously difficult task because the two types of imagery are fundamentally different. While there are plenty of highly advanced AI image-matching tools available, almost all of them were trained on normal, ground-level photos. A new study tries to see whether these general-purpose AI matchers actually handle the extreme differences between overhead optical and SAR satellite imagery.

To find out, a new paper tested 24 different pretrained AI matchers on SpaceNet9, a dataset of paired optical and SAR satellite images. They evaluated the models in a “zero-shot” setting, meaning the AIs had to perform the task straight out of the box without any special training or fine-tuning for satellite data. The results were surprising. While models specifically trained for cross-modal tasks (like matching visible light to thermal images) performed exceptionally well, some general-purpose models performed almost identically. For example, a model called RoMa, which was only ever trained on normal photos, achieved the lowest error rate alongside the cross-modal specialist XoFTR. This suggests that the sheer size and diversity of data used to train modern foundation models gives them an unexpected ability to bridge the gap between radically different types of imagery.

However, the study also revealed that picking the “best” AI model is only half the battle. The researchers found that how the model is deployed (specifically the geometric math used to align the images and how the images are cropped into tiles) often mattered more than the choice of AI itself. E.g., simply forcing the models to use an “affine” geometry model (which assumes the ground is relatively flat) rather than a “homography” model (which accounts for complex 3D perspective) slashed the error rate by quite a lot. The key takeaway for disaster responders is that while off-the-shelf AI matchers are surprisingly capable of handling satellite data, they require careful, domain-specific configuration to be truly reliable in the field.

Geospatial Datasets

1. Global agricultural field boundary map

The PRUE global dataset delivers the very first wall-to-wall map of agricultural field boundaries at a pretty granular 10-m resolution for 2024 and 2025. You can access the data here and code here.

2. Spatiotemporal hyperspectral EO dataset

The ChronoEarth-492K dataset introduces the first large-scale, temporally calibrated hyperspectral self-supervised learning collection, built on NASA’s EO-1 Hyperion mission archive spanning from 2001 to 2017. You can access the data and code here.

3. Climate pledges and emissions dataset

The ClimActor 2.0 database provides an expanded, openly available geospatial resource that maps climate targets, action plans, and emission inventories from subnational governments worldwide. You can access the data here and the code here.

4. National-scale sandy beach dataset

This new dataset introduces the first comprehensive, high-resolution national map of sandy beaches along the extensive 11,098.81 km coastline of India.

Other useful bits

• The creators of the Global Automation Atlas have mapped how automation will unfold across 124 countries by comparing over 18,000 distinct tasks. This new tool provides an incredible 2.3 million task-country comparisons.

• The new GeoX framework is impacting geospatial reasoning by using a self-play mechanism that allows AI to teach itself complex spatial logic without the need for costly human data. By generating and solving its own programming problems, this system creates a virtuous cycle of autonomous improvement that pushes vision-language models to state-of-the-art performance.

• NASA and IBM’s open-source Prithvi model has become the very first AI geospatial foundation model to be successfully deployed in orbit. By running directly on the International Space Station and the Kanyini satellite, the model system can quickly analyse floods and wildfires from space, cleverly saving massive amounts of bandwidth by processing Earth observation data before it even hits the ground.

• In the wake of Hurricane Melissa, Jamaica's National Spatial Data Management Branch demonstrated the power of resilient geospatial infrastructure by mapping nearly 200,000 damaged buildings within days. The nation used its National Geospatial Repository and partnered with international tech organisations to create a shared real-time dashboard, allowing emergency teams to coordinate relief and restore essential services with incredible precision.

Jobs

• UNITAR is looking for (1) Geospatial Analysts - Satellite Imagery and GIS and (2) Geospatial Quality, Assurance, Training and Analytical Support Specialists based in Geneva.

• WWF is looking for a Senior Conservation Data Analyst/Engineer based in Washington, DC.

• Google is looking for a Technical Program Manager under their Geo team based in Singapore.

• UNODC is looking for a Geospatial Information Management Intern based in Vienna.

Just for Fun

The Sentinel-6 Michael Freilich satellite has detected a massive swell of warm water moving across the Pacific Ocean, which means that El Niño will likely arrive later this year.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — a place where you aren’t judged for being a little sinusoidal... Anyway, the aim as usual is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• AI Image Search: ProVG improves satellite object detection.

• Farm Boundaries: PRUE maps fields at global scale.

• Car Dependency: New index maps urban transport reliance.

• Carbon Credits: REDD+ projects show major over-crediting.

• Ocean Data: WOD23 compiles centuries of ocean measurements.

• Photosynthesis Data: TRAX GPP maps global productivity.

Subscribe now

Research you should know about

1. Teaching AI to search satellite images like a human

A new study introduces ProVG, an AI framework designed to dramatically improve object detection in satellite imagery based on text descriptions. Spotting a specific target in a remote sensing image can be pretty difficult because the scenes are massive and packed with identical-looking objects. Usually, AI models try to find a target by processing the user’s entire text prompt as a single chunk. It turns out this approach isn’t great. When a model processes a sentence all at once, it doesn’t pick up on fine-grained clues like spatial relationships or specific physical attributes, which often leads to the model highlighting the wrong object entirely.

To fix this, the researchers looked at how human brains actually process visual searches and built a progressive framework that mimics our natural cognition. Instead of swallowing a sentence whole, ProVG breaks the text prompt down into three distinct pieces: (1) global context, (2) spatial relations, and (3) object attributes. The model then applies these clues in a strict sequence to filter the image. First, it surveys the global context to get a general understanding of the scene. Next, it uses spatial clues to narrow down the search to a specific neighbourhood. Finally, it verifies the exact target by matching the specific physical attributes.

Alongside this structured searching method, the framework also includes special modules to handle the extreme scale variations found in satellite photos, helping it fuse details from both zoomed-in and zoomed-out perspectives. The researchers tested ProVG against a huge lineup of existing models across two major remote sensing benchmarks. The results were pretty impressive. By simply decoupling the language and forcing the model to search step-by-step, ProVG consistently outperformed current top-tier systems, proving to be incredibly accurate at drawing both basic bounding boxes and precise pixel-level masks around targets.

2. Mapping the world’s farms from space

Knowing exactly where farm fields begin and end can be pretty important for tracking crop yields, managing water resources, and monitoring climate initiatives. There are too many approaches to name that uses AI to automatically draw these boundaries by scanning satellite images. However, when these models are taken out of the lab and deployed in the real world, there can be a lot of issues… A model that works perfectly in the sunny plains of Illinois might completely mess up when scanning the cloudy, mountainous terraces of Japan, drawing jittery lines or hallucinating extra fields.

To solve this, researchers built PRUE (Practical Recipe for Field Boundary Segmentation at Scale). They tested 18 different AI architectures against a massive global dataset of fields to see what actually works. This involved introducing new, real-world tests to measure how the AI handled changes in brightness, picture scaling, and the order of the images it was fed. They discovered that while some of the largest, most hyped ‘foundation models’ struggled, a specialized U-Net architecture crushed the competition. By feeding this model mathematically enhanced images and tweaking how it penalises mistakes during training, the researchers created an incredibly robust system.

The results speak for themselves. PRUE scored 6% higher in overall accuracy than previous top-tier models and proved remarkably stable when the lighting or image scale was tweaked. To prove it works at scale, the researchers used PRUE to map out every single agricultural field in Japan, Mexico, Rwanda, South Africa, and Switzerland, covering 4.7 million square kilometres in just a few hours.

3. Decoding car dependency in modern cities

To reach net-zero emissions, urban planners are pushing for car-free zones, better cycling infrastructure, and improved public transport. However, moving away from private vehicles is incredibly difficult because decades of car-centric urban growth have transformed the automobile from a convenience into an absolute necessity. For many residents, giving up their car means losing access to essential services, leisure activities, and jobs. A new study addresses this by quantifying exactly how reliant different neighbourhoods are on private vehicles compared to public transport.

A team of researchers developed the Car Dependency Index to map the accessibility gap between driving and taking public transport across 18 major cities in Europe and North America. By crunching high-resolution geospatial data, they calculated how many points of interest a resident could reach within a normal journey time using either a car or a bus and train network. The data revealed a lot of spatial inequalities, with peripheral districts almost entirely trapped in high-dependency cycles while central areas were far better equipped for car-free living. When looking closely at Vienna, the team also discovered that this neighbourhood dependency was a massive driver of car ownership, completely independent of a household’s income level.

To see if infrastructure upgrades could fix the problem, the researchers simulated the impact of a planned metro expansion in Rome. While the new transit line successfully removed an estimated 60,000 commuting vehicles from the roads, the benefits were extremely localised to the people living right next to the new stations. This proves that building a single new train line is simply not enough to break the cycle of car dependency across an entire city. Ultimately, if policymakers want to dismantle car-based systems and build truly sustainable urban spaces, they need to commit to massive, network-wide public transport expansions rather than isolated projects.

4. The truth behind forest carbon over-crediting

Forest carbon credits, particularly REDD+ projects, are meant to fund tropical forest conservation. However, recent controversies revealed that many early projects issued far more credits than they actually earned, causing voluntary carbon markets to lose over a billion dollars in value. Some industry figures pushed back against these claims, arguing that independent evaluations used flawed global satellite data that simply missed the real deforestation. To settle the debate, a new study from Nature Communications synthesised data from six independent evaluations covering 44 REDD+ projects to see exactly where the discrepancies came from.

The results showed that while most projects did successfully reduce deforestation, they still claimed to have saved nearly 11 times more forest than they actually did. Importantly, the researchers proved that the use of global satellite data was not the problem; these tools actually detected more deforestation than the custom layers used by the projects themselves. Instead, the massive over-crediting stemmed from how projects chose their baseline reference areas. Projects routinely selected highly accessible, heavily degraded comparison zones that were far more vulnerable to logging than the actual protected areas. When combined with overly pessimistic predictive models, this made the projects look vastly more effective than they really were.

To ensure carbon markets genuinely benefit the climate, the researchers argue that the industry must abandon flexible, prediction-based baselines. Future credits must rely on rigorous, after-the-fact evaluations using independent methods to measure real-world impact. You can access the data here and the code here.

Geospatial Datasets

1. World ocean database

The World Ocean Database 2023 (WOD23) is a large digital collection of oceanographic in situ profile measurements covering the instrumental record from 1772 to 2022, with around 18.6 million water column profiles and 3.6 billion measurements across 27 physical and chemical variables, including temperature, salinity, and oxygen. You can access the data here.

2. High-res global GPP dataset

The newly introduced TRAX GPP dataset provides a 0.05° global record of terrestrial photosynthesis from 2001 to 2024, using a hybrid Long Short-Term Memory framework with seasonal-trend decomposition and atmospheric CO₂ assimilation constraints to capture carbon cycle dynamics and CO₂ fertilisation effects. You can access the data here and the code here.

3. Long-term soil analysis dataset

The Sol_Run dataset provides a seventeen-year record of soil analysis data for Réunion Island from 2008 to 2024, with more than 266,000 records from nearly 25,000 unique samples covering physical and chemical properties such as pH, nutrient content, and cation exchange capacity. You can access the data here.

4. High-res Mediterranean wildfire dataset

The CalWildFire dataset brings together eleven years of daily in situ wildfire and meteorological data for the Mediterranean region of southern Italy, combining ground-validated meteorological measurements, field-based burned area records, and calculated fire weather indices. You can access the data here.

Other useful bits

• Planet has launched SuperRes technology, a new AI-based super-resolution dataset that sharpens its satellite imagery from 3 metres to 2-metre resolution. The update makes small-scale details, such as rooftop markings and individual trees, easier to inspect while retaining Planet’s daily global monitoring coverage.

• Earth Index is officially live offering free global access to its AI-powered satellite search tools. The platform is already being used to identify issues such as illegal deforestation and hazardous quarries through large-scale satellite image search.

• Render a House has launched a new 3D mode that allows users to place their own 3D models directly within the Google Earth environment. The update makes it easier to see how proposed projects fit into their real-world surroundings and create more consistent project images.

Jobs

• World Vision is looking for a WASH Data Fellow based in the US.

• Google is looking for a Technical Program Manager under their Geo team based in Singapore.

• UNODC is looking for a Geospatial Information Management Intern based in Vienna.

• Esri is looking for a GIS Solution Engineer – Global Alliances & Partners based in San Antonio.

Just for Fun

Saturn and Neptune in retrograde, traced across 34 nights from May 2025 to February 2026. This composite shows Saturn as the brighter foreground planet and Neptune as the dimmer object behind it, both appearing to move backwards across the sky as Earth overtook them on its faster inner orbit around the Sun. Saturn moved from Pisces into Aquarius and back again, while Neptune remained in Pisces, during their closest apparent pairing since the Saturn-Neptune conjunction of 1989.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — a safe space for map fetishists… The aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Disaster Damage: AI assesses buildings after natural disasters.

• Map Queries: LLMs make spatial databases conversational.

• Data Heat: AI infrastructure warms nearby landscapes.

• Satellite Labels: MAPLE teaches AI land-cover hierarchies.

• Urban Plastics: DURUM tracks microplastics in stormwater.

Subscribe now

Research you should know about

1. A sharper lens on disaster zones

A new study introduces a three-step AI framework designed to improve how we assess building damage from space. When a natural disaster strikes, quickly figuring out which buildings are destroyed is pretty important for sending rescue teams to the right places. However, the satellite imagery used for these assessments is often blurry or full of noise, which makes it pretty difficult for automated systems or even human experts to spot crucial details like collapsed roofs or cracked walls. Traditional object detection models can spot buildings but fail to interpret the severity of the damage, while newer Vision-Language Models (VLMs) can analyse scenes but often get confused and ‘hallucinate’ when looking at low-resolution photos.

To overcome these limitations, researchers from Dakota State University built a hybrid pipeline and tested it against the xBD dataset, a massive benchmark collection of satellite images covering various global disasters. The new framework tackles the problem in three steps. First, it uses a Video Restoration Transformer to artificially upscale the low-resolution satellite images, quadrupling their size to make structural details stand out. Next, it uses a YOLOv11 object detection model to draw precise boxes around every building in the image and crops them out. Finally, these high-resolution cropped images are fed into several different VLMs, which act as a ‘jury’ to assess the damage severity of each building on a four-point scale. By combining multiple models, the system drastically reduces the bias and hallucination risks of relying on just one AI.

When evaluated on imagery of Hurricane Matthew and the Moore Tornado from the xBD collection, the results showed that this multi-stage approach was pretty decent. By upscaling the images first, the VLMs were able to produce much more accurate and semantically rich descriptions of the damage. Furthermore, the team found that the Qwen3 family of models consistently outperformed Gemma3 models, proving to be far more reliable at identifying completely destroyed buildings. Ultimately, this pipeline could provide first responders with a faster way to prioritise rescue efforts without having to set foot in a hazardous area. However, I do remain sceptical about the super-resolution approach…

2. When maps learn to answer questions

Querying complex geographic or time-based databases usually requires some coding skills. If you want to find all the restaurants within a specific flood zone, you can’t just type that into a search bar and expect a database to understand you. Developers build Natural Language Interfaces to Databases so everyday users can bypass the complex code and just ask questions. A new paper maps out the entire landscape of this highly fragmented field, reviewing everything from the datasets used to the evolution of the algorithms themselves.

The paper breaks down how these systems have evolved across four main categories. Early models relied on strict, handcrafted grammar rules that worked well but struggled with casual or unexpected phrasing. Programmers then moved to hybrid neural networks that learned from data but still relied on rigid templates. Today, the focus has shifted entirely to LLMs and multi-agent systems, where different AI agents collaborate to interpret a query, check the database schema, and write the code. While these modern approaches can be incredibly flexible, they often suffer from geo-hallucination, where the AI invents imaginary spatial relationships or references tables that simply do not exist.

Beyond the models, the review highlights a pretty big issue with the data used to test them. Right now, there isn’t a single, unified benchmark that accurately reflects the messy and ambiguous way real people ask geographic questions. Instead, researchers rely on a mix of highly controlled synthetic datasets and real-world GIS databases that make it nearly impossible to compare different models fairly. Ultimately, the authors conclude that before we can build AI that truly understands space and time, the industry needs to ditch these fragmented tests and create a robust benchmark that accounts for real-world geographic ambiguity.

3. AI’s next environmental problem is heat

We hear a lot about the massive energy demands of artificial intelligence, but there’s a hidden side effect we rarely talk about: the heat. As tech companies scramble to build massive AI data centres across the globe, these power-hungry hubs are pumping enormous amounts of thermal energy into the atmosphere. To figure out the real-world impact, researchers combined two decades of satellite land surface temperature records with the exact locations of over 8,000 data centres built outside densely populated cities. This allowed them to isolate the specific temperature changes caused by these facilities without getting confused by typical urban warmth.

The data reveals a pretty crazy phenomenon that they call the ‘data heat island effect’. On average, the land surface temperature around a new AI hyperscaler spikes by 2°C right after it starts operating. This warming footprint isn’t just confined to the building itself. The heat ripples outward, raising local temperatures for up to 10 kilometres in every direction. When researchers overlaid this temperature data with global population maps, they discovered that over 340 million people currently live within these artificially warmed zones. It’s a pretty big deal, considering this extra heat places significant stress on local healthcare, energy grids, and water supplies.

Tackling this growing problem requires a mix of smart software and innovative hardware. On the coding side, developers can reduce compute loads by cleaning up messy data before processing or using stuff like carbon-aware token generation to improve efficiency. Physically, engineers are exploring some incredibly interesting tech to keep temperatures down. This includes adiabatic circuitry that actually recycles energy during computation, hybrid liquid cooling systems, and special passive radiative coatings that reflect solar heat away from the buildings. By combining these hardware and software upgrades, the industry has a real shot at keeping our environment cool(er) as AI continues to scale.

4. Teaching AI the family tree of satellite imagery

When AI models look at satellite imagery, it’s usually trained to spot flat, isolated labels like a ship, a tree, or a road. But the real world is pretty highly structured, and these labels actually belong to a complex hierarchy. E.g. a ship is part of a port area, which itself is a type of artificial surface. While some models try to learn these hierarchical relationships, they can get confused when a single image contains multiple objects from completely different branches of the taxonomic tree. Furthermore, these older methods are pretty computationally heavy and tend to fall apart when they do not have massive amounts of training data.

A recent paper introduces MAPLE, a new framework designed to solve this multi-path classification problem by explicitly teaching AI the hierarchical structure of remote sensing data. The system starts by feeding the model text-based descriptions of how different land cover types are related, creating a semantic map of the categories. It then uses a Vision Transformer to scan the satellite image and a Graph Convolutional Network to pass information along the branches of the label tree. Finally, it uses an adaptive fusion mechanism to dynamically weigh the visual evidence from the image against the structural rules, ensuring it makes logical predictions across every level of the hierarchy without any manual tuning.

The researchers tested MAPLE across several major remote sensing datasets that were mapped to standard land-cover classifications. The results were pretty impressive, particularly when the model was given very little data to learn from. In these restricted scenarios, MAPLE outperformed standard classification baselines by up to 42%, proving that understanding the relationships between categories gives models a massive head start. Interestingly, it achieved these gains while adding only a tiny 2.6% increase in computational overhead. The framework also proved quite effective at reducing dumb mistakes between tricky categories, making it a robust and highly efficient tool for Earth observation.

Geospatial Datasets

1. Wind tunnel gas dispersion dataset

The RED:VAPOR dataset captures gas sensor responses to vapour plumes in scale-model landscapes, using a wind tunnel fitted with both low-cost and advanced sensors to map synthetic gas dispersion across a dense 3D grid under controlled wind conditions. You can access the data here and the code here.

2. Urban runoff microplastics dataset

The Dataset of Urban RUnoff Microplastics (DURUM) brings together 180 urban stormwater microplastic sampling efforts across 15 countries from 2018 to 2024, covering runoff from streets, residential catchments, and industrial areas. You can access the data here and the code here. You can access the data here and the code here.

3. Multi-sensor EO dataset

The BigEarthNet.txt dataset provides more than 464,000 co-registered Sentinel-1 and Sentinel-2 satellite images paired with detailed textual descriptions, with nearly 9.6 million annotations covering land-use classes, spatial relationships, and visual question-answering pairs. You can access the data here.

4. Global soil water isotope dataset

This new dataset provides a harmonised global collection of soil-water stable isotope records from 1975 to 2024, bringing together more than 27,000 records from 463 observation sites across 37 countries and organising them into standard soil-depth intervals. You can access the data here.

Other useful bits

• While AI is often discussed in terms of its environmental footprint, DINOv3 is also being used for nature restoration finance. The model uses computer vision to count individual trees and measure canopy height from satellite imagery, helping investors verify local restoration projects at lower cost and direct funding towards farmers and communities.

• For the first time in history, agricultural field boundaries have been mapped at a global scale. The 10-metre resolution dataset is publicly available at no cost and can be explored through the FTW Explorer.

• Google Earth has just released an update that allows users to import Shapefiles and 3D models directly onto its real-world canvas. This improvement enables us to render industry-standard data as cloud-native layers, and they’ve even added elevation profiles to the measure tool to help you easily visualise detailed terrain data.

Jobs

• Yale University is looking for a GIS Research Specialist based in Connecticut.

• NTT Data is looking for a Esri/ArcGIS Specialist based in Arlington.

• BP is looking for a Senior GIS Specialist based in Denver.

• TomTom is looking for a Staff UX Designer under their Map Visualisation team based in Amsterdam.

• Esri is looking for a remote GIS Project Manager under their Assessment Department based in Canada.

Just for Fun

A research team aboard the Polarstern icebreaker has discovered a small, uncharted island in the Weddell Sea after sailing into a mysterious “danger zone” that was previously hidden from all nautical maps.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — your weekly map to the latest geospatial news. This newsletter is a bit more like RGB than SAR - we’re impacted by the weather, but we’re tried and true. The aim is to help you become a better geospatial data scientist in less than 5 minutes a week.

In today’s newsletter:

• AlphaEarth Insights: Embeddings reveal hidden land-cover structure.

• Disaster AI: Domain adaptation improves damage detection.

• Urban Planning: Deep learning unifies fragmented city data.

• 3D Remote Sensing: AI models finally learn elevation.

• Crop Adaptation: Climate-responsive planting strategies simulated globally.

Subscribe now

Research you should know about

1. Cracking open Google’s geospatial black box

I’ve previously covered Google’s AlphaEarth a few times on here. In short, it’s one of the new geospatial foundation models trying to turn satellite and Earth observation data into reusable “embeddings”. In simple terms, these embeddings are compressed numerical descriptions of places on Earth. The tricky part is that these numbers are usually hard to interpret. A new paper tries to open that black box by asking what the individual embedding dimensions seem to capture when applied to land cover classification.

The main finding is that the embedding space appears to have a kind of internal geography. Some dimensions act like specialists, strongly linked to one land cover type, such as permanent water, built-up areas, grassland, bare soil, or moss and lichen. These make intuitive sense because certain land covers have very distinctive spectral or structural signatures. Water, for example, has very low reflectance in near-infrared and shortwave infrared bands, while bare soil and sparse vegetation have a very different year-round pattern.

The more interesting part is that other dimensions are shared across multiple land cover types. These seem to capture messy transition zones: cropland and grassland, shrubland and tree cover, bare soil and wetlands, or snow and sparse vegetation. That’s useful because real landscapes rarely fit neatly into clean categories. The paper’s bigger point is that geospatial foundation models may be learning both the “core” of land cover classes and the fuzzy spaces between them. If that holds up across more tasks and regions, it could make these models easier to prune, explain, and use for things like change detection, land degradation monitoring, and environmental planning.

Another pretty interesting finding is that the embeddings do a lot of unnecessary heavy lifting. Because the researchers mapped out exactly what each dimension does, they found that you simply do not need to use all 64 of them. Depending on the specific terrain you are looking at, you can hit 98% accuracy using just two to twelve targeted dimensions. This means developers can prune away the dead weight and slash their computing and storage costs by up to 90%, making it far cheaper to run high-resolution global models without losing any meaningful detail.

2. Building AI that works across different disaster zones

When a major disaster strikes, emergency responders increasingly rely on AI to rapidly scan satellite imagery and assess building damage. This allows human operators to stop squinting at fuzzy photos and focus on deploying rescue teams. However, there is a fundamental flaw in how these systems are currently built. If an AI model is trained on satellite photos of an earthquake in Turkey, it could completely fail to detect damaged buildings from a hurricane in Louisiana. This phenomenon, known as ‘domain shift’, happens because the AI gets confused by different camera angles, weather conditions, or regional architecture, rendering the tool useless for new, unseen disasters.

To solve this, researchers experimented with a technique called Supervised Domain Adaptation (SDA). They took a top-tier AI model originally trained on a massive global dataset of various disasters and fine-tuned it using a small batch of specific data from Hurricane Ida. Rather than just relying on standard RGB satellite images, they also fed the AI a variety of mathematically enhanced pictures. They tested ‘unsharp masking’ to highlight tiny cracks and splintered roofs, ‘contrast enhancement’ to spot subtle water damage, and ‘edge detection’ to make the outlines of buildings stand out.

The researchers found that Domain Adaptation was absolutely essential; without it, the AI failed to identify severely destroyed buildings entirely. When paired with ‘unsharp masking’, the model achieved its absolute best results, boosting its ability to detect ‘major damage’ by 190% and ‘destroyed’ buildings by an incredible 341% compared to baseline models. Interestingly, the researchers found that combining all the image enhancements at once actually confused the AI, proving that when it comes to training robust disaster-response tools, less is often more.

3. A deep learning framework for holistic urban planning

As I’m sure you all know, OpenStreetMap is one of the most useful free geospatial datasets out there. And I’m also sure you know the main issue with it: quality varies a lot by place. Some cities have really detailed road networks, building footprints, land-use polygons and points of interest. Others are patchier, especially in fast-growing or less well-mapped areas. A new paper in Scientific Reports looks at whether deep learning can help turn OSM into something more useful for urban planning. The case study is Krasnodar, a rapidly growing city in southern Russia, where the authors combine OSM with Sentinel-2 imagery, demographic data, traffic sensors and air-quality measurements.

The main idea is to build a single workflow that handles several planning tasks at once. The authors use different models for different jobs: a CNN for land-use classification, U-Net for building footprint extraction, LSTM networks for traffic forecasting, and a hybrid CNN-RNN model for short-term air-quality prediction. The results are pretty strong. The land-use model reached 91.6% accuracy, the building footprint model reached 94.0% accuracy, the traffic model had an RMSE of 3.6 vehicles per hour, and the air-quality model had an RMSE of 2.3 µg/m³ for PM2.5 forecasting. The framework also showed that OSM performed best for roads and buildings, while points of interest were less reliable, likely because they depend more heavily on voluntary tagging.

The useful part of this paper is the shift away from treating urban datasets as separate layers. Building footprints help make sense of urban structure, land-use classification helps identify functional zones, traffic prediction captures mobility pressure, and air-quality modelling adds an environmental layer. Together, these outputs can support things like zoning updates, green-space planning, congestion management and pollution monitoring. There are still some clear limits: the study is based on one city, OSM quality is uneven, and deep learning models can be expensive for smaller planning departments to run. But the broader direction is interesting: free geospatial data, satellite imagery and relatively standard deep learning models can now be stitched together into a pretty practical urban intelligence system.

4. Teaching AI to see the third dimension in satellite imagery

When it comes to analysing satellite imagery, most modern Vision-Language Models (VLMs) have a massive blind spot: they can only see in 2D. While these models are fantastic at looking at a flat image and identifying forests, roads, and buildings, they have absolutely no concept of height or terrain. This is a pretty big problem if you are trying to use AI for things like predicting where a flood will hit or assessing landslide risks, where the physical slope and elevation of the land are far more important than what it looks like from above.

To fix this vertical blind spot, researchers built GeoHeight-Bench, a new testing framework specifically designed to see if AI can understand height. Because getting experts to manually annotate the elevation of thousands of buildings and hills is incredibly expensive, the team used an automated AI pipeline to generate the data instead. The resulting benchmark forces models to tackle a range of 3D problems, from simply retrieving the exact elevation of a specific pixel, to identifying the tallest building in a city, to predicting which areas of a map are most likely to flood based on the terrain.

To prove that AI can actually learn to see in 3D, the researchers also built their own model called GeoHeightChat. Instead of just feeding the AI raw optical images, they used a two-stage training process to teach it how to implicitly guess the geometric structure of a landscape just by looking at a standard 2D photo. When tested on the new benchmark, GeoHeightChat completely blew the competition out of the water, scoring 44.14% overall compared to GPT-4o’s 21.61%. This proves that by injecting a sense of vertical scale into these models, we can unlock a whole new level of practical, real-world problem-solving for remote sensing AI.

You can check out the project page here.

Geospatial Datasets

1. High-altitude wetlands map

This newly developed dataset presents the very first global, high-resolution (30 m x 30 m) map of high-altitude wetlands across the world’s major mountain regions. The researchers combined Sentinel imagery, elevation data, and global ecoregion maps with machine learning to identify more than 30,500 km² of wetland ecosystems. The dataset is useful because high-altitude wetlands remain poorly mapped despite their importance for water storage, runoff regulation, and ecosystem functioning, particularly across remote mountain regions such as the Himalayas and Andes. You can access the data here and the code here.

2. Watershed hydrometeorological dataset

The MACH dataset compiles hydrometeorological data across 1,014 US watersheds, combining daily meteorological forcings with streamflow observations over a 44-year period, with some catchments extending back as far as 75 years. It also includes watershed-level attributes such as geology, topography, land cover, and climate characteristics. You can access the data here and the code here.

3. Climate-responsive crop selection dataset

This dataset explores how changing crop varieties and planting schedules could help agriculture adapt to climate change by simulating crop yields and water use for maize, wheat, soybean, and rice between 1961 and 2100. One of the more interesting aspects is its focus on adaptation timing, showing how relatively small shifts in sowing dates can substantially affect water demand and crop performance under warming conditions. You can access the data here and the code here.

4. European Atlantic wave climate dataset

A new dataset provides high-resolution projections of future wave conditions along the European Atlantic coastline using regionally downscaled CMIP6 climate simulations. The researchers generated 3-hourly directional wave spectra for more than 1,000 offshore locations across both historical (1985 to 2014) and future (2030 to 2059) periods under two emissions scenarios, including both integrated wave parameters and full spectral energy information. You can access the data here and the code here.

Other useful bits

• An important new global assessment has applied the Red List of Ecosystems framework to mangroves for the first time, providing a detailed look at the pressures facing coastal ecosystems worldwide. The report finds that roughly half of global mangrove ecosystems are now considered at risk due to factors such as coastal development, sea-level rise, pollution, and changing sediment dynamics. Beyond the conservation implications, the assessment also highlights the growing role of geospatial monitoring in tracking ecosystem degradation and coastal resilience over time.

• Vantor is partnering with Google Earth AI to integrate more advanced geospatial reasoning capabilities into its Tensorglobe platform. The aim is to move beyond basic object detection towards understanding more complex spatial behaviour and relationships within imagery and geospatial data. One of the more notable aspects is that these capabilities are being designed for classified and air-gapped environments, where many large AI systems are still difficult to deploy securely.

• NOAA is using AI and cloud infrastructure to modernise weather forecasting workflows by migrating large volumes of historical climate and meteorological data into cloud-based systems. The broader goal is to speed up forecasting pipelines for extreme weather events and improve model efficiency, particularly as data volumes continue to grow. At the same time, NOAA officials have stressed that AI tools are intended to support rather than replace scientific expertise, especially for high-stakes forecasting decisions.

• Google Earth is expanding its professional geospatial toolkit by adding global data layers and native Earth Engine raster support directly into its no-code interface. The update also includes an AI-powered feature called “Ask Google Earth”, which allows users to search for and visualise datasets using natural language prompts. The broader direction is fairly clear: reducing the technical barriers required to work with large-scale geospatial datasets and remote sensing products.

Jobs

• TomTom is looking for a Staff UX Designer under their Map Visualisation team based in Amsterdam.

• Esri is looking for a remote GIS Project Manager under their Assessment Department based in Canada.

• Stantec is looking for a GIS Analyst under their Energy and Resources budiness unit based in Toronto.

• EIB is looking for a Data Warehouse Officer based in Luxembourg.

Just for Fun

USGS has brilliantly released a seamless, globally consistent geologic map of the entire Moon at an incredible 1:5,000,000 scale.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — a newsletter that’s slightly cheaper than your ESRI subscription. In any case, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Nightlights Harmonisation: Deep learning links DMSP and VIIRS.

• Map Navigation: AI struggles with route planning.

• Earth World Models: RS-WorldModel predicts future satellite scenes.

• Satellite Image Editing: RSEdit reshapes remote sensing imagery.

• Google Urban Embeddings: S2Vec summarises the built environment.

Subscribe now

Research you should know about

1. Harmonising nighttime light data across decades

Anyone who’s worked with nightlights data knows the long-running headache: DMSP-OLS data goes back to 1992 but suffers from saturation in city centres, blooming, and no on-board calibration. VIIRS, which kicked in from 2012, fixes most of these issues with finer resolution and a much wider dynamic range. The problem is, if you want a long time series stretching back before 2012, you’re stuck stitching together two sensors that don’t really speak the same language. A new paper addresses this with a deep learning approach that translates DMSP imagery into something that looks like it came out of VIIRS.

The authors use a CUT-based generator (a type of image-to-image translation model) trained on overlapping DMSP and VIIRS data. The idea is to teach the model what a VIIRS scene “should” look like given a DMSP input, so you can then run it on pre-2012 DMSP data and get a harmonised series. On their held-out test set of 1,862 patches, they get an R² of 0.87 on radiance, an RMSE of 0.114, and an SSIM (structural similarity) of 0.79. Visually, around 75% of cases look pretty clean, with the model successfully recovering internal structure in cities that DMSP had flattened into uniform blobs.

It’s not flawless though. About 8% of patches throw up artefacts, and the failure modes are pretty instructive. In megacity cores where DMSP is fully saturated at DN=63, the model can’t hallucinate plausible internal structure and produces checkerboard patterns from the upsampling kernel. Around isolated bright points like ports and gas flares, you get halo effects where the model over-generates radial glow. So if you’re using harmonised data for analysis of dense urban cores or industrial sites, you’ll want to flag those areas. For everything else, this looks like a useful step towards a properly continuous nightlights record from 1992 to today.

2. Testing if AI can navigate a map

Multimodal large language models (MLLMs) are becoming pretty smart at analysing satellite images. If you show them a photo of a landscape, they can usually identify the buildings, spot the rivers, and classify the terrain. But there’s a massive difference between simply recognising objects and actually planning a route through them. If a rescue team needs to know the safest path for an off-road vehicle across a flooded disaster zone, simply identifying the water isn’t enough; the AI needs to understand the vehicle’s capabilities, map out the terrain, and plot a strict, step-by-step route. Until now, there hasn’t been a reliable way to test if AI models can actually do this kind of complex, constraint-based planning.

A new study introduces NeSy-Route, a massive new testing framework designed to evaluate how well AI models can navigate remote sensing imagery. Instead of just asking the AI to pick the best route from a multiple-choice list, NeSy-Route forces the model to complete three increasingly difficult tasks. First, the AI has to read a text prompt (like “find the fastest route for a pedestrian avoiding water”) and translate those rules into strict mathematical constraints. Next, it has to look at the satellite image and correctly identify which parts of the terrain match those constraints. Finally, it has to generate an actual, coordinate-by-coordinate path from start to finish.

The researchers tested 10,821 different scenarios across a variety of top-tier AI models, and the results were pretty revealing. While most advanced models were pretty good at understanding the text constraints, they completely fell apart when asked to actually plot the route on the map. Even the smartest proprietary models generated highly inefficient paths, while open-source models often plotted routes that drove straight through restricted obstacles. Ultimately, this benchmark proves that while AI is great at describing satellite images, it still lacks the deep, global reasoning required to reliably navigate the real world. I don’t think this is surprising though, as LLMs are not trained/fine-tuned for the task (yet…).

3. A unified world model for Earth observation

If 2025 was the year of ‘foundation models’, 2026 is the year of ‘world models’. Basically, the idea is that a World Model understands complex environments and predict future states for things like autonomous driving and robotics. However, applying this concept to Earth observation has been pretty difficult. Typically, remote sensing algorithms are split into two completely separate camps. Models either understand and describe changes between satellite images, or they synthesise new landscapes from scratch. Because these tasks are kept isolated, the algorithms miss out on shared geographic knowledge, leaving generative models hard to control and analytical models unable to grasp future physical constraints.

RS-WorldModel is a new system that bridges this gap by tackling both spatiotemporal change analysis and future scene forecasting simultaneously in three stages. These stages are worth understanding because each does something distinct. First, Geo-Aware Generative Pre-training teaches the model to predict future scenes conditioned only on geospatial metadata, with no text involved. Second, Synergistic Instruction Tuning jointly trains the model on both change description and text-guided forecasting, so the two tasks reinforce each other. Third, Verifiable Reinforcement Optimization uses GRPO with task-specific rewards: cosine similarity for forecasting, and an LLM judge for change descriptions that can detect physically implausible outputs (e.g. impossible illumination changes given the sun angle). The ablations show each stage matters. Stripping out the geographic metadata alone bumps FID from 50.28 to 53.72, and removing the pre-training stage entirely sends FID up to 73.55.

The numbers are pretty compelling. On change description, RS-WorldModel beats Qwen3-VL-32B on most metrics despite being 16x smaller, with ROUGE-L jumping 21% over the same-size base model. On forecasting, it cuts FID by 48% relative to CRS-Diff and even beats Gemini-2.5-Flash Image (43.13 vs 46.14). The qualitative examples are particularly nice: when prompted with a winter scene description, the model preserves the underlying settlement layout while adding realistic snow cover and long shadows from a low sun angle, whereas the baselines either miss the structure or generate geographically implausible textures. For anyone working on land-use change, climate adaptation, or any application where you’d want to simulate future satellite imagery under different scenarios, this looks like a pretty interesting tool.

4. RSEdit: giving AI the power to reshape satellite imagery

While text-to-image AI models can easily generate highly realistic pictures of cats or fantasy landscapes, they struggle when asked to edit remote sensing satellite imagery. If you prompt a standard AI editor to show what a village would look like after a flood, it will often hallucinate buildings that don’t exist, distort the strict top-down perspective, or break the laws of physics. This happens because general-purpose AI models lack a deep understanding of geography and are built using conditioning methods that don’t align with the rigid spatial rules of Earth observation data.

To fix this, researchers built RSEdit, a new framework specifically designed to edit remote sensing imagery. Instead of forcing satellite data to fit a generic AI model, RSEdit adapts the underlying architecture of top-tier diffusion models (like Stable Diffusion and PixArt-α) to respect the strict spatial layout of satellite images. For older models, it tightly binds the original image to the edit instructions pixel-by-pixel, and for newer models, it treats the edit as a continuous stream of data tokens. The researchers trained the system on over 60,000 before-and-after satellite images detailing everything from urban expansion to natural disasters.

The results are pretty impressive. When asked to simulate complex scenarios like a tsunami hitting a coastline or a wildfire damaging specific structures, RSEdit generated physically plausible, highly accurate edits without hallucinating extra details or warping the surrounding roads and vegetation. In direct comparisons using specialised building-damage assessment tools, RSEdit outperformed leading general-domain editors like InstructPix2Pix by a massive margin. Ultimately, this framework provides a powerful, on-demand way to simulate disaster impacts and urban growth, creating a valuable new source of training data for environmental analysis.

Geospatial Datasets

1. High-res in-season crop mapping dataset

The newly developed In-season Crop-type Data Layer (ICDL) provides 10-metre resolution crop planting maps across the contiguous United States. You can access the data here and the code here.

2. Ancient China population dataset

A pretty original new dataset reconstructs county-level population distributions in ancient China for the pivotal years of 2, 742, 1102, and 1820 AD. It estimates population figures for over 6,000 counties across four representative dynasties. You can access the data here.

3. Off-shore marine cadastre dataset

The US Bureau of Ocean Energy Management has recently released a new Offshore Marine Cadastre Data Collection, essentially consolidating various regionally focused datasets into one streamlined national resource. You can access the data here or here. You can also check out the navigator here.

4. Comprehensive crop yield dataset

The CYCleSS dataset offers a large-scale resource for predicting crop yields across England, blending precision agriculture with environmental data. It features anonymised yield data from 934 fields alongside 10-km resolution satellite, daily weather, and soil type information from 2015 to 2017. You access the data here and the code here.

Other useful bits

• Google Research introduced S2Vec, a new AI framework that learns to read the built environment of our cities just like a human would. By transforming complex geospatial data into simple mathematical summaries, it provides a way of predicting important socioeconomic and environmental patterns across the globe.

• The WMO has published its latest State of the Global Climate report.

  It brings together evidence on ocean heat, sea ice, temperatures, greenhouse gases, and other indicators of a changing climate. It is also a useful reminder of why long-term Earth observation matters for climate monitoring, risk management, and public policy.

• The World Bank has launched the Land Data Map, an interactive platform for exploring land-related data. The tool makes it easier to see how land systems connect with development outcomes such as economic growth, jobs, and investment. It is a useful resource for anyone working on land governance, urban development, or spatial planning.

Jobs

• TomTom is looking for a Staff UX Designer under their Map Visualisation team based in Amsterdam.

• UN DESA is looking for two interns in (1) Geodesy & Geospatial Research Support and (2) Digital Design, Data Visualization & Geospatial Communications.

• Esri is looking for a remote GIS Project Manager under their Assessment Department based in Canada.

• Stantec is looking for a GIS Analyst under their Energy and Resources budiness unit based in Toronto.

Just for Fun

NASA has released some images of the SWOT satellite to map the Earth’s ocean floor.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — your weekly map to the latest geospatial news. In any case, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Urban Physics: PDEs model city sprawl dynamics

• Map Training: OpenStreetMap improves satellite AI captions

• EO Embeddings: Blueprint for stronger geospatial representations

• City Graphs: New Python library for urban networks

• Aerosol Forecasts: AI delivers rapid global predictions

Subscribe now

Research you should know about

1. Why do cities sprawl? The physics of urban growth

Between 1985 and 2015, the total amount of land covered by cities doubled, eating into green spaces, worsening air quality and making infrastructure incredibly expensive to run. Despite this massive transformation, actually explaining how and why cities expand the way they do is pretty difficult. Traditional urban economics often uses models that treat cities as if they are in a state of perfect balance, assuming that land is instantly redeveloped to its optimal use like a neat, circular dartboard. The reality is that cities grow in messy, uneven and unpredictable ways, driven by everything from traffic congestion to developer whims.

A new study argues that we should look at cities not through the lens of traditional economics, but through the physics of ‘surface growth’. In the same way that physicists use Partial Differential Equations (PDEs) to model the jagged edges of a growing bacterial colony or the spread of a tumour, these same mathematical tools can be used to model the irregular, sprawling boundaries of a city. Unlike older economic models, PDEs can handle the chaotic, real-world feedbacks of urban growth, such as how the construction of a new railway line suddenly makes a distant suburb boom, which in turn demands even more roads.

Recent studies have shown that this isn’t just an abstract theory. When researchers applied these physics-based PDE models to historical data from London and Sydney, they successfully replicated the real-world shift from dense, packed city cores to sprawling commuter belts over the last 150 years. The models naturally captured the ‘angiogenic’ growth of the cities, where population density and transport networks feed off each other in a constant cycle. Ultimately, the researchers argue that by merging complexity science with satellite data, planners can finally get a mathematical grip on urban sprawl, allowing them to test the long-term impact of new infrastructure before pouring any concrete.

2. Using maps to teach AI about satellite imagery

When it comes to processing satellite imagery, vision-language models (VLMs) have historically relied on a technique called ‘pseudo-labelling’ to learn about the Earth. Because high-quality, human-annotated satellite data is incredibly rare and expensive, developers usually rely on massive, general-purpose frontier models like GPT-5 or Gemini to act as a ‘teacher’. These teacher models look at satellite images and generate captions, which are then used to train a smaller ‘student’ model. However, this approach is both expensive and fundamentally flawed. The student model can never be smarter than its teacher, meaning it inherits all of the teacher’s mistakes and hallucinations.

Researchers have introduced OSMDA (OpenStreetMap-based Domain Adaptation) to break this reliance on expensive external teachers. The core idea is pretty simple: instead of asking a massive AI to guess what is in a satellite photo, the researchers pair the satellite image with a rendered map tile from OpenStreetMap. Because modern VLMs are already excellent at reading charts and OCR, the model can simply read the map to identify the roads, buildings and land-use polygons, and then cross-reference this with the satellite image to write a highly accurate, geographically grounded caption. This allows a capable base model to act as its own annotation engine.

Using this self-contained pipeline, the team generated OSMDA-Captions, a massive dataset of over 200,000 highly detailed image-caption pairs, entirely for free. When they mixed this new dataset with existing remote sensing data to train their OSMDA-VLM model, it achieved state-of-the-art results across the majority of ten rigorous benchmarks. It completely outperformed models that were trained using expensive frontier teachers, proving that leveraging crowdsourced geographic data is a far more scalable and accurate way to adapt AI to the remote sensing domain.

3. The blueprint for EO embeddings

Earth observation satellites generate massive amounts of data every day. To make analyzing this imagery more efficient, developers use Geospatial Foundation Models to compress raw satellite images into compact mathematical representations called embeddings. This is something I’ve covered previously here. By reusing these embeddings, pipelines can run much faster without constantly reprocessing the raw images. However, the best way to extract and design these embeddings (e.g. choosing the right model architecture, the best layers, or the optimal pooling method) has remained unclear, which can lead to suboptimal performance in real-world applications.

A recent study introduces a systematic blueprint for designing these embeddings by rigorously evaluating various GeoFM configurations using the NeuCo-Bench framework. The research team tested how different architectural decisions, pretraining strategies, and data aggregation methods impact the AI’s ability to track diverse environmental factors, from crop coverage to biomass and urban heat islands.

The findings offer some useful guidelines for developers. The study shows that Vision Transformers consistently produce stronger, more versatile embeddings than Convolutional Neural Networks (CNNs) for these tasks. When compressing the spatial data, simple “mean pooling” (basically averaging out the features) proved to be the best strategy across the board (simple is best as they say…). Interestingly, the researchers discovered that pulling data from the final layer of a CNN often degrades accuracy for tracking continuous physical variables, meaning developers should extract data from intermediate layers instead. Finally, the study highlights that stitching together embeddings from models trained with different self-supervised learning objectives creates highly robust representations, effectively compressing satellite data by a factor of 500 while maintaining exceptional predictive power.

Geospatial Datasets

1. Cactus ecological and evolutionary dataset

CactEcoDB brings together spatial, environmental, trait, and phylogenetic data for over 1,000 cactus species. It combines occurrence records with a time-calibrated phylogeny, making it useful for studying biodiversity patterns, species evolution, and conservation risks. You can access the data here and the code here.

2. Pore-scale CO2-water interaction dataset

This new dataset captures how CO2 and water interact within porous media at the pore scale, with relevance for geoscience and carbon capture and storage. It includes 624 high-resolution 2D samples across 100 time steps under a constant injection rate, generated using numerical simulations. You can access the files here and the code here.

3. High-precision landslide event dataset

This dataset maps 1,582 landslide events across mainland China between 2008 and 2024. It uses LLMs to extract information from local news reports, capturing detailed timing and location data, often at village level. You can access the data here and the code here.

4. Forest disturbance deep learning dataset

The Deep4Dist dataset provides around 17,500 high-resolution image patches (0.2 m) from Rhineland-Palatinate, Germany. It combines RGB, near-infrared, and height data, with segmentation labels for disturbance types such as bark beetle damage, clear cuts, and windthrow. Access the data here and the code here.

Other useful bits

• A new Python library called City2Graph has just launched, allowing developers to transform complex urban datasets into seamless graph representations. It’s a pretty useful resource for anyone looking to build advanced spatial network analyses or power innovative artificial intelligence applications using city mobility and infrastructure data.

• The Planet and NVIDIA are teaming up to build a new AI-powered engine that processes planetary satellite imagery in seconds rather than hours. The system uses high-performance computing to generate higher-resolution outputs and enables a searchable, near real-time view of the Earth. This improves access to up-to-date geospatial data for monitoring and analysis.

• SpaceX has exceeded 10,000 active Starlink satellites in low Earth orbit following a double launch. This marks a significant expansion of its global broadband network, increasing coverage and capacity across regions.

• Researchers in China have introduced an AI-based system for global aerosol and weather forecasting. Trained on over 40 years of data, it produces detailed five-day forecasts in under a minute. The model supports faster environmental monitoring and improved understanding of atmospheric conditions.

Jobs

• UN DESA is looking for two interns in (1) Geodesy & Geospatial Research Support and (2) Digital Design, Data Visualization & Geospatial Communications.

• UNOPS is looking for an ICT Associate based in Valencia.

• Esri is looking for a remote GIS Project Manager under their Assessment Department based in Canada.

• Stantec is looking for a GIS Analyst under their Energy and Resources budiness unit based in Toronto.

Just for Fun

In celebration of Earth Day, NASA has released a cool interactive tool that spells out any name using natural geographic features captured by Landsat satellites.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge. If you called your high school cover band Rasterheads, we have one thing to say to you. Welcome home… The aim of this newsletter is, as always, to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Map Compression: Optimising tiles without losing spatial detail

• Embedding Methods: Moving beyond averages improves model accuracy

• LLM Reliability: Reducing hallucinations in satellite image analysis

• 5G Prediction: Fixing spatial bias in network demand models

• Soil Dataset: High-resolution global soil carbon mapping

Subscribe now

Research you should know about

1. Shrinking massive map tiles without losing the details

If you’re reading this newsletter, chances are you love a good interactive map. And let’s face it, who doesn’t? Well, making them fast and customisable is actually pretty difficult. Right now, developers are forced to choose between two flawed options. Server-side rendering generates static image tiles that load quickly, but they lock users into a single visual style with no room for client-side tweaking. Conversely, client-side rendering sends raw vector data to the browser for fully flexible styling, but these vector files don’t have size limits. As datasets grow, vector tiles become bloated with overlapping geometries and endless attribute tables, which chokes network bandwidth and browser memory. Existing compression tools try to fix this by blindly dropping data, but this typically warps geographical boundaries and deletes the exact attributes users want to visualise. Not great…

A new study introduces HiFIVE, a framework that treats map tile reduction as a strict mathematical optimisation problem. Instead of indiscriminately deleting polygons, the system uses a two-stage approach to shrink tiles to a strict size limit while preserving their visual and semantic fidelity. First, a lightweight triage step makes rough cuts by discarding visually insignificant records. Next, a highly precise ‘sparsification’ algorithm steps in. This algorithm weighs the visual prominence of a shape (such as its pixel footprint) against the usefulness of its underlying data. It selectively nullifies specific attribute values that are unlikely to be used for styling, like random unique identifiers, while preserving categorical data like state names or road types.

When tested on massive terabyte-scale datasets, HiFIVE processed almost a billion records in under an hour. The resulting maps proved to be vastly superior to those produced by standard reduction tools. By intelligently choosing exactly which data points to keep and which to discard, the framework maintained crisp, undistorted boundaries and retained the necessary attributes for complex client-side styling. Ultimately, this approach provides a highly scalable way to explore massive spatial datasets directly in the browser without sacrificing rendering speed or visual accuracy.

You can access the code here.

2. Why averaging satellite data is a bad idea

Geospatial foundation models are brilliant at turning satellite images into highly detailed pixel-level data. However, many practical applications require labelling entire regions, such as a whole farm or a residential neighbourhood. To make this work, developers typically compress thousands of pixel vectors into a single representation using a technique called mean pooling, which is essentially just averaging everything out. The major flaw with this default approach is that it completely erases all the nuanced variations within a patch. When these models are deployed in new geographic areas, this loss of detail causes their accuracy to drop significantly.

A team of researchers built a new dataset called EuroSAT-Embed. They generated 81,000 embedding files using three different foundation models and benchmarked eleven training-free pooling methods. Instead of just averaging the pixels, they tested richer statistical summaries that capture the extremes and the variability within a specific region. For example, a method called stats pooling combines the minimum, maximum, average and standard deviation of the pixels, while covariance pooling looks at the complex relationships between all the different data points.

The results clearly show that moving beyond simple averages makes a massive difference for spatial generalisation. By using richer pooling schemes, the researchers managed to cut the geographic accuracy gap in half and boosted overall performance by up to 6 per cent on spatial splits. They recommend a straightforward three-tier strategy for anyone working with earth embeddings. Mean pooling is fine for a quick baseline, but stats pooling should absolutely be the default choice, while covariance pooling should be reserved for projects where peak accuracy is the absolute priority.

3. Stopping AI from hallucinating over satellite maps

Multimodal LLMs are great at many things, but they tend to make things up when looking at satellite imagery. This issue, known as hallucination, usually happens for two reasons. Either the models get distracted by the massive scale of remote sensing images and can’t find the right area, or the targets are simply too small and cluttered to see clearly. To figure out exactly what is going wrong, researchers built RSHBench, a new diagnostic tool. It proved that models mostly suffer from factual errors, like making up objects or misidentifying attributes, which then snowball into flawed logic.

A clever training-free framework called RADAR essentially forces the AI to use its own internal attention mechanisms to zoom in on the image in two distinct stages. First, it asks a location-oriented query to pinpoint exactly where the relevant visual evidence is hiding. Once it locks onto that specific region, it uses a content-oriented query to zoom in and extract the fine-grained details needed to answer the prompt accurately.

When put to the test across a variety of major open-source and proprietary models, the results were highly impressive. By forcing the AI to actively seek out and refine visual evidence before making a guess, the RADAR framework consistently boosted overall accuracy by 2 to 4 per cent. More importantly, it slashed both factual and logical hallucination rates by around 10 per cent. Ultimately, this gives developers a highly scalable, plug-and-play way to make foundation models much more reliable for analysing complex Earth observation data.

4. Smarter spatial predictions for 5G networks

Predicting exactly where mobile network traffic will spike is essential for planning 5G and 6G infrastructure. While machine learning is great at combining different types of data (like population density and local land use) to map out demand, it often falls into a trap called spatial autocorrelation. Because neighbouring city blocks tend to have very similar traffic patterns, standard AI training methods accidentally leak information between the training and testing datasets. As a result, network planners get a model that looks highly accurate on paper but fails to generalise when deployed in the real world, leading to poorly placed cell towers and wasted spectrum.

A team of researchers developed a new AI-driven framework that forces the model to actually learn rather than just memorise nearby locations. They introduced a two-stage splitting strategy. First, it divides the city into geographically separate clusters to cut off the spatial data leakage. Then, it refines these clusters based on local context, such as whether an area is residential or commercial, to make sure the AI is tested on a truly diverse set of environments. Finally, they apply a Spatial Error Model to scrub out any leftover geographical biases from the predictions.

They tested the framework across five major Canadian cities using a massive crowdsourced dataset of 15 million mobile usage measurements. The new method consistently slashed prediction errors compared to basic location clustering, giving engineers a much more reliable picture of true network demand. When applied to real-world scenarios like 5G spectrum planning, these tighter predictions successfully prevented the costly overestimation or underestimation of network congestion. Ultimately, this gives telecom operators a much sharper tool for figuring out exactly where to deploy their next wave of antennas.

Geospatial Datasets

1. Global soil carbon dynamics dataset

The OpenLandMap-soildb dataset provides the most detailed information to date on global soil carbon dynamics. It integrates over 600,000 field measurements with satellite data and machine learning, and maps soil organic carbon density and content at a 30-metre resolution across three soil depths from the year 2000 onwards. You can access the maps here, the files here, and the code here.

2. Inland water pH and alkalinity dataset

The newly compiled PHALK dataset provides a global assessment of pH and alkalinity across the world’s inland surface waters. It collates chemical data from 18 databases and 55 scientific publications, and maps over 1 million drainage basins. You can access the data here and the code here.

3. Global ocean boundary current dataset

GOXBT dataset provides high-resolution data on the dynamics of major ocean boundary currents. You can access the data here and the code here.

Other useful bits

• ESA’s CryoSat ice-monitoring satellite has received a new software upgrade that allows it to now measure Earth’s magnetic field. Originally designed simply to keep the spacecraft on track, its onboard magnetometer recently captured incredibly precise data during a massive solar storm, offering researchers a fantastic, unexpected bonus alongside dedicated magnetic missions.

• 25 new Open Buildings datasets are now available on HDX thanks to the team at Google Research.

  

• By measuring microscopic changes in gravity on the ocean's surface, a new satellite has helped researchers create the most accurate map of the seafloor to date. One finding is that small underwater hills cover a 70% of the ocean floor 🤯.

• Satellogic has just announced Merlin, a new satellite constellation designed to map the planet every day at 1m resolution. It’s expected to become operational by first half of 2027.

Jobs

• UN DESA is looking for two interns in (1) Geodesy & Geospatial Research Support and (2) Digital Design, Data Visualization & Geospatial Communications.

• UNOPS is looking for an ICT Associate based in Valencia.

• FAO is looking for a Remote Sensing and GIS Specialist based in Rome.

• Esri is looking for a remote GIS Project Manager under their Assessment Department based in Canada.

• ERM is looking for a Spatial Analyst (Remote Sensing) based in Australia.

Just for Fun

The recent equinox saw the sun align perfectly over the equator, treating everyone across the globe to an equal measure of day and night as spring arrives in the north and autumn settles in the south.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — a newsletter that has more rhythm than dembow… In any case, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Radar Model: Billion-scale AI improves SAR image understanding

• Water Resilience: New index captures true water scarcity risks

• Cloud-Free Imaging: AI merges cloud removal and sharpening

• Canopy Heights: Global 1m forest height dataset from Meta and WRI released

• Cropland Emissions: New dataset maps global agricultural emissions

Subscribe now

Research you should know about

1. A billion-scale model for understanding radar imagery

As long time readers know, Synthetic Aperture Radar (SAR) is an incredibly powerful tool for earth observation because it can see through clouds and operate in the pitch black. But teaching AI to understand radar images can be pretty difficult. Unlike normal optical photos, SAR images are plagued by granular “speckle” noise and severe geometric distortions caused by the radar’s side-looking angle. Even worse, SAR data is pretty fragmented. A model trained to identify buildings using one satellite’s specific frequency band or polarisation mode will often completely fail when looking at data from a different satellite. This extreme “domain gap” has prevented the creation of a universal AI model for radar imagery.

Researchers have built CrossEarth-SAR to solve this, the first billion-scale vision foundation model specifically designed to handle the massive diversity of radar data. To keep computational costs down while still using billions of parameters, they employed a “sparse Mixture-of-Experts” (MoE) architecture. Instead of every part of the neural network working on every image, the model uses a “router” to send specific types of radar images to specialised “expert” sub-networks. As part of this, the team built a novel “physics-guided” router that uses actual radar physics (e.g. speckle strength and directional entropy) to decide which expert should handle which image, ensuring the AI adapts to the specific characteristics of the satellite that took the picture.

To train this massive model, the team assembled a dataset of 200,000 radar images, using existing AI models to automatically generate “pseudo-labels” for unlabelled data. They then tested CrossEarth-SAR across 22 benchmarks designed to simulate real-world domain gaps. The model achieved state-of-the-art results on 20 of the 22 benchmarks, outperforming previous models by over 10 per cent in some of the hardest multi-gap scenarios. This suggests that by explicitly hardwiring radar physics into the AI’s routing mechanism, it’s possible to build a single, robust model capable of interpreting radar data from almost any satellite on Earth.

You can check out the project page here and the code here.

2. A smarter way to measure water scarcity

When we think of water scarcity, we usually just look at how much rain is falling or how full the reservoirs are. But a new paper from Scientific Reports argues that this is missing the bigger picture. Whether a community actually runs out of water has just as much to do with politics, infrastructure and economics as it does with hydrology. To fix this, researchers have proposed the Integrated Water Strategic Resilience Index (IWSRI). Instead of just measuring physical water, this new index acts as a broader, more holistic dashboard, combining data on climate variability, governance quality, political stability and economic adaptability to reveal a country’s true ‘water resilience’.

To test this new tool, the team applied it to the Middle East and North Africa, which is essentially ground zero for water stress. The results challenge some common assumptions. For example, Israel, Qatar and the UAE are practically deserts, yet they scored incredibly high on the resilience index. Why? Because at the time they had wealthy, stable governments that had invested heavily in desalination and wastewater recycling. They might be regretting that rating now… Anyway, on the flip side, countries like Yemen, Syria and Libya scored at the absolute bottom. It’s not just that they lack water; it’s that years of war, political instability and destroyed infrastructure have completely crippled their ability to manage the resources they do have.

The authors point out that traditional metrics like the Falkenmark Indicator would completely miss these nuances by focusing solely on per-capita water availability. By integrating sociopolitical factors, the IWSRI shows that water scarcity is often a manufactured crisis. While the researchers acknowledge that quantifying things like ‘governance’ can be tricky, this new index provides a much more realistic map of where the world’s water systems are actually breaking down.

3. Seeing through the clouds with a new all-in-one AI

Satellites monitoring the Earth face a frustrating compromise between detail and frequency. You can either get highly detailed images every few weeks or blurry images every few days. To make matters worse, optical sensors are frequently blocked by clouds, resulting in massive gaps in data. Until now, scientists have tried to fix this by using artificial intelligence to first remove the clouds and then artificially sharpen the images through a process called spatiotemporal fusion. However, treating these as two completely separate tasks often introduces compounding errors that ruin the final picture.

This is what SuperSTF tries to address. It’s essentially a framework that tackles cloud removal and image sharpening at the exact same time. Instead of operating directly on the raw pixels, the system uses a latent diffusion model paired with a Swin Transformer. In simple terms, it compresses the images into a more efficient hidden mathematical space, fuses the frequent blurry data with the rare sharp data, and then rebuilds a pristine image. The model is also fed specific data about cloud locations and the time of year to help it intelligently guess what is hiding beneath the cloud cover.

When tested across diverse regions like urban Washington and agricultural Texas, SuperSTF completely outperformed existing sequential methods. It successfully reconstructed sharp, cloud-free image sequences even when up to 70 per cent of the original high-resolution reference image was obscured by thick clouds. Because it operates in a compressed latent space rather than processing every single pixel during its diffusion phase, it’s also surprisingly fast and computationally efficient. Ultimately, this gives scientists a much more reliable tool for tracking rapid environmental changes, crop health, and urban development without having to constantly wait for a clear sky.

Geospatial Datasets

1. Meta & WRI’s high-res global canopy height map

The newly updated CHMv2 dataset, created by a collaboration between the World Resources Institute and Meta, provides a 1-metre resolution global canopy height map. You can access the data here and the code here.

2. Global cropland emissions dataset

A new dataset from Cornell University and the Land & Carbon Lab maps the greenhouse gas emissions generated by the world's croplands (rice, maize, wheat, and oil palm). You can access the data and code here.

3. Convective weather forecasting dataset

The newly introduced CIDS dataset is designed to train machine learning models for detecting and nowcasting severe convective weather. It covers southeastern China from 2018 to 2023, and captures intense events like short-duration heavy rainfall, thunderstorm winds, and hail at crisp 10-minute intervals. You can access the data here and the code here.

4. Global cropland and irrigation dataset

The MIRCA-OS dataset maps monthly irrigated and rainfed harvested areas between 2000 and 2015. It includes 5-arcminute gridded data for 23 major crop classes. You can access the data here and the code here.

Other useful bits

• ESA’s EarthCARE satellite has just delivered some new global maps of atmospheric dust trails. By using an advanced laser instrument to track how these tiny mineral particles travel across the globe, researchers are getting a wonderfully clear picture of how dust impacts our climate and weather systems.

• Google Earth’s 2026 roadmap has been unveiled, showcasing a shift towards professional workflows. We’re going to see everything from global elevation contours and seamless custom data imports to AI assistants that turn natural language into instant geospatial insights.

• A new initiative in Australia is using Google Earth AI and a bunch of spatial datasets to tackle heart disease in remote communities. By combining environmental data with health records, the approach identifies spatial patterns in risk exposure. The aim is to support earlier intervention by directing care to locations where underlying risk factors are highest.

Jobs

• The UN Department of Economic and Social Affairs is looking for two interns in (1) Geodesy & Geospatial Research Support and (2) Digital Design, Data Visualization & Geospatial Communications.

• FAO is looking for a Remote Sensing and GIS Specialist based in Rome.

• IOM is looking for a Displacement Tracking Matrix (DTM) Systems Developer and Architect based in Geneva.

• UNGSC is looking for a remote ArcGIS Enterprise Administrator from Europe, Middle East and North Africa.

• GHD is looking for a GIS Analyst based in Melbourne.

Just for Fun

This is pretty nuts… 143 million people who spent the last eight years catching Pokémon were actually building one of the largest real-world visual datasets in AI history. Niantic has just revealed that this staggering collection of over 30 billion crowdsourced images is now being cleverly used to train visual navigation AI for delivery robots.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now

Hey guys, here’s this week’s edition of the Spatial Edge — a newsletter that’s as frequent as a Marvel movie. In any case, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Spatial AI: LLMs struggle with pure GPS math.

• Change Detection: Foundation model tracks complex landscape changes.

• War Mapping: Satellites track destruction in conflict zones.

• Urban Shade: High-resolution dataset maps global pedestrian shade.

• Image Alignment: Massive dataset of aligned satellite pairs.

Subscribe now

Research you should know about

1. Do AI models actually understand GPS coordinates?

Large Language Models (LLMs) are increasingly being built into navigation apps and geographical tools, but their ability to actually understand and manipulate GPS coordinates has remained a bit of a mystery. Most spatial AI tests involve asking a model to describe where an object is in a photo of a living room, which doesn’t really translate to calculating the distance between Tokyo and Sydney. To bridge this gap, researchers built GPSBENCH, a new dataset designed to test whether LLMs genuinely understand the Earth’s coordinate system or if they are just bluffing.

The researchers tested 14 top-tier LLMs across two main tracks: ‘Pure GPS’ (geometric math like calculating distances or bearings) and ‘Applied’ (using world knowledge, like identifying which city sits at a specific coordinate). The results show a pretty stark divide. Most models are actually much better at the ‘Applied’ track, using their vast pre-trained world knowledge to guess locations, but they completely fall apart when asked to do the pure spherical geometry required for the ‘Pure GPS’ track. For instance, tasks like calculating the area of a polygon on the globe had a near 0 per cent success rate across the board, proving that the models haven’t actually learned geodetic formulas.

Interestingly, the study also revealed that LLMs have a highly hierarchical understanding of geography. They can almost always identify the correct country for a given GPS coordinate, but their accuracy drops off a cliff when asked to pinpoint the specific city. However, when the researchers added random ‘noise’ to the coordinates, the models’ performance didn’t drop, which proves they aren’t just memorising coordinates from databases but do have a genuine, albeit fuzzy, spatial understanding. Ultimately, this shows that if you want an AI to perform precise geographic reasoning, you still need to augment it with external calculators or specific GPS tools, because right now, their internal compass is a bit broken.

You can access the data and code here.

2. A new foundation model approach to tracking landscape changes

Tracking changes on the Earth’s surface usually relies on binary change detection, which simply spots where a landscape has been altered. Semantic change detection takes this a step further by identifying exactly what those changes are, such as a dense forest being replaced by a paved car park. While incredibly useful for urban planning and disaster relief, building models for this task is notoriously difficult. Most current systems rely on standard visual encoders trained on everyday photos, leaving them poorly equipped to understand the complex, top-down perspective of satellite imagery. Furthermore, because the vast majority of land remains unchanged between satellite passes, the models often get overwhelmed by the sheer imbalance of data and resort to lazy predictions.

A new paper has introduced PerASCD, a new framework driven by a massive remote sensing foundation model. By leveraging an AI that has been explicitly pre-trained on vast amounts of satellite data, the system possesses a much deeper, native understanding of geospatial features. The team paired this foundation model with a custom-built Cascaded Gated Decoder. Older methods typically forced the AI through highly convoluted, multi-branch pathways to separate the before and after semantics. This new decoder streamlines the entire process, handling feature compression, multi-level fusion, and upsampling in a single modular pipeline, which drastically simplifies the overall architecture.

The researchers also patched a frustrating mathematical glitch that has plagued previous models. Older systems used a rigid loss function to force the AI to separate changed and unchanged pixels, but the harsh mathematical boundaries of this rule would often cause the model’s accuracy to suddenly collapse during training. By introducing a softened version of this mathematical rule, the team smoothed out the learning gradients and eliminated the numerical instability. When tested on major benchmark datasets like SECOND and LandsatSCD, the framework achieved state-of-the-art performance, delivering significantly sharper boundaries and fewer false positives than previous methods.

3. Mapping war zones with combined satellite data

The ongoing war in Ukraine has caused immense damage to infrastructure, agriculture and the broader environment. Obviously, sending survey teams into active conflict zones to assess this wreckage is incredibly dangerous and often impossible. To get around this, a new study from Scientific Reports have developed a new method to automatically map the destruction from space using freely available satellite data. By combining radar data from Sentinel-1 with optical imagery from Sentinel-2, they have created a system that monitors conflict-related changes without putting anyone in harm’s way.

The interesting part of this approach is how it adapts to different types of terrain. The algorithm automatically classifies the land cover (separating urban environments from rural or agricultural areas) and then chooses the best analysis strategy for that specific zone. The researchers combined radar-based change detection with optical image classification to spot destruction that single-sensor methods might miss. They also added a ‘context-aware smoothing’ technique, which essentially filters out visual noise and local glitches to produce a much cleaner and more reliable map.

When put to the test, the results were pretty impressive. The team compared their automated findings against the official UNOSAT database and found that their tool successfully detected over 80 per cent of damaged buildings. Furthermore, their smoothing technique proved to be far more accurate at detecting built-up areas than existing global land-cover products like AlphaEarth. Ultimately, this gives humanitarian organisations a rapid and reliable way to pinpoint destruction in restricted regions.

You can access the data here and the code here.

Geospatial Datasets

1. Urban pedestrian shade mapping dataset

This dataset provides high-resolution simulations of pedestrian shade provision across nine geographically diverse global cities, including Amsterdam, Sydney, and Rio de Janeiro. You can access the data here and the code here.

2. SAR-Optical image alignment dataset

The SOMA-1M dataset offers a massive collection of over 1.3 million precisely aligned Synthetic Aperture Radar (SAR) and optical image pairs. The dataset will be publicly released here.

3. Multimodal environmental monitoring dataset

The newly introduced MMEARTH-BENCH is a collection of five environmental monitoring tasks designed to evaluate geospatial machine learning models on a global scale. It features 12 diverse data modalities and includes geographic test splits to specifically challenge how well algorithms adapt to unseen regions. You can access the dataset, code, and read more about the project here.

4. Global subnational farm size dataset

This dataset provides the most comprehensive and spatially detailed empirical assessment of global mean farm size to date, targeting the year 2000. Unlike previous products that rely on national averages or modelled data, this collection compiles census and survey information at the smallest available subnational administrative level for 101 countries, alongside national data for 99 others. You can access the data and code here.

Other useful bits

• The team behind AlphaEarth Foundations has just rolled out their 2025 Satellite Embedding dataset, cleverly packing an entire year's worth of satellite data into neat 10-metre pixels. This update makes it easier than ever to spot global shifts without the headache of processing raw imagery.

• Google DeepMind has showcased a new realistic city planner app powered by Gemini 3.1 Pro. It tackles complex terrain and simulates traffic to generate incredibly high-quality visualisations of future urban infrastructure.

• A new time series foundation model called TimesFM has just been released, which has been pre-trained with 100 billion data points. It’s showing pretty impressive performance across a whole host of domains, making it a useful resource for anyone keen to dive into machine learning and forecasting.

Jobs

• Mapbox is looking for a remote Software Development Engineer based in either Germany or Finland.

• The European Centre for Medium-Range Weather Forecasts (ECMWF) is looking for a (1) Data Management Engineer and (2) Climate Data and AI/Machine Learning Scientist, both based in either Bonn, Germany or Reading, UK.

• The European Organisation for Nuclear Research (CERN) is looking for a GIS Specialist and Developer based in Geneva.

Just for Fun

The Artemis II crew ran into a very Earthly problem whilst en route to the Moon. Just hours into their ten-day flyby, the astronauts had to radio mission control for IT support after their Microsoft Outlook crashed. It’s comforting to know that no one is safe from an email glitch.

That’s it for this week.

I’m always keen to hear from you, so please let me know if you have:

• new geospatial datasets

• newly published papers

• geospatial job opportunities

and I’ll do my best to showcase them here.

Yohan

Subscribe now