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

Hey guys, here’s this week’s edition of the Spatial Edge — a safe space for Terra and exactextract enthusiasts... 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:

• Human Development: Satellites map local development levels.

• Flood Prediction: LLMs estimate damage without training.

• Ecological Mapping: Testing foundation models on ecosystems.

• Urban Inequality: Satellites reveal China’s built disparities.

• Hyperspectral Data: Planet expands its open dataset.

Subscribe now

Research you should know about

1. A much better way to map human development

For years, the UN’s Human Development Index (HDI) has been the gold standard for measuring a country’s wellbeing, factoring in health, education and income. The problem is that HDI data is generally only available at the national or, at best, provincial level. This makes it almost useless for local policy decisions, like deciding which specific neighbourhoods need a new clinic or school. A new paper from Nature Communications used satellite imagery and machine learning to produce the first high-resolution global map of HDI, estimating development levels for over 60,000 municipalities and a 10km-by-10km grid worldwide.

The team achieved this using an approach called MOSAIKS, which translates satellite imagery into a set of random convolutional features. Rather than trying to map irregularly shaped provinces directly, the model learns the relationship between the visual features of an area (like building density, road networks and nighttime lights) and its known HDI. Because this relationship is linear, they can train the model on coarse provincial data and then “downscale” it to predict HDI for much smaller areas based purely on what the satellites see. They validated this by testing it against ground-truth municipal census data in Mexico, Brazil and Indonesia, proving the model could accurately spot local variations.

The results expose a massive flaw in how we currently look at development. The researchers found that if you only use provincial data, more than half of the global population is assigned to the wrong HDI quintile within their country due to “aggregation bias”. It essentially lumps rich urban centres and poor rural outskirts into a single misleading average. By contrast, this new high-resolution data allows policymakers to target aid far more accurately. In a simulated test in Mexico, using municipal data rather than provincial data increased the accuracy of targeting aid to the poorest 10 per cent of the population by over 11 percentage points.

You can access the code here.

2. Predicting flood damage without training models from scratch

Predicting property damage immediately after a flood usually involves training complex machine learning models on highly specific regional data. This requires an immense amount of upstream effort to assemble datasets, engineer features and handle skewed data where extreme damage cases are rare. To bypass this bottleneck, a new study has introduced R2RAG-Flood, a new framework that uses LLMs to predict post-storm Property Damage Extent (PDE) without requiring any task-specific training or fine-tuning.

Instead of fitting new parameters, the framework uses Retrieval-Augmented Generation (RAG). It takes historical tabular data about flood events (like rainfall, elevation and building density) and converts it into concise text summaries paired with logical “reasoning trajectories.” When a new storm hits, the system looks at a specific target area and searches its knowledge base for similar historical cases nearby (geospatial neighbours) and typical examples of different damage levels (prototypes). It feeds these examples to an LLM, asking it to emulate the reasoning process to classify the new target into low, medium or high damage.

The team tested this approach on data from Hurricane Harvey in Harris County, Texas. While a traditional supervised model achieved 0.714 overall accuracy, the training-free R2RAG-Flood approach was highly competitive, hitting up to 0.668 accuracy depending on the LLM backbone used. More importantly, the RAG approach outputs a structured, human-readable rationale explaining exactly why it predicted a certain level of damage. When factoring in the cost of API calls versus the computing power needed to train a model from scratch, the lightweight LLM variants proved significantly more cost-efficient, offering a scalable way to rapidly assess flood impacts in new regions without heavy computational overhead.

3. Putting AI foundation models to the ultimate ecological test

Geospatial Foundation Models (GFMs) are, of course, all the rage for earth observation, but mapping complex ecosystems is a whole different beast compared to drawing basic land cover maps. To see if these models actually live up to the hype, researchers put two leading GFMs (Prithvi-EO-2.0 and TerraMind) to the test against a standard deep learning baseline. They wanted to find out if these systems could handle highly specialised jobs like estimating forest canopy density across the United States and tracking the extent of carbon-rich peatlands in Patagonia.

The results were pretty clear: both GFMs comfortably beat the standard baseline model across all the ecological tasks. By being pre-trained on massive amounts of satellite data, these models avoided the usual pitfalls of standard image classifiers and adapted much better to geospatial nuances. TerraMind slightly outperformed Prithvi on basic tasks, but it really pulled ahead when the researchers fed it multimodal inputs. By combining standard optical imagery with radar and elevation data, the model became much better at separating tricky vegetation types, like distinguishing vital peat moss from generic grass.

Despite the impressive performance, the study highlighted some pretty big roadblocks before we can completely hand ecological mapping over to AI. For one, these models are highly sensitive to the quality of the training labels. When the researchers used coarse, off-the-shelf datasets to teach the models, the AI struggled to draw accurate boundaries, proving that you still need high-fidelity, expert-verified field data. Furthermore, the standard 10-metre resolution of satellite inputs proved to be a major limitation for capturing fine-scale ecological changes. So while these foundation models are a massive leap forward, they still need sharper data and better ground truths to truly map out the complexities of the natural world.

4. Satellite mapping reveals deep built environment disparities in urban China

China’s cities have grown at a breakneck pace over the last few decades, but figuring out exactly how equitable this growth has been at the street level is notoriously difficult due to a lack of building-level data. To tackle this, a team of researchers just released SinoBF-1, a massive national map that categorises the specific function of 110 million individual buildings across 109 major Chinese cities. By combining 1-metre high-resolution satellite imagery with other multi-modal data, they essentially built a microscopic view of the country’s urban landscape to track exactly where resources are concentrated.

Using nine distinct indicators covering everything from facility accessibility to infrastructure sufficiency, the study reveals some pretty big disparities across different regions and city tiers. Unsurprisingly, top-tier megacities dominate when it comes to amenity diversity and access to services, with these perks dropping off a cliff as you move down to lower-tier cities. However, the data shows that mid-tier cities actually offer the most equitable housing allocation. Geographically, southern cities boast the best access to healthcare and education, but this comes at the cost of severe infrastructure overcrowding compared to other regions.

Zooming in on individual cities, the map also highlights a growing divide between old and new neighbourhoods. The researchers found that newer, recently expanded zones on the outskirts of cities suffer from much greater built environment disparities than the early-established urban cores. This spatial footprint serves as a physical ledger of national development policies over the past half century, offering a highly detailed framework for tracking urban inequality in rapidly developing areas.

Access the data here and the code here.

Geospatial Datasets

1. Open hyperspectral satellite dataset

Planet has recently expanded its Open STAC Catalog with nearly 100 new hyperspectral scenes, offering an impressive global footprint for geospatial exploration. You can access the data here.

2. Tile-drainage and Rotation-Enhanced Cropland (TREC) dataset

The newly developed Tile-drainage and Rotation-Enhanced Cropland (TREC) dataset significantly improves the spatial accuracy of ecohydrological models across the Conterminous United States. You can access the data here and the code here.

3. High-resolution global precipitation dataset

The newly updated PERSIANN-CCS-CDR Version 2.0 offers a remarkable high-resolution global precipitation climate record, boasting a 0.04° spatial and 3-hourly temporal resolution. You can access the data here and the code here.

4. Global water storage anomaly dataset

The newly released ML-TWiX dataset is a brilliant resource that extends our understanding of global total water storage anomalies back to 1980, well before the launch of the GRACE satellite missions. You can access the data and code here.

Other useful bits

• Vantor has cleverly teamed up with Google to integrate powerful Earth AI imagery models into its Tensorglobe platform, allowing these tools to be used in secure, air-gapped environments for the very first time. By combining cutting-edge AI with a massive archive of high-resolution satellite imagery, it offers a brilliant new way to effortlessly monitor infrastructure and track changes offline.

• To tackle AI's struggle with 'spatial grammar', researchers have built MapTrace, a new pipeline that generates millions of synthetic map-path pairs for training. This approach has already given models a massive boost in accurately tracing paths on real-world maps, proving just how useful synthetic data can be.

• A developer has cleverly forked Apple’s Embedding Atlas to create Geospatial Atlas, a new open-source tool for exploring massive datasets of up to 100 million points right in your web browser. It brings together tools like WebGPU, DuckDB, and MapLibre. This essentially provides a smooth and interactive way to visualise huge amounts of spatial data without needing heavyweight desktop software.

• A new AI methodology called Groundsource has just been unveiled, turning millions of public reports into a massive historical dataset for predicting urban flash floods. By mapping these events using Gemini and Google Maps, a new model can now forecast sudden flooding up to 24 hours in advance, offering a vital lifeline to communities worldwide.

Jobs

• ESA is looking for two EO Data Architect and AI Experts based in Frascati for their (1) Copernicus Ground Segment Systems Section and (2) Ecosystem Development Section.

• Development Seed is looking for a Technical Project Lead based in the US who will work across their NASA portfolio.

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

• Médecins Sans Frontières (Doctors Without Borders) is looking for a GIS Data Governance Specialist based in Geneva.

• The Center for International Forestry Research (CIFOR) is looking for a Spatial Data Scientist for Machine Learning & Remote Sensing who will be based in either Kenya, Nairobi or remote.

Just for Fun

Researchers at NOAA have shared a rather striking animation of high winds over the Great Lakes, created using their experimental RRFS weather model. It provides a brilliant demonstration of DESI, a clever tool designed to help forecasters effortlessly explore, compare, and share ensemble weather guidance.

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 just as rivetting as a Lex Fridman podcast. 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:

• Hidden Carbon: Earthquake repairs generate massive CO2 emissions.

• Spatial AI: Drones learn to measure 3D dimensions.

• Design Economics: Distinctive buildings boost surrounding property values.

• Location Data: Mobility patterns reveal true venue functions.

• Building Atlas: Open dataset provides global 3D models.

Subscribe now

Research you should know about

1. Earthquakes have a huge carbon footprint

When we talk about the environmental cost of buildings, we usually focus on the materials used to build them or the energy they consume. But a new study in Nature Communications shines a light on a hidden carbon cost: the emissions generated by repairing and rebuilding structures after earthquakes. By integrating seismic risk models with a massive database of construction materials, researchers have estimated that Europe’s building stock embodies nearly 14 billion tonnes of CO2 equivalent. More strikingly, the damage caused by earthquakes across the continent generates an average of 6.6 million tonnes of carbon emissions every single year— roughly the same as the annual emissions of 3.9 million cars.

The study introduces a new metric called ‘Average Annual Embodied Carbon’ (AAEC) to quantify this risk. Instead of just looking at financial losses, this measures the expected yearly carbon footprint of seismic damage. The results show a heavy concentration of this environmental burden in just a few countries. Türkiye tops the list, accounting for over half of the total annual emissions due to its high seismic activity and large number of vulnerable buildings. Italy, Romania, Greece, Spain and Bulgaria also feature prominently, meaning just six nations are responsible for about 90 per cent of Europe’s earthquake-related carbon emissions.

This research highlights a critical blind spot in our current sustainability strategies. While we are busy making buildings more energy-efficient, we often ignore the ‘embodied carbon’ that gets released when we have to fix or replace them after a disaster. The authors argue that seismic resilience is actually a form of climate action. By retrofitting buildings to withstand shocks, we aren’t just saving lives and money; we are also preventing millions of tonnes of CO2 from being pumped into the atmosphere during reconstruction. The team has released their datasets and models publicly, hoping to help policymakers integrate these hidden environmental costs into their disaster risk planning.

2. Giving drones a sense of depth

Remote sensing AI is getting sharper, yet it still struggles with a fundamental human skill: understanding 3D space. Most current models look at 2D pixels and can identify a ‘red car’, but they can’t reliably tell you its actual dimensions or how far away it is from the sensor. To bridge this gap, researchers have developed AirSpatial, a massive dataset derived from drone imagery that introduces 3D bounding boxes to the mix. By combining aerial photos with ground-level video, they have annotated thousands of vehicles with precise spatial data, allowing models to move beyond simple visual recognition to true spatial grounding where an AI can understand depth and scale.

The team used this data to train AirSpatialBot, an agent designed to recognise fine-grained vehicle attributes from the sky. The system uses a clever two-stage training strategy: it starts by learning standard 2D image understanding before fine-tuning on spatial tasks using techniques like Geometric Mapping Learning. Instead of just memorising what a specific car model looks like from above, the bot actually measures the vehicle’s length, width and height in the 3D scene. It then acts like a detective, cross-referencing these physical dimensions with a database to determine the exact make, model and even the price of the car, managing to distinguish between vehicles that look visually similar but differ in size.

In testing, AirSpatialBot significantly outperformed existing models like GeoChat, particularly in tasks requiring depth estimation and dimension measuring. The system excels at ‘target retrieval’, where a user can ask it to find a specific car (e.g. ‘white Mercedes-Benz C-Class’) and the bot locates it by calculating 3D coordinates. This approach is particularly flexible because it doesn’t require retraining when new car models come out; you simply update the reference table with the new dimensions. It’s a compelling step forward for drone-based embodied intelligence, suggesting that future aerial agents won’t just see the world as a flat image, but will navigate and understand it in full 3D.

3. The economics of good design

We all know that walking through a neighbourhood with stunning architecture feels better than walking through a sea of bland concrete, but quantifying that feeling has always been tricky. A new working paper takes a deep dive into the economics of architecture by combining a massive literature review with a new quantitative model. They found that distinctive buildings sell for about a 15 per cent premium compared to ordinary ones, confirming that people are willing to pay for good design. Perhaps more interestingly, they found a significant positive spillover effect where distinctive buildings boost the value of nearby properties by around 9 per cent. The catch is that building something unique is expensive, costing about 25 per cent more than a standard structure. This creates a classic coordination problem where developers under-invest in good design because they bear all the costs but only capture some of the value.

To understand how to fix this, the researchers modelled a neighbourhood where residents have different tastes for architecture. They ran a survey and discovered that people’s preferences for design are quite varied, roughly as diverse as their preferences for where to live within a city. This heterogeneity means that as you build more distinctive buildings, the premium people are willing to pay for them drops because you run out of ‘super-fans’ for that style. The model shows that without intervention, the market provides less distinctive architecture than is socially optimal. It turns out that the best way to solve this isn’t through complex zoning rules but through a direct Pigovian subsidy. Their simulations suggest that subsidising about 10 per cent of the construction costs for distinctive buildings creates the maximum welfare gain, balancing the extra cost against the aesthetic benefits for the community.

The study also throws cold water on some common planning tools. For instance, offering Floor Area Ratio (FAR) bonuses—letting developers build taller if they include good design—often backfires. Unless the city is already severely height-constrained, these bonuses tend to reduce welfare by distorting the housing supply. Similarly, relying on a ‘super-developer’ to build a whole district doesn’t necessarily help because they might restrict the supply of distinctive buildings to keep prices high. Designating small ‘distinctive districts’ (like conservation areas) can work well if they cover a small chunk of the neighbourhood, around 4 per cent, but expanding them too much leads to diminishing returns. The takeaway is that if we want better-looking cities, we should probably just pay for them directly rather than trying to engineer them through complex planning loop-holes.

4. Your location data knows more than you think

In the world of digital mapping, a point of interest (POI) is usually defined by static data: its name, category and coordinates. But as anyone who has ever visited a ‘quiet’ cafe that turned out to be a bustling co-working hub knows, a label doesn’t tell the whole story. To capture this nuance, researchers have introduced ME-POIs, a framework that enriches static POI data with patterns from large-scale human mobility. Instead of just knowing a place is a ‘restaurant’, the model learns its function by analysing visit sequences (whether it’s a quick lunch spot or a long-stay dinner venue).

The system uses a contrastive learning approach to align individual visit patterns with a global representation for each POI. One clever trick they employ is a ‘multi-scale distribution transfer’ mechanism. Since most places don’t get enough visits to generate robust data on their own, the model borrows insights from nearby, popular spots to fill in the gaps for less-frequented locations. This allows it to generate meaningful insights even for the ‘long tail’ of rarely visited businesses that usually get overlooked by data-hungry algorithms.

When tested on tasks like predicting opening hours, price levels and visit intent in Los Angeles and Houston, the mobility-augmented model consistently outperformed text-only baselines. For instance, adding mobility data boosted the accuracy of predicting a venue’s price level by over 75 per cent in some cases. It turns out that how people move through a city—when they arrive, how long they stay, and where they go next—reveals as much about a place’s identity as its official description does.

Geospatial Datasets

1. Global building dataset

GlobalBuildingAtlas presents the first open, globally complete dataset comprising building polygons, heights, and Level of Detail 1 (LoD1) 3D models. You can access the data here and the code here.

2. Semantic vehicle trajectory dataset

Captured via Unmanned Aerial Vehicles (UAVs) over the busy Guangzhou Bridge, the High-Density Semantic Vehicle Trajectory (HDSVT) dataset fills a gap in autonomous driving resources by providing long-duration tracking in high-density scenarios. You can access the data here.

3. Transport systems database

The African Transport Systems Database (AfTS-Db) stands as the first comprehensive, geolocated multi-modal transport database for the entire African continent. You can access the dataset here and the code here.

4. Global leaf chlorophyll content dataset

The MuSyQ Global LCC product revolutionises ecosystem monitoring by leveraging Sentinel-2 imagery to map leaf chlorophyll content at an impressive 10-m resolution. You can access the data here and the code here.

Other useful bits

• Europe’s Destination Earth project is taking climate modelling to the next level with a high-resolution ‘digital twin’ of our planet. This AI-powered simulation isn’t just about sharper weather forecasts; it’s already helping to optimise renewable energy and map urban heat, providing a crucial dashboard for understanding Earth’s complex systems.

• In its latest impact report, Planet Labs reveals how its daily Earth imagery is driving real-world change, from helping conservationists protect endangered species to spotting massive methane leaks in Texas.

• Albedo has shared a candid look at its Clarity-1 mission, proving that satellites can indeed thrive in the harsh environment of Very Low Earth Orbit (VLEO). Although the mission ended early due to hardware issues, it successfully validated the platform’s core tech, paving the way for ultra-high-resolution 10 cm imagery in the future.

• Data Center GeoSniffer is a fascinating new tool that merges AI permit scraping with satellite imagery to track critical infrastructure expansion across the US. By providing a ‘neural sniff’ of the grid, it allows users to look past the paper trail and spot physical changes like new substations and generator pads.

Jobs

• Center for International Forestry Research (CIFOR) is looking for a remote Spatial Data Scientist

• International Water Management Institute (IWMI) is looking for a Senior Geospatial Data Engineer based in Colombo, Sri Lanka

• Impact Initiatives is looking for a Senior Assessment officer based in Geneva, Switzerland.

• CERN is looking for a GIS Specialist based in Geneva, Switzerland

Just for Fun

New research reveals that space travel can actually cause an astronaut's brain to shift upwards in the skull, leading to disorientation that lingers long after they return to Earth. Understanding these ‘sensory conflicts’ is now seen as a vital step before we embark on longer missions to the Moon or Mars.

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 was named by the same folks who named GPT-5.4 (Thinking) High. 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:

• Data Centres: New maps show remaining US capacity.

• SAM3 Fixes: CONCEPTBANK improves segmentation under domain drift.

• Spatial AI: Why chatbots still struggle to drive.

• Health Mapping: AI links imagery and demographics.

• WorldPop 2: New global population grids at 100 metres.

Subscribe now

Research you should know about

1. We’re running out of room for data centres

The recent generative AI boom is driving a massive expansion of hyperscale data centres across the United States. While we have plenty of maps showing where these facilities are currently located, a new study takes a different approach by looking at where they can actually still be built. Rather than relying on future demand forecasts or basic zoning laws, the researcher built a constraint-first geospatial framework. This means they focused entirely on the strict physical, environmental and infrastructural limits that dictate where a massive server farm can realistically operate today.

To map this out, this new study divided the country into a uniform hexagonal grid and analysed the precise characteristics of existing hyperscale sites. The models layered in a huge amount of spatial data, including high-voltage power transmission lines, local substations, summer temperature peaks, flood risks and built-up land density. By using unsupervised machine learning approaches to compare these data layers against the environments of current facilities, the analysis identified remaining regions that share the specific structural DNA needed to support new development.

The findings suggest that the US is facing a pretty tight ceiling when it comes to future hosting capacity. Both models converged on a surprisingly limited envelope of feasible land, estimating that the total physically viable capacity left is somewhere in the tens of gigawatts (roughly 25 to 100 GW), rather than the hundreds of gigawatts that some optimistic industry forecasts assume. Ultimately, this shows that the tech industry is running out of easy real estate. Exceeding this physical limit will require a fundamental overhaul of the underlying electricity system and local regulatory landscapes.

2. Taming foundation models for the real world

The recently released SAM3 model has been pretty massive for text-to-segmentation. As with the other SAMs, it allows users to segment almost anything just by typing a text prompt. However, when you take it out of its comfortable pre-training environment and deploy it in the wild, things start to break down. The main culprits are data drift and concept drift. Data drift happens when the actual visual statistics shift, which is a pretty big issue in remote sensing where aerial viewpoints and spectral signatures look nothing like standard photos. Concept drift occurs when the meaning of a label changes depending on the context (like how the word “mouse” means an animal in a nature dataset but a clicking-device-thingy in an office dataset). When these shifts happen, the model’s static text prompts no longer align with the visual evidence, leading to missed objects and incorrect masks.

To fix this without the massive computational headache of retraining the whole model, researchers have proposed a parameter-free framework called CONCEPTBANK. Instead of relying on static text prompts, this system builds a dataset-specific dictionary derived directly from the target domain’s actual statistics. It works through a clever three-stage pipeline. First, it anchors target evidence by finding visual prototypes for each class. Second, it filters out noisy outliers to ensure it is only looking at representative examples. Finally, it uses a large language model to generate a variety of synonyms and attribute descriptions, fusing the best ones together to create a calibrated text anchor that perfectly matches the target dataset. It does all of this on the fly without updating a single weight in the SAM3 backbone.

The results are quite compelling, especially for those of us working with geospatial data (which I’m guessing is you). When tested across four different remote sensing benchmarks, CONCEPTBANK boosted SAM3’s average performance by 13 percentage points compared to the vanilla version. Datasets like LoveDA and iSAID, which usually trip up standard models due to their complex aerial perspectives, saw huge improvements. It also performed exceptionally well on standard natural scene datasets. Because the system bypasses the text encoder during actual inference and just retrieves the pre-calibrated anchors, it actually speeds up the processing time by 25 per cent. Ultimately, this approach provides a highly robust, plug-and-play way to optimise massive foundation models for messy, real-world satellite imagery.

3. Why chatbots make terrible drivers

LLMs are great. And I’m sure many of you are like me - our best friends are an LLM, like my OpenClaw Billy. But LLMs have historically failed when navigating the physical world. A model that can perfectly describe a photo of a kitchen cannot necessarily figure out how to move through it or pick up a mug. This happens because these models lack ‘spatial grounding’, which is the metric understanding of geometry and physics required to turn perception into action. To solve this disconnect, a team of researchers reviewed over 2,000 papers to create a massive new taxonomy that connects standard AI agent capabilities with spatial intelligence.

Their framework divides the landscape into three axes: the specific spatial task, the agent’s cognitive capabilities, and the physical scale. When mapping existing research onto this grid, they discovered a pretty big imbalance. Roughly 68 per cent of current methods focus on ‘meso-spatial’ tasks like room-scale navigation, leaving micro-scale robotic manipulation and macro-scale geospatial analysis completely underexplored. To bridge these gaps, the authors highlight some promising architectural patterns, specifically integrating Graph Neural Networks with language models. This helps agents maintain a structured, persistent understanding of spatial relationships over time rather than relying on text alone.

Another major takeaway is the absolute necessity of ‘world models’ for safe physical deployment. Since physical mistakes can cause irreversible damage, agents need these internal simulators to predict the consequences of their actions before actually making a move. Looking ahead, the researchers pinpoint several grand challenges that stand in the way of truly autonomous spatial systems. The most glaring issue is the lack of unified cross-scale representation, meaning an AI struggles to seamlessly transition from planning a city-wide route down to the centimetre-level precision needed to open a door. Solving these structural barriers will be essential for the next generation of robotics and autonomous vehicles.

4. Mapping public health from space

Predicting public health outcomes usually requires massive amounts of census and medical data. Satellite imagery can show us the physical environment, like green spaces or industrial zones, but it misses crucial demographic context. To bridge this gap, researchers have developed a new AI model called the Geo-Context Guided Visual Transformer (GCGVT). Instead of just merging data blindly, it uses a ‘Guided Attention’ mechanism. This allows the model to look at an aerial view of a neighbourhood while being explicitly guided by specific socioeconomic factors, pointing the AI to the most relevant physical features.

The team tested their model on predicting the prevalence of nine chronic diseases, including diabetes, obesity and depression, across 14,330 historical redlining zones in the US. They fed the AI aerial photos alongside 228 variables from the American Community Survey, covering details like age, income and race. The new model achieved an impressive average predictive score of 0.85, completely outperforming standard vision-language models like CLIP. Interestingly, the researchers found that they did not need all 228 variables. By combining the aerial imagery with just two demographic categories, such as Income and Race for predicting obesity, or Age and Housing for arthritis, the model still delivered highly accurate forecasts.

The real breakthrough here is the transparency of the system. Most deep learning models operate as a black box, making them hard to trust in healthcare settings. However, this framework assigns different AI attention heads to specific demographic categories, allowing users to see exactly how the model connects the dots. For instance, when predicting depression rates, the model visually highlighted how employment data correlated to specific housing blocks, and how education levels mapped onto nearby natural areas. This gives public health officials a highly interpretable tool to map out health disparities without relying on exhaustive, expensive on-the-ground surveys.

Geospatial Datasets

1. WorldPop Global 2 dataset

The newly released WorldPop Global 2 dataset provides highly detailed, annual geospatial population estimates at a 100-metre resolution for over 240 countries and territories, spanning the years 2015 to 2030. Built using recent census information and satellite-derived settlement modelling, this open-access resource also provides age and sex breakdowns. You can access the data here.

2. Long-term night-time light dataset

The Extended VIIRS-like Artificial Nighttime Light (EVAL) dataset provides a continuous, high-quality annual record of night-time illumination across China from 1986 to 2024. Using a two-stage deep learning framework, this 500-metre resolution map resolves common issues found in older satellite records, such as the underestimation of brilliant city centres and the blurring of intricate road networks. You can access the data here and the code here.

3. Impervious surface cover dataset

The China Impervious Surface Cover (CISC) dataset provides a 30-metre resolution map of artificial surfaces across mainland China for 2020 and 2022. It fuses together high-resolution 2-metre imagery from the Gaofen satellite series with 30-metre Landsat and SRTM data via a regionally adaptive deep learning model. You can access the data here and the code here.

4. Bioavailable strontium isotope data

If, unlike me, you’ve heard of bioavailable strontium isotopes, then you’re in luck. This compilation harmonises over 28,000 bioavailable strontium isotope (87Sr/86Sr) data points from more than 150 countries into one easily accessible resource. It draws from decades of research across soil, water, flora, and fauna samples. You can access the data here and here, and the code here.

Other useful bits

• The European Space Agency has just launched the EOPF Sentinel Zarr Explorer, a new platform that shifts massive Earth observation datasets into a new (and different) cloud-native format. This means we can now discover, visualise, and analyse satellite imagery directly in their web browsers without the headache of downloading colossal files.

• Researchers have just released PyGALAX, a new open-source Python toolkit designed to take the headache out of complex geospatial machine learning. By combining automated modelling with explainable AI, it gives users a much clearer picture of the 'why' behind spatial patterns, making it a fantastic resource for everything from urban planning to environmental monitoring.

• A new tool called the Interpretable Code-based assistant for Earth Observation (IC-EO) is making satellite data analysis accessible by translating simple, natural language questions directly into Python code. Developed by researchers alongside the European Space Agency, it allows even non-experts to tackle complex tasks like wildfire assessments and land-use mapping with impressive accuracy and transparency.

• Google Earth is tackling the headache of city gridlock by letting urban planners import their own custom traffic data directly onto the globe. By mixing this with built-in layers like vehicle trip counts and signal performance, it provides a new way of pinpointing bottlenecks.

Jobs

• Mapbox is looking for a Technical Support Engineer based in China

• UNEP - United Nations Environment Programme is looking for a Spatial Data Application Developer based in Nairobi, Kenya

• International Water Management Institute (IWMI) is looking for a Senior Geospatial Data Engineer based in Colombo, Sri Lanka

Just for Fun

This map outlines the European Union's envisaged transport and trade corridors across Africa.

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 more riveting than a Bad Bunny halftime performance. As usual, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Spatial Mapping: ANPs improve biomass uncertainty estimates.

• Image Sharpening: Synthetic data enhances hyperspectral resolution.

• Landslide Detection: Deep learning improves hazard monitoring.

• Malaria Threat: Climate change disrupts disease eradication.

• Building Heights: New deep learning estimation dataset.

Subscribe now

Research you should know about

1. Knowing when to doubt the data

A lot of folks use standard machine learning models like Random Forest or XGBoost to map environmental variables like aboveground biomass. These models are fantastic at making point predictions, but a new paper highlights that they are systematically overconfident when estimating uncertainty. When you use these standard baseline configurations, you end up with uncertainty estimates that fail to capture local spatial variability. For instance, if you’re mapping a landscape with sharp transitions between forests and cleared fields, traditional models generate the exact same narrow uncertainty interval they would anywhere else. They completely miss the local context. This basically means development organisations and carbon market verifiers could be making big conservation decisions using highly inaccurate confidence levels.

The researchers present Attentive Neural Processes (ANPs) as a much smarter alternative for spatial mapping. ANPs use an episodic training structure to learn spatial patterns directly, improving upon older methods that treat every observation in isolation. The model takes a sample area, splits the data, and learns to predict targets conditioned on the surrounding context. If the nearby data points are tightly clustered, the model assigns low uncertainty. If the context points are scattered and highly variable, it naturally expands its prediction intervals. The model essentially meta-learns how to adapt to local landscape heterogeneity on the fly.

The results show a massive difference between the two approaches. Across diverse forest types, the ANP consistently achieved well-calibrated uncertainty scores, whereas the traditional models fell way below expected coverage targets. When the models had to transfer their predictions to entirely new geographic regions, XGBoost coverage dropped to around 15 per cent because it simply could not adapt to the distributional shift. The ANP maintained strong coverage even as overall accuracy dipped. It is a pretty big reminder that having a model that knows when it is unsure is just as crucial as having one that makes accurate predictions.

2. Sharpening images with ‘dead leaves’

Hyperspectral imaging is awesome for identifying materials from space, but it usually suffers from a trade-off where you get rich spectral detail but poor spatial resolution. Deep learning can normally sharpen these images, but there’s a catch. There’s always a catch… These models typically need high-resolution ‘ground truth’ data to learn from, which simply doesn’t exist for most real-world scenarios. To get around this, researchers from Télécom Paris have come up with a clever unsupervised approach that relies on fully synthetic training data generated by something called the ‘dead leaves model.’

The main idea is to break the hyperspectral image down into ‘abundances’ (maps showing where specific materials are) and ‘endmembers’ (the spectral signature of those materials). The team then trains a super-resolution neural network solely on synthetic abundance maps created by simulating dead leaves falling on a canvas. While this sounds abstract, these random, overlapping shapes create statistical properties like edges and flat regions that mimic real-world abundance maps surprisingly well. This allows the network to learn how to sharpen features without ever seeing a real high-resolution image during training.

When tested on the standard ‘Urban’ dataset, this method didn’t just work; it actually outperformed state-of-the-art supervised methods like MCnet and HSISR. This is a pretty big deal because the competitors were trained on data with ground truth, while this model learned entirely from synthetic shapes. It demonstrates that we don’t always need expensive or impossible-to-acquire real-world datasets to train effective AI models. By using the dead leaves model to simulate texture and structure, the researchers provided a robust proof of concept for sharpening hyperspectral imagery in a completely unsupervised way.

3. Teaching AI to spot landslides

Landslides pose a massive threat to infrastructure in geologically unstable regions, yet our traditional methods for monitoring them (like ground surveys and visual inspections) are often too slow to be effective. To address this gap, a new paper in Scientific Reports looks into a new deep learning approach that employs enhanced Deep Convolutional Neural Networks (DCNNs) to detect landslides with high precision.

The researchers introduced several key modifications to make the system smarter. They integrated a spatial attention mechanism and attention-based Global Average Pooling, which essentially help the AI focus on the most critical parts of an image rather than getting distracted by irrelevant background noise. To further refine the training process, they utilised the Lookahead Adam optimizer and optimised learning rate schedules. These technical tweaks were designed to improve how the model extracts features and converges on a solution, ensuring it can generalise well across different types of terrain.

The performance metrics for this new approach are pretty impressive. In experiments using the Kaggle Landslide Dataset, the model achieved a testing accuracy of 95.8 per cent, with similar success observed when testing against the NASA Landslide Inventory. This level of accuracy suggests that attention-driven DCNNs could significantly outperform conventional assessment methods. By offering a reliable and efficient tool for automated monitoring, this technology could be crucial for early detection systems that help mitigate risks to communities living in danger zones. You can access the code here.

4. Climate chaos threatens malaria eradication

After decades of progress, the global fight against malaria has stalled, and climate change is emerging as a massive new hurdle. A new study in Nature has quantified this threat by looking at both the direct ecological impacts of a warmer world (like mosquito breeding rates) and the indirect, ‘disruptive’ impacts of extreme weather. By integrating 25 years of data on climate, disease burden and socioeconomic factors, the researchers project that climate change could lead to an additional 123 million malaria cases and 532,000 deaths in Africa between 2024 and 2050.

Interestingly, the study finds that it isn’t just about mosquitoes enjoying warmer weather. In fact, 79 per cent of the additional cases and 93 per cent of the extra deaths will likely be driven by extreme weather events like floods and cyclones. These disasters destroy housing, cut off access to healthcare and disrupt vector control programs, creating perfect conditions for outbreaks in areas that are already struggling. The research shows that while some regions might actually see a decrease in transmission due to excessive heat, this is far outweighed by the intensification of malaria in existing endemic zones, particularly in densely populated countries like Nigeria and Uganda.

This analysis challenges the traditional focus on ‘range expansion’, showing that 99 per cent of the additional burden will hit communities that already suffer from malaria, rather than spreading to new areas. The compounding effect of ecological changes and infrastructure disruption creates a ‘double whammy’ for vulnerable populations. To safeguard the goal of eradication, the authors argue we need to move beyond standard control measures and invest heavily in climate-resilient health systems, ensuring that clinics, supply chains and mosquito control efforts can withstand the increasingly volatile weather of the coming decades. You can access the code here.

Geospatial Datasets

1. Building height estimation dataset

M4Heights is a new benchmark dataset designed to advance building height estimation through deep learning, covering vast landscapes across Estonia, the Netherlands, and Switzerland. You can access the data here and the code here.

2. Carbon, water, and energy fluxes dataset

The Unified FLUXes (UFLUX) ensemble provides a globally consistent dataset of carbon, water, and energy fluxes, derived from a robust combination of eddy covariance data, satellite observations, and machine learning. You can check out the list of datasets here and the code here.

3. Automated crop monitoring dataset

This comprehensive dataset addresses the critical need for automation in crop monitoring by providing high-quality, diverse data for six crop species (sugar beet, spring wheat, sweet corn, soybean, potato, and wheat-faba bean intercrop). You can access the data here and the code here.

4. Root zone soil moisture dataset

TAMSAT-SM provides a reliable, long-term dataset of root zone soil moisture across Africa, designed to support operational agricultural drought monitoring. Spanning from 1983 to the present at a 0.25° spatial resolution, it uses the JULES land surface model forced with TAMSAT rainfall and NCEP reanalysis data, tuned to satellite observations. You can access the data here and the code here (registration required).

Other useful bits

• A new Earth Engine tutorial shows how to replicate this pretty awesome GOES GeoColor visualisation using Python. By blending daytime imagery with night-time city lights and infrared cloud data, this guide helps users create seamless animations that beautifully capture the transition from day to night across the winter solstice.

• Planet is helping to illuminate the world's ‘dark fleets’ with their new Maritime Domain Awareness solution. By combining daily satellite imagery with AI detection, this tool tracks ships even when they switch off their AIS signals.

• Google Earth is testing a new experimental feature that lets users bring their own KML, KMZ, and GeoJSON files directly onto the globe. This update makes it easier than ever to securely layer custom data over Google’s satellite imagery, helping users make smarter decisions, faster.

• A new tool called GeoSpy AI is turning heads with its ability to pinpoint the exact location of a social media photo in just two seconds. It’s pretty freaky… It maps the results in full 3D, offering a powerful (if slightly unnerving) demonstration of just how much information can be gleaned from a single image.

Jobs

• Development Seed is looking for a remote Technical Project Lead

• FAO - Food and Agriculture Organization of the United Nations is looking for a Geospatial Data Scientist based in Rome, Italy

• WHO - World Health Organization is looking for a remote Epidemic Intelligence and GIS Analyst: https://unjobs.org/vacancies/1772554525336

• WFP - World Food Programme is looking for a remote Earth Observation Analyst

Just for Fun

A stunning detailed map of the world’s 1,180 micro-tectonic plates.

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

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

In today’s newsletter:

• US Migration: New granular data reveals neighborhood-level movement trends.

• 3D Cities: Deep learning creates urban models from radar.

• Solar Forecasting: Explainable AI improves renewable energy yield predictions.

• Agricultural AI: Google’s AlphaEarth model tested against traditional metrics.

• Renewable Scenarios: New dataset closes gaps in distributed energy studies.

Subscribe now

Research you should know about

1. A new high-resolution lens on US migration

US migration data has essentially been stuck in a ‘pick one’ scenario: reliable but clunky Census data that only goes down to the county level, or high-resolution proprietary data that is full of biases. To fix this, researchers have developed MIGRATE, a new dataset that fuses commercial address histories from Infutor with the reliability of Census constraints. By harmonising these sources, they created annual migration matrices between 47.4 billion pairs of Census Block Groups. That’s roughly 4,600 times more granular than the standard county-to-county data we’re used to seeing, effectively letting us zoom in from a satellite view right down to the neighbourhood level.

The team spent a lot of time cleaning up the messy commercial data, which tended to overcount wealthy and rural populations while missing others. Once corrected, the national trends revealed a stark picture of ‘homophily’, where people overwhelmingly move to areas demographically similar to where they left. The data shows that movers from plurality Black, Asian and Hispanic neighbourhoods are 5.5, 14.6 and 4.3 times more likely, respectively, to move to areas with the same plurality race group. Upward mobility is also uneven; while people generally aim for higher-income neighbourhoods, there is a clear racial gap. Even when starting from the same income level, movers from plurality Asian areas are more likely to upgrade to a wealthier block, whereas movers from plurality Black areas are less likely to do so.

This granular view proves its worth when looking at localised shocks like the California wildfires. Public county-level data completely missed the migration impact of the 2017 Tubbs and 2018 Camp fires because the displacement happened within county lines or was washed out by broader averages. In contrast, MIGRATE picked up a massive signal, showing that out-migration rates in the distinct burn zones spiked to over 37% and 46% respectively in the year following the fires. It turns out that a huge chunk of these displaced people didn’t leave the county, but just moved to a safer block nearby, a dynamic that remains invisible unless you have this kind of street-level resolution.

MIGRATE is available upon request here. You can also find the code here.

2. Building 3D cities from messy radar data

Getting accurate 3D models of cities is usually a bit of a headache involving expensive LiDAR flights or waiting for cloud-free satellite imagery. Synthetic Aperture Radar (SAR) offers an interesting alternative since it works day and night in any weather, and a technique called TomoSAR can even reconstruct 3D point clouds from space. The problem is that these point clouds are often pretty messy. They suffer from noise and gaps that make it tough to extract clean building heights. To fix this, researchers from the Technical University of Munich have developed a new deep learning framework that turns these raw, rough radar points into high-res height maps.

The main part of their approach is a ‘dual-topology’ network that toggles between two different ways of looking at the data. One branch processes the irregular 3D points to capture structural details, while a second branch projects everything onto a 2D grid to enforce spatial consistency. By constantly exchanging information between these two views, the model effectively learns to denoise the data and fill in the missing blanks where the radar signal didn’t bounce back. This allows it to generate continuous height estimates even from sparse inputs, without needing an external terrain model to tell it where the ground is.

The team tested this on TerraSAR-X data over Berlin and Munich, representing both high-quality and lower-quality datasets. The results showed a massive improvement over standard interpolation methods, successfully reconstructing building shapes that were previously lost in the noise. They also demonstrated that the framework is flexible enough to ingest standard optical satellite imagery alongside the radar data, which further sharpens the results. This is a pretty big step forward as it serves as a proof of concept for generating large-scale, weather-independent urban height maps directly from space.

You can access the code here.

3. Solar energy forecasting gets a transparent upgrade

Solar energy is great, but it can be a bit fickle. For example, clouds and local climate shifts can sometimes make it hard to integrate into the grid reliably. Instead of installing expensive sensors everywhere, researchers are turning to machine learning to predict solar irradiance based on weather data. A new study from Scientific Reports compared six different regression models to see which could best handle the job using data on temperature, humidity, wind and pressure.

The clear winner in their tests was the Random Forest Regressor, which edged out competitors like Gradient Boosting and Linear Regression with a regression score of roughly 0.90. But the researchers didn’t just want a number; they wanted to know why the model worked. To peek inside the ‘black box’ of the AI, they employed Explainable AI (XAI) techniques known as LIME and SHAP. These tools help interpret complex algorithms, breaking down exactly how much weight the model assigns to different variables when making a prediction.

The XAI analysis revealed that temperature is the biggest factor, showing the strongest positive correlation with solar radiation. In contrast, humidity and wind speed tended to have a negative impact. This insight is valuable because it allows engineers to forecast potential energy yields for new solar farm locations using readily available geospatial data, rather than deploying costly hardware first. By making these AI decisions transparent, grid operators can trust the forecasts more, leading to better stability and smarter investment decisions in renewable infrastructure.

You can access the data here.

4. Google’s giant AI model meets the farm

As I’ve previously covered on here, last year Google DeepMind released AlphaEarth Foundation (AEF), a massive model pre-trained on billions of images that harmonises optical, radar and climate data into ready-to-use ‘embeddings’. A new paper puts AEF to the test on specific agricultural tasks in the US, such as predicting crop yields and mapping tillage practices, to see if these pre-cooked features can actually beat traditional, hands-on remote sensing methods.

The results were pretty encouraging at a local level. When trained and tested in the same region, models built on AEF embeddings performed just as well as those built on carefully engineered remote sensing features. For tasks like estimating corn and soybean yields, the AI approach was competitive and offered a huge convenience advantage. Since AEF automatically handles data harmonization and fills in gaps caused by clouds, researchers didn’t have to spend weeks cleaning data to get a usable input.

However, the study uncovered some serious limitations when the models were pushed further. AEF struggled quite a bit with ‘spatial transferability’, which means a model trained in the eastern Corn Belt failed completely when tested in the west. Traditional satellite metrics handled this shift much better because they are based on consistent physical properties of plants. Additionally, AEF is a ‘black box’, so users have no idea what a feature like ‘A05’ actually represents physically, unlike an index like NDVI which directly measures vegetation vigour. This lack of interpretability suggests that while foundation models are powerful, we can’t quite ditch our physics-based indices just yet.

Geospatial Datasets

1. Distributed renewable energy scenarios dataset

The DDRE-33 dataset addresses the scarcity of public data for distributed renewable energy (DRE) studies within the standard IEEE-33 distribution network. This provide spatiotemporally correlated scenarios for both distributed wind and photovoltaic generation without the data gaps found in earlier collections. You can access the data here and the code here.

2. Riverine levee overtopping events dataset

The Levee Loading and Incident Dataset - Overtopping (LLID-OT) version 1.0 provides data on 487 riverine levee overtopping events across the US from the past 15 years. You can access the data here.

3. Electric distribution networks dataset

This harmonized geospatial dataset provides data on electric distribution networks across the US Northeast, covering seven states from Connecticut to Vermont. It features over 3.8 million line segments. You can access the data here and the code here.

4. LiDAR benchmark for railway corridors

SemanticRail3D and its enhanced V2 iteration provide a comprehensive mobile LiDAR benchmark designed specifically for railway infrastructure monitoring. It features 2 semantic classes, including rails, catenary systems, and masts and is comprised of approximately 2.8 billion points across 438 high-resolution segments. You can access SemanticRail3D here andSemanticRail3D-V2 here. You can access the code here.

Other useful bits

• Google DeepMind is powering a new agricultural layer in Google Earth that uses machine learning to map individual field boundaries across the Asia-Pacific region. This essentially allows users to pinpoint water resources and calculate acreage with precision, offering vital data for drought contingency planning.

• Researchers have introduced Embedded Seamless Data (ESD), an ultra-lightweight database that compresses twenty-five years of global 30-metre imagery into a surprisingly manageable size. With a massive 340x compression ratio, it allows the entire global land surface for a single year to fit on a standard workstation, democratising planetary-scale analysis. Check out the demo and the manuscript.

• Google has launched a handy new endpoint for its Weather API, giving developers a single, reliable source for global weather alerts. By unifying data from government agencies worldwide, it takes the hassle out of aggregating warnings and automatically surfaces local alerts based on simple coordinates.
  

Jobs

• FAO - Food and Agriculture Organization of the United Nations is looking for a Junior Agricultural Specialist based in Rome, Italy

• UNEP - United Nations Environment Programme is looking for a Information Management Assistant based in Nairobi, Kenya

• Zipline is looking for a Senior Analyst based in South San Francisco, USA

• FAO - Food and Agriculture Organization of the United Nations is looking for a remote Data Analyst

• OICT - Office of Information and Communications Technology is looking for a Chief of Service, Information Systems and Telecommunications based in New York, USA

Just for Fun

Those spectacular auroras seen in mid-January might have been a treat for stargazers, but they served as a stark warning for the upcoming Artemis II mission. With the launch just weeks away, the European Space Agency is using data from these severe solar storms to ensure the crew’s journey to the Moon remains safe from dangerous radiation.

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 weekly round-up of geospatial news. We’re a bit like Tensorflow. Some people still think we’re kinda cool, but nobody else is interested. In any case, the aim is to make you a better geospatial data scientist in less than 5 minutes a week.

In today’s newsletter:

• Urban Road Access: New metrics map road deprivation in Africa.

• AI Flood Mapping: Fine-tuned models improve disaster detection accuracy.

• Wildfire Forecasting: Global graph networks predict fires months ahead.

• Soil Health Sensing: Satellite data estimates carbon and nitrogen levels.

• Renewable Energy Data: Hourly climate projections for future power planning.

Subscribe now

Research you should know about

1. It’s not the distance to the road. It’s the dirt.

Access to motorable roads is a massive issue in rapidly urbanising regions like Sub-Saharan Africa, where informal settlements often get left off the map. A new study tries to address this by proposing a new way of modelling ‘road access deprivation’ in Nairobi, Lagos and Kano. Instead of just measuring distance, they combined two clever metrics. First, they developed a distance-agnostic accessibility measure that counts how many buildings obstruct the path between a structure and the nearest road. Second, they integrated data on road surface type to distinguish between paved and unpaved infrastructure. This allowed them to classify areas into low, medium and high deprivation levels based on whether residents have direct access to a paved road, a dirt track or are physically cut off from the network.

When they ran this model across the three cities using open geospatial data, the results showed that highly deprived areas are actually less common than you might expect. The majority of built-up zones fell into the low or medium deprivation categories, meaning most buildings do have direct access to some form of motorable road. However, the extent of severe disconnection varies quite a bit between locations. For instance, high deprivation areas made up only 11.8 per cent of Nairobi but climbed to 27.7 per cent in Kano. This suggests that while total physical isolation is a specific problem, a large chunk of the urban population is dealing with the ‘medium’ deprivation of having direct access but only to poor-quality, unpaved surfaces.

To see if these maps reflected reality, the team validated their model against data crowdsourced from local communities. The system proved highly effective at identifying well-connected, low-deprivation areas, achieving strong accuracy scores in Nairobi and Lagos. It struggled a bit more with the ‘medium’ category, often confusing it with low deprivation. This usually happened because the underlying data might misclassify a road’s surface type or because community members perceive access differently than the rigid definitions of the model. Despite these hiccups, the study shows that combining building obstruction metrics with road quality data is a promising, scalable way to identify disconnected neighbourhoods and help city planners prioritise upgrades in data-scarce environments.

2. Improving flood maps with heavy-duty AI

Flooding is causing havoc worldwide, with 2024 seeing devastating events from Valencia to Vietnam. While we have massive archives of Earth observation data, using it effectively is tough because standard AI models need huge amounts of labelled data. To tackle this, researchers took an existing Geospatial Foundation Model (GFM) called TerraMind and fine-tuned it specifically for flood detection. They used a new dataset called FloodsNet, which combines both Sentinel-1 radar and Sentinel-2 optical imagery for 85 global flood events. The goal was to see if retraining this pre-existing ‘brain’ with a rich, multimodal dataset could handle the messiness of flood data better than current methods.

The study ran experiments on four different versions of the model, tweaking the size and whether the core ‘backbone’ was frozen or allowed to update. They found that the ‘base unfrozen’ configuration offered the best balance, delivering strong accuracy without the heavy computational price tag of the larger models. While the massive 326-million-parameter version achieved the best recall among the GFM options, it didn’t offer enough of an overall performance boost to justify the extra cost. It seems that for practical flood mapping, a mid-sized model that can adapt its internal weights is the most efficient choice.

Things got interesting when they compared these GFMs against a standard U-Net, a conventional deep learning model that has been around for years. Surprisingly, the U-Net achieved better recall than every single TerraMind configuration, meaning it missed fewer flooded pixels overall. While the Foundation Models produced smoother and more coherent maps, the U-Net was often sharper at picking up fine details. This suggests that while multimodal GFMs are promising for unlocking vast data archives, traditional supervised models are still holding their ground when it comes to catching every last bit of water during a disaster.

3. Predicting wildfires with Earth-as-a-graph

Climate change is turning wildfire forecasting into a global priority. Traditional models often struggle to capture the complex, non-linear interactions between weather, vegetation, and human activity that drive fires over long periods. To address this, a team of researchers has developed FireCastNet, a new deep learning model that treats the Earth system as a giant interconnected graph. By combining 3D convolutional encoding with a Graph Neural Network (GNN) based on the GraphCast weather model, FireCastNet learns from both local fire dynamics and distant climate ‘teleconnections’, like how ocean temperatures in the Pacific might influence fire risk in Africa months later.

Trained on the comprehensive SeasFire datacube, which includes climate, vegetation, and human variables from 2001 to 2021, the model predicts burned area patterns up to six months in advance. When benchmarked against other state-of-the-art AI models, FireCastNet came out on top, particularly in fire-prone regions like Africa, South America, and Southeast Asia. The study found that giving the model longer time-series data significantly boosted its ability to make robust long-term predictions, confirming that fires are often the result of slowly accumulating conditions like drought and fuel buildup.

Interestingly, while a single global model performed well, the researchers also tested a ‘Local Area Modeling’ approach. This involved training specific models for different biomes, refining the graph’s mesh to be ultra-high resolution over a target region while keeping the rest of the globe coarser to capture those important long-range links. This local tuning improved accuracy in places like Europe and the Middle East but surprisingly didn’t help everywhere. In regions like Southeast Asia and Australia, the global model still reigned supreme, suggesting that for some parts of the world, those broad, planetary-scale connections are just as critical as local details.

4. Measuring soil from the sky

Precision agriculture relies heavily on accurate soil data, but traditional physical sampling is slow, expensive, and logistically difficult. A team from CO2 Angels and the European Space Agency has developed a scalable system to estimate soil properties like organic carbon and nitrogen directly from satellite data. They used a hybrid modelling approach that combines direct spectral observations with environmental drivers such as climate, terrain, and vegetation traits. By integrating physics-informed machine learning with foundation model embeddings, the system can infer underground soil health conditions even when the surface is covered by crops.

The researchers trained their model on a massive harmonised dataset of European croplands, incorporating data from Sentinel-2, Landsat, and MODIS. They applied a rigorous validation method known as spatial blocking, where test samples were separated from training data by blocks of approximately 100 kilometres. This strict separation ensures the model isn’t just memorising local geographic patterns but is genuinely learning to predict soil properties from environmental signals.

The performance varied significantly depending on the nutrient being analysed. The model proved highly effective for Soil Organic Carbon and Nitrogen, achieving a Concordance Correlation Coefficient of 0.77 for both, with a Mean Absolute Error of 5.12 g/kg for carbon and 0.44 g/kg for nitrogen. However, it found Phosphorus and Potassium much harder to pin down, with correlation coefficients dropping to 0.53 and 0.58 respectively. The system also successfully quantified its own uncertainty, achieving 90% coverage for its prediction intervals, which suggests it is a viable tool for carbon markets and broad-scale monitoring even if it isn’t quite ready for precise phosphorus management.

Geospatial Datasets

1. Climate projections and renewable energy generation dataset

This dataset addresses the critical need for high-resolution energy modelling by providing hourly climate projections and renewable energy generation data for mainland China. Spanning from 2021 to 2060, it uses analog-based temporal downscaling to refine daily Global Climate Model outputs into the hourly resolution required for accurate power system planning. You can access the data from the Zenodo projects cited (reference no. 41 to 60) and the code here.

2. Flood hazard mapping framework

This study presents a hybrid framework for flood hazard assessment in the Swat River Basin. It blends machine learning with coupled hydrologic–hydraulic modelling.

3. Soil Moisture Climatological Record

The SMCR provides the first global, satellite-derived soil moisture record that spans from 1980 to 2023 at a daily, 1 km resolution.

Access the dataset:

• 1980–1985

• 1986–1991

• 1992–1997

• 1998–2023

Access the code here.

4. Railway network dataset

The Italian Railway Network Dataset offers a comprehensive look at multi-type train operations across Italy, spanning from January to June 2024. It covers over 3,300 trains and nearly 1,400 stations. You can access the dataset here and the processing code here.

Other useful bits

• By analysing how ice flows over the bedrock, researchers have produced the most detailed map yet of Antarctica’s hidden ‘underbelly’, revealing thousands of previously unknown hills and valleys. This is a crucial leap for climate science, as knowing the shape of this buried landscape is essential for predicting exactly how the ice sheet will react to a warming world.

• Vantor has slashed satellite imagery delivery times from 90 minutes down to just 11. By processing data right at the edge rather than in central queues, their new approach ensures vital intelligence reaches the people who need it faster than ever before.

• ESRI founder Jack Dangermond envisions a ‘planetary nervous system’ where digital twins act as living, evolving entities rather than static snapshots. He argues that the industry’s next great leap depends less on new software and more on a cultural shift towards sharing data to solve global challenges.

• FAO’s Hand-in-Hand Initiative has released a new ‘suite’ of geospatial datasets aimed at transforming agriculture and rural development across more than 80 countries. By using advanced analytics to pinpoint high-impact investment opportunities, this project provides a vital roadmap for fighting global hunger through smarter, data-driven planning.

Jobs

• The World Bank is looking for a Senior Technical Lead for Geospatial Solutions based in Bulgaria.

• Genex Systems is looking for a GIS Analyst based in Mountain View.

• ESA is looking for a Graduate Trainee in Earth Observation Foundation Modelling based in Frascati.

• The Lincoln Institute of Land Policy is looking for a remote Geospatial Backend Software Developer based in the US.

• ETH Swiss GeoLab is looking for an Office Manager based in Zurich (and eventually, Lucerne).

Just for Fun

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

Hey guys, here’s this week’s edition of the Spatial Edge — a place where you can say things like ‘cloud native’ and people nod with agreement. The aim is to make you a better geospatial data scientist in just 5 minutes a week.

In today’s newsletter:

• Urban Access: Data maps the 15-minute city reality.

• Heat Resilience: Better health masks rising climate risks.

• Cloud Mapping: Ground cameras fix weather model blind spots.

• Ecosystem Resilience: ENSO weakens our greening world.

• Satellite Imaging: Sentinel-2A captures Earth in night mode.

Subscribe now

Research you should know about

1. Mapping the reality of the 15-minute city

The concept of the ‘15-minute city’ has become a bit of a buzzword in urban planning, yet we’ve had surprisingly little data on how many people actually live in one on a global scale. A new study published in Nature Communications tackles this data gap by mapping global accessibility to six essential categories, including healthcare, education and public transit. By combining Overture Maps POI data with high-resolution land cover and elevation models, the researchers created a ‘friction surface’ map. This basically measures the time it takes to travel across different types of terrain to reach these services.

To pull this off, the team integrated nearly 66 million points of interest from Overture Maps and Amap (for China) with population density data. They calculated travel times using a least-cost-path algorithm, which figures out the quickest route based on terrain and road networks. The results show that roughly 62.8% of the world’s urban population currently lives within a 15-minute walk of essential amenities. If you extend that radius to a 30-minute walk, the coverage jumps to 82.5%. While these numbers might sound high, they hide some pretty stark inequalities when you break the data down by region and income level.

The data reveals a significant divide between the Global North and South. Residents in high-income nations enjoy an average travel time of 15.5 minutes to essentials, whereas those in the Global South face an average trek of 30.8 minutes. The disparity in infrastructure density is even wider, with high-income countries having nearly nine times the number of amenities per capita compared to low-income nations. This confirms that wealth heavily dictates resource allocation, and it highlights just how much work remains to achieve the UN’s Sustainable Development Goals regarding equitable access to basic services.

2. Better health is hiding the impact of heat

Climate change is driving up temperatures, so I would’ve expected heat-related deaths to be skyrocketing. But a new study looking at 15 major German cities between 1993 and 2022 found something unexpected. Despite the summers getting hotter, the actual number of heat-related deaths has slightly declined. The researchers discovered that this is largely down to a drop in vulnerability. Basically, improvements in life expectancy and general health have acted as a buffer, protecting the population from the worst effects of rising temperatures.

To figure this out, the team used a clever method involving ‘counterfactual’ scenarios. They crunched the numbers to see what would have happened if life expectancy had stayed stuck at 1993 levels. The results were pretty interesting. Without those improvements in health and longevity, climate change would have driven a sharp rise in heat-related deaths. It’s a bit like running up a down escalator; we are getting healthier fast enough to outpace the rising heat, at least for now.

Of course, this doesn’t mean we are off the hook. The study found that the fingerprint of climate change on the deaths that do occur is getting stronger. The proportion of heat deaths directly attributable to climate change has been rising by about 5.6% every decade. In extreme years like the 2003 heatwave, climate change was responsible for a massive chunk of the mortality burden. This suggests that while better health is masking the problem, the underlying threat from a warming climate is intensifying.

3. Ground-based cameras are fixing the blind spot in weather models

We rely heavily on weather models for everything from routing flights to predicting renewable energy output, but these models have a significant blind spot: small, shallow cumulus clouds. These clouds cover a massive portion of the Earth’s surface, yet they are too small and short-lived for standard global models to simulate directly. The usual fix involves using approximations, but these introduce errors. Getting better data is tough because high-resolution satellites might only revisit a spot every few days, and radar systems only see a tiny slice of the sky. To solve this, researchers from Oxford and Imperial College London have developed Cloud4D, a framework that uses simple ground-based cameras to reconstruct clouds in four dimensions.

The system works by using a network of six synchronised cameras pointed skyward to capture the same cloud field from different angles. It applies a ‘homography-guided’ approach, which exploits the fact that clouds naturally form in layers, to map these 2D images into a 3D structure. A transformer model then refines this data to estimate the cloud’s liquid water content on a 25-metre grid. Unlike satellite data which can be days old, this system updates every five seconds 🤯. By tracking how these 3D reconstructions move over time, the model can even calculate horizontal wind vectors at different altitudes.

During a two-month real-world deployment, the system proved to be super effective. Cloud4D delivered an order-of-magnitude improvement in space-time resolution compared to state-of-the-art satellite products. Crucially, when the team cross-referenced their results with expensive collocated radar measurements, the camera-based system maintained a relative error of less than 10 per cent. This indicates that arrays of relatively cheap cameras could be a scalable way to gather the high-frequency data needed to validate and improve the next generation of climate and weather models.

4. The hidden fragility of a greener world

We often hear that the world is getting greener due to CO2 fertilisation, but a new study in Nature Communications suggests this greening hides a deeper problem. By analysing decades of satellite data, researchers found that while vegetation cover is increasing, its ‘resilience’ is actually dropping across over 40% of vegetated land. ‘Resilience’ is pretty much how quickly land can bounce back from a shock.

It turns out that a massive driver of this hidden instability is the El Niño-Southern Oscillation (ENSO), the major climate cycle that warms and cools the tropical Pacific. The researchers discovered that ENSO significantly impacts the resilience of 53% of the global vegetated area, meaning this single climate phenomenon is dictating the health of forests and grasslands on a massive scale.

The study breaks down exactly how ENSO messes with plants, identifying two main pathways:

1. ‘Atmospheric synchronisation’, where large-scale air circulation patterns directly link ENSO events to plant health.

2. The ‘climate-mediated’ pathway, where ENSO triggers local anomalies like heatwaves, droughts or floods that stress plants out.

The researchers found that El Niño events tend to cause sharp, immediate drops in resilience due to high heat and water stress, particularly in tropical forests. La Niña isn’t harmless either, though its impacts are sneaky; they often lag behind, hitting ecosystems hard up to three years after the event starts.

Looking ahead, the situation looks likely to intensify. Using climate models to project through to 2100, the team predicts that the footprint of ENSO-driven climate anomalies will expand by another 7 to 10%. This means regions that were previously relatively safe from these tropical climate swings, such as Eastern Siberia and the northern parts of North America, are going to start feeling the pressure. This expansion suggests we can’t just rely on planting trees to solve climate issues; we need to ensure the forests we have are actually tough enough to survive the increasingly volatile pendulum of global climate cycles.

Geospatial Datasets

1. Downscaled CMIP6 simulations

The Ouranos CRCM5-CMIP6 ensemble contributes to the NA-CORDEX initiative by providing dynamically downscaled climate simulations over North America. Driven by four global models, this project provides high-resolution 0.11° (approx. 12 km) projections spanning from 1950 to 2100 across various emission scenarios. You can access the data here and the code here.

2. Marine heatwave dataset

Capturing the unprecedented 2023 Marine Heatwave in the North Atlantic, this dataset features high-resolution observations from a drifting Spotter buoy off the west coast of Ireland. You can access the data here, the spectral code here, and the wind estimation tools here.

3. Shoreline change drone data

This dataset offers a seasonally structured record of shoreline change at Sugarloaf Island, North Carolina, tracking the evolution of a hybrid living shoreline project from 2023 to 2025. You can access the data here.

4. High-res CO₂ and pollutant emission data

The CHETNA-Road dataset offers a vital resource for understanding urban air quality in India, delivering 500 m gridded data on CO₂ and pollutant emissions across 15 major cities. You can access the data here and the code here.

Other useful bits

• ESA has successfully switched the ten-year-old Sentinel-2A satellite into night mode, capturing unexpected views of wildfires and fishing boats. These tests are providing vital insights for the Sentinel-2 Next Generation mission, ensuring future satellites can monitor the Earth around the clock.

• A new case study from Zambia highlights the power of open-source geospatial tools and free satellite data in mapping complex drought risks. By combining hazard indicators with vulnerability metrics, this report offers a practical blueprint for using accessible technology to strengthen climate resilience and early warning systems.

• Globe Telecom is breaking new ground in Southeast Asia by rolling out Starlink’s Direct to Cell service for everyday mobile phones. By acting as a ‘cell tower in space’, this partnership will bring vital connectivity to remote Philippine islands and ensure a lifeline remains open when terrestrial networks fail.

• 2026 is shaping up to be a landmark year for space exploration, featuring everything from new flagship telescopes to historic lunar missions. With NASA’s Artemis II returning humans to the Moon’s orbit and international players like China, India, and Japan launching ambitious projects, the year promises a thrilling mix of global cooperation and competition in the cosmos.

Jobs

• ICARDA - International Center for Agricultural Research in the Dry Areas is looking for a Data Scientist based in Abu Dhabi, UAE.

• UNODC - Office on Drugs and Crime is looking for a Data Visualisation Consultant based in Vienna, Austria.

• ESCAP - Economic and Social Commission for Asia and the Pacific is looking for an Intern - Economic Affairs based in Bangkok, Thailand

Just for Fun

Open Infrastructure Map reveals the hidden skeleton of our world, visualising the power lines and telecom networks that are usually invisible on the standard OpenStreetMap. It’s a pretty interesting open-source project that brings these global layers to light for everyone to explore.

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 geospatial newsletter that’s hotter than a Nelly song… 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:

• Maritime Risks: Narrow lanes face $192 billion in trade risks.

• Extreme Rainfall: Local history drives risks for a billion people.

• Simple Models: RNNs outperform complex setups for African rainfall.

• Ecosystem Loss: Agriculture threatens vital grasslands and non-forest landscapes.

• Building Data: High-resolution building characteristics for the Global South.

Subscribe now

Research you should know about

1. The massive $192 billion trade risk hiding in our shipping lanes

Global trade relies on a handful of narrow passageways, known as maritime chokepoints, which are surprisingly vulnerable to a bunch of different hazards. A new study in Nature Communications finds that about $192 billion of trade is exposed to disruptions every year from things like cyclones, droughts, and geopolitical conflict. While we often think of these as local problems, the effects are actually systemic. Many countries are heavily dependent on multiple chokepoints without even realising it, particularly those in Central Asia or West Africa that might be thousands of kilometres away from the actual trouble.

To figure out the actual risk, the team calculated the Expected Value of Trade Disrupted by looking at how likely a hazard is, how long a closure would last, and how much trade would be blocked. They also validated their transport model against real-world vessel movements from the PortWatch platform, which uses AIS data to track ships. This approach accounts for whether there’s a way to go around a blockage or if ships are just stuck. They even looked at how joint disruptions might happen, such as when a single cyclone hits multiple chokepoints at once.

Altogether, the annual economic bill for these disruptions is roughly $10.7 billion, with an extra $3.4 billion tacked on from spiked freight rates. These price jumps happen because rerouting ships pulls capacity out of the global fleet, which makes shipping more expensive for everyone everywhere. Geopolitical risks at the Taiwan Strait and the Suez Canal are the primary drivers of these losses. Even if a country isn’t near a conflict zone, it might still see higher inflation and pricier goods because of the way these maritime links are all stitched together.

You can access the data and code here.

2. We’re underestimating the next record-shattering rain event

We often think of extreme rainfall through the lens of a steady climate trend, but a new study in Nature Communications shows that local history is a much bigger driver of near-term disasters. The researchers found that record-breaking potential depends on a bunch of factors, but the size of the standing record is a pretty big one. If a region has a low historical record just because of natural luck, it’s in a much more dangerous spot for a surprise jump in the near future. This path-dependency means that our local experience of the past is just as important as the global models we use to predict the future.

The way climate change interacts with these records is pretty surprising because it doesn’t hit every place the same way. On average, moderate warming is set to hike up the chance of a record-breaking event by about 40% by 2050. However, the most sensitive areas are actually the ones with high standing records. These regions see the steepest increase in risk, with a 75% jump in the likelihood of a record-shattering event. It turns out that while low-record areas are most at risk right now, the high-record areas are becoming less safe at the fastest rate.

There’s also a human element involved in how these records turn into full-blown disasters. When a place hasn’t seen a record-breaking storm in a long time, the local society often loses its sense of risk, which leads to a massive gap in preparedness. This is a major threat for about a billion people who are likely to face record-shattering rainfall by the end of the century. Many of these hotspots are in fast-growing urban areas where poverty and rapid urbanisation make the population even more vulnerable to the next big surprise.

You can access the code here.

3. Complex models aren’t always better for rainfall

I've been looking at how we predict rainfall in Africa lately, as it's a pretty big factor for food security across the continent. A new paper in Scientific Reports examines the use of deep learning for daily forecasts in cities like Nairobi and Abuja. The researchers were analysing over 40 years of NASA’s MERRA-2 data, which is a popular reanalysis dataset for this kind of work, to see if they could improve on traditional stats by comparing single models like Recurrent Neural Networks (RNNs) against more complex hybrid setups.

The results are a bit of a reality check for anyone who thinks more complex is always better. Even though hybrid models are theoretically more powerful, the study found that single models actually did a better job in most spots. Specifically, the RNN came out on top in Nairobi, Pretoria, and Rabat (this was news to me, since I thought the RNN was all but dead…). There are a bunch of reasons for this, but it’s mostly because simpler models are more reliable, have fewer parameters, and don’t overfit the noisy weather data as easily. The only place where a hybrid model took the lead was in Abuja, which suggests that extra complexity only pays off when the rainfall patterns are particularly wild.

There’s also a bunch of interesting spatial stuff happening here. The researchers found that rainfall patterns between these cities aren’t really correlated, meaning local atmospheric conditions are driving the bus rather than one big continental system. Relative humidity was the biggest predictor in most spots, which I guess makes sense for the tropics. However, in drier places like Rabat, the weather from the previous two days was the most important factor. This highlights how important it is to use location-specific modelling because what works for one African city can’t just be copy-pasted onto another (something we’ve all been guilty of)…

4. Why our focus on deforestation is missing half the picture

While the world’s eyes are usually glued to deforestation rates in the Amazon, a new study shows that agricultural expansion is impacting non-forest ecosystems just as much. Grasslands, shrublands, and wetlands are often overlooked in global conservation talks, yet they store huge amounts of carbon and host a massive chunk of the planet’s biodiversity. By analysing land cover changes from 2000 to 2020, researchers found that the conversion of these open landscapes into croplands and pastures is often more extensive than the loss of actual forests. This is a pretty big deal because these areas are typically less protected and are more vulnerable to being ploughed up for farming.

There’s a bunch of reasons why this study stands out, but the main one is how it handles satellite data. The team used three different high-resolution datasets to track where these changes are happening, which is important because different models have different ways of defining a forest or a wetland. For example, some datasets might count tree crops like oil palm as forest while others see them as agriculture, which can lead to messy results. By comparing the data they analysed, they identified a consistent group of global hotspots where non-forest land is disappearing fast. Brazil, the United States, China, Russia, and Argentina topped the list, making up over 60 per cent of all non-forest conversion worldwide.

The environmental cost of this shift is massive. The study found that habitats for over 5,000 threatened species have been affected by this expansion, and over half of these creatures rely specifically on non-forest ecosystems. Even within supposedly protected areas, conversion rates for grasslands and wetlands are actually increasing. This suggests that current conservation frameworks are failing to shield these vital landscapes, particularly in places where agricultural suitability makes them a prime target for new farms. As supply chains come under more scrutiny, focusing solely on trees will likely leave some of the world’s most carbon-rich and diverse landscapes at risk.

You can access the code here.

Geospatial Datasets

1. Building characteristics dataset

This dataset derives high-res (100 m) annual building characteristics for the Global South from 2016 to 2023, based on the Google Open Buildings Temporal dataset. It provides six spatial layers per year, including building count, area, volume, height variability, and proximity metrics. You can access the data here.

2. Global vegetation dataset

VegVault is a huge, versioned SQLite database (~110 GB) that brings together global vegetation data across both the present day and the last ~20,000 years. You can access the data here and the code here.

3. City and town boundaries dataset

A new Global City and Town Boundaries (GCTB) dataset maps annual urban settlement boundaries worldwide from 2000–2022 at 30 m resolution. You can access the data here and the code here.

4. Cartographic map benchmark dataset

CartoMapQA is a new benchmark dataset for testing how well vision–language models can actually understand cartographic maps, not just talk about them. It includes 2,251 QA samples across 853 OpenStreetMap-rendered maps, covering a neat hierarchy of tasks from symbol/feature semantics and feature counting/name extraction through to scale-bar distance estimation and turn-by-turn shortest-route navigation. You can access the data and code here.

Other useful bits

• This handy Python–Flask tool lets you draw a box on a map and download OpenStreetMap or satellite tiles for offline use, exporting them as a ZIP or MBTiles file. It’s ideal for personal or educational projects, with features like tile count previews, live map previews, and flexible zoom levels.

• The Library of Congress Geography and Map Division has released its 2025 digital scan highlights, featuring notable 18th-century Dutch wall maps and a rare hand-drawn Islamic world map. The collection also includes significant historical documents such as Albert Speer's 1942 Berlin redevelopment plan and various newly digitized panoramic "bird's-eye-view" city maps.

• As satellite launches are projected to reach 1.7 million by 2030, astronomers are urging UN bodies to establish international standards to mitigate light and radio interference. While some operators are testing non-reflective coatings and signal-steering, the sheer volume of planned megaconstellations threatens to permanently degrade both optical and radio observations.

• Scientists have used Parker Solar Probe data to map the Alfvén critical surface, the "spiky" boundary where solar plasma becomes solar wind. These maps show the surface expands and becomes more irregular during solar maximum, offering a new tool for predicting how solar storms might affect Earth.

Jobs

• The Alan Turing Institute is looking for a Senior Research Associate based in London under its Environment Forecasting Mission.

• The Gates Foundation is looking for a Senior Strategy Officer, Geospatial Insights (LTE) based in Seattle under its Global Development Division.

• UNOCC is looking for a Geographical Information Systems Intern under its Data Unit (offering a flexible work arrangement).

Just for Fun

Check out this "Earthrise" footage captured by the Japanese lunar orbiter, SELENE (Kaguya).

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 — think of us as a safe space for the EPSG:4326-curious. The aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Damage Mapping: Sentinel data maps disaster damage effectively.

• Road Safety: Probabilistic model predicts crash risk uncertainty.

• Human Mobility: Satellite imagery predicts urban movement flows.

• Renewable Energy: Microsoft maps global solar and wind sites.

• Fire Emissions: Global database tracks landscape fire emissions.

Subscribe now

Research you should know about

1. Predicting human mobility flows from satellite imagery

Understanding how people move around cities is obviously quite important for transport systems and urban planning. Traditionally, we’ve relied on expensive surveys or mobile phone data to track these mobility flows. However, surveys are costly to update and mobile data comes with privacy concerns. A new study in Nature Communications proposes a different approach called Imagery2Flow. It uses a deep learning model to predict human mobility flows directly from satellite imagery. The authors tested this on the top 10 largest metropolitan areas in the US to see if the built environment alone could reveal how populations move.

The researchers developed a framework that extracts visual features from medium-resolution satellite imagery like Sentinel-2 and Landsat-8. The model encodes these images into high-dimensional vectors and uses a Graph Attention Network (GAT) to understand the spatial interactions between different areas. Essentially, it learns to predict the number of people moving between locations by analysing the visual characteristics of the urban landscape. It looks at the texture and arrangement of urban features to infer movement patterns without needing direct tracking data of individuals. This allows it to generate origin-destination matrices purely from open-source imagery.

The results were pretty impressive. The model outperformed traditional gravity and radiation models and even beat other deep learning baselines. Specifically, using 10-metre resolution imagery reduced the Root Mean Square Error by a range of 4.5% to 13.9% compared to machine learning models that just use visual features. Interestingly, the study found a strong link between the predicted mobility patterns and urban morphology. The model also showed good transferability. A model trained on data from 2020 could accurately predict flows using imagery from 2010. This suggests that the physical structure of a city holds deep clues about how we move through it.

You can access the code here.

2. Some surprising findings on resolution and damage mapping

Accessing Very High Resolution (VHR) imagery immediately after a disaster is often difficult or prohibitively expensive for humanitarian agencies. A new study from ETH Zurich investigates whether free, medium-resolution data from the Copernicus programme can effectively fill this gap. The researchers introduced xBD-S12, a massive dataset that pairs over 10,000 pre- and post-disaster image pairs from Sentinel-1 and Sentinel-2 with the established xBD benchmark. Their goal was to determine if these 10-metre resolution images could detect building damage across various disaster scenarios, ranging from floods to wildfires, without relying on commercial providers.

The results indicate that while resolution is a constraint, it isn’t a dealbreaker for every scenario. The models performed surprisingly well for large-scale events like wildfires and floods where spectral signatures change dramatically over wide areas. However, the 10-metre ground sampling distance struggled with sparse damage events, such as weak earthquakes where only individual buildings were affected amidst a dense urban fabric. The authors also found that architectural sophistication provided little advantage here. Simple U-Net models actually outperformed complex geospatial foundation models like Prithvi or DOFA, particularly when the models had to generalise to unseen disasters.

To achieve these results, the team adopted a two-step approach that first localises buildings and then classifies the damage. This method proved more robust for unseen locations compared to trying to do everything in a single joint optimisation step. Ultimately, this research suggests that while Sentinel data can’t quite replace VHR imagery for detailed forensic analysis, it serves as a powerful and accessible complement for rapid, wide-area assessments. It allows humanitarian teams to get a pretty big head start on understanding the extent of destruction when aerial or high-resolution satellite data is unavailable.

3. Estimating road crash risk and uncertainty from satellite imagery

Most models trying to predict car crash risk from satellite imagery have a pretty big flaw. They tend to be overconfident binary classifiers that just spit out a single “crash” or “no crash” prediction. A new study that’ll be presented at AAAI’26 proposes a smarter way to handle this using something called Beta Distribution Learning. By moving away from static yes or no answers, their model generates a full probability distribution for every location. This allows the system to express uncertainty, meaning it can tell you if a road looks genuinely safe or if the model just isn’t sure because the visual data is ambiguous.

The researchers achieved this by using a clever procedural labelling technique during training. When the model looks at a satellite image crop, it calculates an “influence score” based on how close a crash site is to the centre of the image and the size of the crop. This teaches the neural network that visual evidence is stronger when hazards are front and centre. Consequently, the model outputs two parameters (alpha and beta) that define a curve. A sharp peak in the curve means the model is highly confident in its risk assessment, while a flat, wide curve signals that the model is uncertain. It’s a lot more nuanced than a simple binary label and helps distinguish between safe roads and confusing ones.

Testing this on a dataset of Texas roadways showed that this probabilistic approach is much more reliable than standard methods. The model improved recall by around 20 per cent compared to state-of-the-art baselines, meaning it successfully identified many dangerous locations that other models missed. In a case study of the San Antonio River Walk, it correctly flagged a hazardous intersection near a parking garage that earlier models ignored. Even when the model made “mistakes” (like flagging a safe but complex highway interchange as risky), it did so with low confidence. This provides a helpful signal for human planners to investigate further rather than blindly trusting the machine.

Geospatial Datasets

1. Microsoft global renewables watch

Microsoft has released two global geospatial datasets mapping solar and wind energy installations worldwide, covering the period 2017 to Q2 2024. Together, they identify 375,197 individual wind turbines and 86,410 solar PV installations, each with estimated construction dates and associated land-use context.

2. Global fire emissions database

GFED5 is the latest version of the Global Fire Emissions Database, providing monthly global estimates of landscape fire emissions at 0.25° resolution from 2002–2022, with extensions back to 1997. You can access the data and code here.

3. Large reservoir operational variables dataset

GDROM v2 is a comprehensive open dataset covering daily inflow, release, storage time series, and operational rules for 2,017 large reservoirs across the contiguous United States. You can access the data and code here.

4. Potential light availability dataset

The SwissRad10 dataset provides nationwide, hourly maps of potential light availability across Switzerland at a 10 m resolution, covering a full annual solar cycle. You can access the data here and the code here.

Other useful bits

• Apple’s SHARP shows just how fast things are moving in 3D vision: generating sharp, photorealistic new views from a single image in under a second. It delivers big quality gains across benchmarks while dramatically cutting compute time, opening the door to more lightweight and scalable 3D scene reconstruction.

• Meta has released SAM Audio, a unified model that can isolate any sound from complex audio using text, visual, or time-span prompts— a big step forward for flexible audio understanding. The model, along with benchmarks and research resources, is now open to the community, opening up new creative and analytical possibilities across audio applications.

• Copernicus Sentinel-2 satellites are teaming up in early 2026, with Sentinel-2A and Sentinel-2B flying in tandem to image the same locations just 30 seconds apart, helping fine-tune radiometric calibration across the constellation. This short but carefully planned campaign will further boost data consistency and quality for everything from precision agriculture to methane monitoring.

• InSAR.dev has launched a new Sentinel-1 workflow on Google Colab, making burst-level InSAR preprocessing and analysis fast, portable, and genuinely reusable across platforms. With cloud-ready data, a GPU-accelerated phase unwrapper, and dramatic speed-ups (minutes instead of hours), it’s a big step toward making high-resolution elevation and deformation mapping accessible to everyone.

Jobs

• Department of Political and Peacebuilding Affairs-Department of Peace Operations-Shared Structure is looking for a Geographical Information Systems Intern based in New York, USA

• UNEP - United Nations Environment Programme is looking for an Intern for Policy and Analysis Unit based in Geneva, Switzerland

• Resources for the Future (RFF) is looking for a Summer Research Internship based in Washington, USA

• First Street is looking for a Lead Product Manager based in New York, USA

Just for Fun

This video shows how Earth rotates in space by stabilizing the Milky Way galaxy.

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 someone asks who your favourite band is, and you answer ‘near infrared’, then we have one thing to say to you: welcome home. As usual, the aim is to make you a better geospatial data scientist in less than five minutes a week.

In today’s newsletter:

• Mapping Buildings: OpenFACADES turns street images into structured data.

• Identifying Vulnerability: New index tracks climate risks at subnational levels.

• Seismic Mapping: Smartphones improve accuracy of urban shaking maps.

• Transit Analysis: Tool links metro access to housing price trends.

• Forest Data: Map distinguishes natural forests from tree plantations.

Subscribe now

Research you should know about

1. An open framework for understanding buildings from street-view images

Gaps in objective building data are a massive headache for urban analytics. While we have plenty of street-level imagery, extracting structured data from it remains a bit of a challenge. A new study introduces OpenFACADES, a framework that combines crowdsourced street-level visuals with OpenStreetMap data to train a Vision-Language Model (VLM). The goal is to automate the extraction of physical attributes like material, age, and type, while also generating descriptive captions. It essentially turns messy street photos into structured, actionable geospatial data on a global scale.

The researchers used a pipeline involving isovist analysis and reprojection to grab holistic views of building facades from crowdsourced images. They then fine-tuned open-source VLMs on this dataset, and the results were pretty impressive. These fine-tuned models outperformed traditional computer vision models and even beat zero-shot ChatGPT-4o in predicting multiple attributes. They found that even a modest, well-curated dataset allowed small-scale models to capture most of the benefits of large-scale pretraining. This shows you don’t always need the biggest model or the most compute to get state-of-the-art results.

To prove the system works, they applied this pipeline to half a million buildings across seven global cities. This generated a massive dataset of objective attributes and rich textual descriptions which they have released openly. This kind of data is gold for things like energy modelling, structural risk assessment, and understanding urban morphology. By releasing the code and data, they are making advanced building profiling accessible without the high costs of proprietary APIs. It opens up a bunch of new possibilities for analysing the built environment using open-source tools.

You can access the data and code here.

2. Mapping vulnerability at 10x higher resolution

Most climate vulnerability indices rank countries against each other, but a new study published in Sustainability argues that national averages hide massive disparities on the ground. To address this blind spot, researchers from the Global Data Lab have released the Subnational Global Data Lab Vulnerability Index (SGVI). This massive new dataset covers 1260 regions across 118 Low- and Middle-Income Countries to track human vulnerability to climate change and natural disasters. It represents a pretty big leap forward for the field as it provides ten times more detail than previous national-level models, allowing us to see exactly where the hotspots are located within borders.

The team constructed this index by aggregating eleven indicators across seven core dimensions, including economy, education, health, gender, and infrastructure. Since subnational data is often patchy in developing regions, they used regression-based prediction models to estimate missing values based on available survey and satellite data. They then standardised these local estimates around established national means to ensure consistency with existing country-level datasets. This approach essentially allowed them to generate a complete year-by-year record of vulnerability for every included region from 2000 to 2023.

The results highlight just how much information is lost when we only look at national statistics. The study found that using national data masks about 20 per cent of the variation in vulnerability globally, and this figure jumps to over 70 per cent in the poorest regions like Sub-Saharan Africa. While the data shows that overall vulnerability across the developing world has dropped by roughly 24 per cent since 2000, the gap between the best and worst-performing regions has actually widened. This indicates that while development is happening, it is highly uneven, making these local-level insights essential for targeting climate adaptation funds where they are needed most.

3. We can now use phones to map seismic risk

We rely on seismic shaking maps to understand earthquake impacts, yet these maps often lack detail in urban areas because monitoring stations are too sparse. A new study in Nature Communications tackles this by tapping into a resource that’s pretty much everywhere: the smartphone. Focusing on the Campi Flegrei red zone in Italy, the researchers used data from the Earthquake Network citizen science initiative to densify the recording network. While traditional stations are few and far between, thousands of residents have phones equipped with accelerometers that can capture seismic motion right where people live.

Integrating this crowdsourced data is sort of tricky because smartphones aren’t anchored to the ground like scientific instruments. The study found that smartphones typically record higher acceleration values than ground stations, likely because they sit on furniture or loose surfaces that amplify the shaking. To solve this, the authors developed a statistical approach that fuses data from both sources. They extracted the consistent spatial patterns of amplification from the noisy smartphone readings and combined them with the precise data from seismic stations. This allowed them to map local site effects at a much higher resolution than was previously possible.

The results show that adding smartphone data makes a massive difference to the accuracy of ground motion models. By incorporating these devices, the researchers reduced the uncertainty in their shaking estimates by over 70 per cent compared to using stations alone. This method created a detailed amplification map that highlights exactly which parts of the city are most prone to heavy shaking. It provides a pretty big leap forward for emergency planning, as it allows authorities to generate real-time, street-level shaking maps immediately after an event occurs.

You can check out the data and code here.

4. Exploring how metro access shapes housing prices

It’s pretty well established that living near a metro station bumps up property values, reducing commute times and boosting neighbourhood appeal. Usually, though, trying to visualise this data is a pain because you have to cross-reference static maps with market reports manually. That’s where a new system called RailEstate comes in. Developed by researchers at Virginia Tech, this web-based tool mashes up twenty-five years of housing data with transit infrastructure to show exactly how proximity to the Washington metropolitan area’s metro stations impacts local real estate prices.

The platform lets you interactively explore price trends at the ZIP-code level, but one feature (of course) is the integration of a natural language chatbot. Instead of needing to know how to code, you can just ask plain English questions like ‘What’s the highest price in Falls Church in the year 2000?’. The system uses an LLM to translate that text into an optimised SQL query, runs it against the spatial database, and spits back the answer in seconds. It basically democratises access to complex geospatial queries that used to require a fair bit of technical know-how.

On top of the historical analysis, the tool includes a forecasting engine that projects future values up to a year in advance. This is super useful for seeing how infrastructure shocks, like a new line extension, might shake up the market down the road. While the current demo focuses on D.C., the architecture is portable enough to work for any city with standard transit data. It is a pretty solid example of how we can combine spatial analytics with AI to make urban planning data accessible to just about anyone.

You can check out the demo video here.

Geospatial Datasets

1. Natural Forests of the World 2020

Natural Forests of the World 2020 is a globally consistent 10-m map that distinguishes natural forests from plantations and other tree cover. It’s trained on over 1.2 million multi-temporal Sentinel-2 image patches. The release also includes large benchmark datasets (Planted and ForTy) to support next-generation forest-type modelling and the development of future global maps. You can access the data here and the code here.

2. Integrated Urban Traffic-Flood (IUTF) dataset

The IUTF dataset offers a rare, cross-border view of how rainfall and flooding affect urban mobility, bringing together harmonised traffic sensor data, ERA5 precipitation, and detailed road-network topology for 40 cities across Europe, North America, and Asia. With over 21,700 sensors (raw 5-minute readings aggregated to hourly) and more than 1 million road segments, it provides one of the most comprehensive resources yet for studying weather–traffic interactions at scale. You can access the data here and the code here.

3. Integrated meteocean-seismic dataset

This integrated meteocean–seismic dataset provides rare, high-resolution observations from Deception Island, Antarctica, capturing seawater pCO₂, temperature, salinity, wind, solar radiation, tides, and volcanic seismic activity. You can access the code here.

4. Hourly potential light availability dataset

SwissRad10 is a high-res dataset of hourly potential light availability at 10 m across all of Switzerland, capturing how terrain and every individual tree shape direct and diffuse light over a full year. You can access the data here and the code here.

Other useful bits

• Sentinel-2A is running a special December 2025 night-time acquisition campaign, collecting Level-1B images over hotspots like gas flares, bright city lights, wildfires, and fishing zones to test how well the mission can see the world after dark. The data will help shape Sentinel-2 Next Generation by showing where night-time imaging adds real value.

• The World Bank’s new MANAGE-WB model offers teams a flexible, single-country CGE framework to explore macroeconomic scenarios across sectors, institutions, and production factors. It comes with a user-friendly interface, SAM-building tools, and built-in sensitivity and stochastic simulation features, making complex macro analysis much more accessible.

• SamGeo v0.14.0 recently dropped, bringing interactive, SAM3-powered segmentation to remote sensing workflows. Draw a box or type a prompt, and it instantly finds matching objects across an image. It’s fast, label-free, and delightfully simple to use, with demos and code ready on GitHub and the new notebook.

Jobs

• Map Action is looking for a remote Geospatial Data Engineer.

• MapBox is looking for a Director of Product (Maps), in the US.

Just for Fun

Check out this video from NASA, which shows what the first 150 milliseconds of a supernova looks like.

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,

Today is a bit of a special edition. A few people have been asking about how to begin writing on Substack. A bunch of people are stuck at 10-100 subscribers or so, and are wondering how to take it from here.

So if you’re considering writing on Substack, I hope today’s edition will help in a few areas:

1. How to initially start writing on Substack

2. How to grow subscribers

3. How to make writing more sustainable

Firstly, and importantly let me start with some caveats. I only have about 4,000 subscribers. I don’t make any money from this blog and I do this on the side (since I have a full time job). So there are certainly other people you can learn from on how to make Substack your main source of income, if that’s what you’re into.

Onwards…

1. Why start a Substack: inbound opportunities

There a bunch of reasons why people choose to write on social media and Substack more specifically. The main one is that it helps improve your visibility, it can establish you as a domain expert, and ultimately this can all help drive sales to your business (if you have one).

I’m in a slightly different position. I don’t actually sell any products, and I don’t do this to make money. Instead the reasons are a bit more internal.

At the end of the day, my main job is as a geospatial researcher. And I want to be on top of the latest innovations in the geospatial space. This helps me ensure that I’m doing cutting-edge research, rather than doing stuff that was innovative 5 years ago. Writing this newsletter is essentially a forcing function to stay on top of the latest papers in the geospatial space.

By sharing what I read, I’m required to understand the topics in these papers and to articulate them clearly to less technical folks (this is a pretty important skill to develop in my day job).

But what are the benefits of writing online?

• I’ve e-met a bunch of interesting folks who’ve reached out and have become co-authors or collaborators.

• People send me papers they think should be featured in the newsletter, which is another awesome way of staying on top of things.

• From time to time, people reach out with requests to do podcasts, guest lectures and so on.

So the rewards, in my opinion, are worth it.

OK, so then how do you actually start writing on Substack?

2. Starting on Substack: get subscribers before making your first post

I’ve seen a bunch of advice on how to start on Substack. The advice is mainly about staying persistent, writing ‘Notes’ every day, engaging with other publications and so on.

This is actually the opposite of what I did.

The main problem with Substack is that ‘discovery’ (i.e. being discovered), isn’t as good as other platforms like X, Youtube, Instagram, etc.

My strategy to gain subscribers at the start was to leverage ‘discoverability’ from Twitter (yes it was called Twitter back then). I essentially posted 4 threads a week on Twitter on a range of geospatial topics: my favourite datasets, new papers, new methodologies, and so on.

Then, at the end of every thread, I’d provide a call to action to subscribe to this newsletter:

This worked remarkably well. I still do that to this day. And in fact, most of you guys reading this have discovered me through X.

When I decided to launch this newsletter, I decided I didn’t want to publish anything till I got to 200 subscribers. It took a LOT of effort to write newsletters back then - probably 1-2 days (I’ll explain how I managed to expedite the process below). I didn’t want to spend that much time writing a newsletter if only a couple of people read it.

So I told my followers on Twitter than I was about to launch a new newsletter.

I then waited for 200 people to sign up, before sending out my first newsletter.

This is the strategy I would take: start posting on the socials (X, LinkedIn, YouTube or Instagram), and then plug your newsletter.

And yes, I recognise this means you need to develop an audience on another platform first. I have a bunch of strategies/thoughts on how to do this, but for now it’s beyond the scope of this article.

Ultimately, my posting on X is mainly to get subscribers for this newsletter.

Writing on X means you need to write for engagement, retweets, etc. The room for nuance is non-existent. That’s why I much prefer Substack: I don’t need to worry about the algorithm. I can be nuanced.

3. Growing on Substack: consistency, consistency, consistency

At the end of the day, you’re obviously not going to grow on Substack if you’re not posting regularly.

I’d recommend posting at least once a fortnight, but ideally once a week.

4. Writing on Substack without burning out

The question, of course, is how to post consistently without burning out.

In the early days of this newsletter, I was writing a lot of ‘think’ pieces and tutorials. This ended up taking a lot of time to do.

I needed to come up with a topic to write about, I’d then need an original take, and a lot of editing to ensure I could articulate my point concisely.

When I’d hit ‘send’ on an edition, I didn’t feel happy or relieved. Instead, I felt a sense of dread. Because I knew I had to go through this whole process for the following week’s edition.

I essentially felt like this dude:

I knew I couldn’t go on like this.

So I decided to completely rebrand this newsletter into a weekly ‘round up’ of geospatial research, that could be read in roughly 5 minutes.

To do this, I came up with a structure for the newsletter:

1. Research you should know about

2. New geospatial datasets

3. Other interesting geospatial news

4. Geospatial job vacancies

Having this new templated structure was a life saver. It meant I didn’t need to constantly worry about how to write a new edition. I just needed to populate the template.

For the first several months, this took a lot of time. I’d spend numerous hours on X and LinkedIn looking for relevant things to feature.

Side note: in the early days, Twitter used to be excellent for finding geospatial papers and news. I’d curated a Twitter list with a hundred or so people who were actively discussing geospatial topics. This was probably the best way of discovering new stuff to feature.

Then, after Elon endorsed Trump, most of those people left X and migrated to BlueSky. I tried for months to use BlueSky, but it just didn’t have the same vibe as the old Twitter, so I gave up… This meant I’d lost one of the best avenues for discovering geospatial news.

Given this, I’d have to visit dozens of research journal websites to find new geospatial papers. I’d also visit a bunch of dataset websites (e.g. Zenodo, or Data Dryad) to find new datasets. This would take around half a day to one full day to compile the papers.

Again, this wasn’t sustainable, so I needed to develop a more efficient system.

5. Getting consistency through automations

As a data scientist, I knew that had to be a better way of doing things. One that helped me automate at least some of the process.

In the end, I decided to set up dozens of scrapers that would scrape relevant geospatial paper abstracts from journal websites, datasets and jobs and push them to my Slack workspace:

This is set to run every Monday morning. I then wake up to a hundred or so papers with their abstracts located in the #papers-automation channel:

This makes it super easy for me to skim through the abstracts to find papers I find interesting. I usually select papers that are related to topics I’m working on, or which have a social science element to it (e.g. using geospatial techniques to estimate government quality, or inequality, etc.).

The bottom line is that I no longer need to visit dozens of different websites. This helps me save several hours each week.

Finally, I’m fortunate to have hired someone to help me with the newsletter. She helps me identify items for the “other interesting bits” and “jobs'“ sections, and to set up the Substack template for each week.

Having someone to help out isn’t strictly necessary, but for me, it helps reduce friction and ensure that I can stay consistent with the newsletter.

Anyway, hope all of this helps. Hit me up if you have any questions.

Merry Christmas 🎄

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 sinusoidal fetishists. 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:

• Segmentation Uncertainty: Deep learning models struggle with pixel-level confidence.

• Earth AI: Google combines foundation models for geospatial analysis.

• Urban Greening Simulation: IBM predicts park cooling effects before planting.

• Burned Area Data: ESA provides monthly fire data at 25km resolution.

• Building Density: TEMPO offers quarterly global building height estimates.

Subscribe now

Research you should know about

1. How well can segmentation models know when they’re wrong?

If you’ve worked with deep learning models for satellite image segmentation, you’ve probably wondered how much you can trust the model’s confidence scores. A new paper from Google DeepMind benchmarks different methods for estimating uncertainty in segmentation models trained on remote sensing data, and the findings are a bit of a mixed bag.

The authors tested a bunch of approaches (including simple probability-based metrics, ensemble models, and more sophisticated Stochastic Segmentation Networks) across two datasets: PASTIS (a French agricultural dataset with high-quality labels) and ForTy (a global forest types dataset with more variable label quality). The headline finding is that common uncertainty methods are pretty limited at identifying individual misclassified pixels at test time. However, they’re much better at flagging entire images that are likely to be poorly segmented, which could still be useful for quality control. Perhaps the most surprising result is that the choice of model architecture matters more than the choice of uncertainty method. Vision Transformer-based models substantially outperformed convolutional models (like UNET3D) at identifying segmentation errors. Ensembles gave the best overall segmentation accuracy, but Stochastic Segmentation Networks offered a good compromise between performance and efficiency, requiring only about 1% more parameters than a standard model while delivering competitive results.

There’s also a bit of an issue when it comes to noisy inputs. Models can only reliably identify corrupted pixels when the test-time noise level is much higher than what they saw during training. If you train with noise at the same level you encounter in the wild, the model basically adapts to it and loses its ability to flag those regions as problematic. The authors recommend setting aside a dedicated “uncertainty test set” for proper evaluation, since performance varies quite a bit across datasets and tasks.

2. Google’s new ‘Earth AI’ framework

Google Research has released a working paper introducing ‘Earth AI’, a family of geospatial AI models paired with an agentic reasoning system. The main idea is to move beyond the traditional approach of using single, siloed models for specific tasks (like analysing satellite imagery or population data) and instead combine multiple foundation models that can ‘talk’ to each other. The framework is built on three pillars:

1. an Imagery model (for interpreting satellite and aerial photos),

2. a Population model (for understanding human behaviour and demographics), and

3. Environment models (for weather, floods, and cyclones).

A Gemini-powered ‘reasoning agent’ then orchestrates these models, allowing users to ask complex, multi-step questions in plain language rather than needing to manually download, join, and cross-reference datasets themselves.

The results are pretty compelling. Google’s Remote Sensing models achieved state-of-the-art performance on a bunch of benchmarks for tasks like zero-shot image classification and object detection. Their Population Dynamics model, which fuses maps data, search trends, and anonymised ‘busyness’ data, has been independently validated by external partners for applications ranging from predicting retail activity to forecasting dengue outbreaks in Brazil. Interestingly, the paper shows that combining these models produces better predictions than using any single one alone. For instance, using both Population and Imagery embeddings together led to an 11% improvement in predicting FEMA disaster risk scores compared to using either model on its own. In a retrospective analysis of Hurricane Ian, a model combining Google’s experimental cyclone forecasts with their Population embeddings predicted the number of damaged buildings to within 3% of the actual figure, three days before landfall.

The reasoning agent is where things get pretty interesting for real-world applications. Rather than just retrieving data, it can break down complex queries (like ‘identify Florida counties with populations over 20,000 that are forecast to experience hurricane-force winds’), delegate sub-tasks to the appropriate specialist model, and synthesise the results. On a benchmark of crisis-response scenarios, the agent significantly outperformed a baseline Gemini model without the custom geospatial tools. I think this is one further step towards the golden goose of being able to generate geospatial analyses without requiring a geospatial background.

3. Simulating urban greening before anyone picks up a shovel

As cities get hotter, planners need good temperature data to figure out where to focus their cooling efforts. But there’s a bit of a problem. Traditional machine learning models need tons of local data to make accurate predictions, and that data often doesn’t exist for the cities that need it most. A new study from IBM Research tests whether geospatial foundation models (GFMs) can fill this gap. These models are trained on huge amounts of global satellite data, which means they can generalise to new cities with only minimal fine-tuning. The researchers used a GFM called Granite to predict land surface temperatures across 13 European cities that weren’t in the training set. They first established a ‘ground truth’ by measuring how parks actually cool down urban areas, both internally (within the park itself, temperatures dropped by up to 2.6°C) and through ‘spillover’ cooling into nearby built-up zones (up to 3.5°C cooler within 150 metres of a park edge).

The model did a pretty decent job replicating these cooling patterns. An improved version trained on more diverse cities reduced the error in predicting spillover cooling from 0.30°C to 0.20°C. They also tested how well the model could predict temperatures it had never seen by training it only on cooler days and then asking it to predict the hottest 10% of observations. It managed to extrapolate about 3.6°C beyond its training range with reasonable accuracy, which gave the researchers enough confidence to project future urban heat island intensification under different climate scenarios out to 2100.

The most interesting part, though, is the ‘inpainting’ simulation. The researchers digitally replaced a patch of built-up area in Prague with green space in the satellite imagery, adjusted the spectral indices accordingly, and ran the model to see what would happen to local temperatures. The model predicted both internal cooling within the hypothetical new park and spillover effects into the surrounding neighbourhood. It’s essentially a way to simulate urban greening interventions before anyone picks up a shovel, which could be pretty valuable for planners trying to decide where new parks would have the biggest impact.

Geospatial Datasets

1. Monthly burned area dataset

This dataset provides monthly mean burned area at 0.25° (~25 km) resolution, averaged across 2019–2024 and derived from the ESA FireCCI Sentinel-3 SYN v1.1 product.

2. Enhanced vegetation index composites

This dataset offers bimonthly Enhanced Vegetation Index (EVI) composites for 2020 at 250 m resolution, derived from MOD13Q1 and neatly organised into continental subsets. You can check out more on the data and code here.

3. GitHub’s GH Archive

The GH Archive project provides a continuously updated, open record of all public GitHub activity, capturing millions of events, such as commits, issues, forks, and comments, across more than a decade.

4. Building density and height estimates

TEMPO is a new global dataset and AI model that estimates building density and height from Planet imagery every three months. It provides a 2023 Q4 global layer at 100 m resolution, plus quarterly 40 m time-series datasets for several rapidly changing regions. You can check out the data and code here and the interactive map here.

Other useful bits

• NASA has released a new set of step-by-step tutorials to help GIS users bring Earth observation data to life, with guides for adding datasets, accessing web services, and building time-enabled mosaics in tools like ArcGIS Pro and QGIS. The resources draw on ECOSTRESS, MERRA-2 and other NASA datasets, making it easier than ever to explore and analyse environmental change.

• GIS and satellite data are helping Red Cross teams take life-saving early action in conflict-affected regions like Mali. By blending satellite climate intelligence with community-collected data and conflict monitoring, practitioners can pinpoint vulnerable water sources, understand compound risks, and support more targeted, locally driven humanitarian decisions.

• Thanks to Google’s Roads Management Insights, CERTH and NGIS can now track congestion, forecast traffic, and understand network bottlenecks with far greater precision. In Thessaloniki’s massive Flyover construction project, these tools revealed 40–50% longer travel times and fewer crashes, helping authorities reroute traffic, communicate expectations, and make smarter, data-driven decisions for the city’s travellers.

• AlphaEarth Foundations’ 64-channel satellite embeddings are now publicly accessible as Cloud-Optimized GeoTIFFs on Google Cloud Storage, giving users flexible, high-performance access across tools like Earth Engine, BigQuery, Vertex AI, and GDAL. The dataset is neatly organized by year and UTM zone, comes with spatial index files for fast querying, and remains free under CC-BY, making large-scale geospatial AI workflows far easier to build and integrate.

Jobs

• International Telecommunication Union (ITU) is looking for a remote Data Scientist under their Telecommunication Development Bureau.

• UN ESCAP is looking for a Senior Consultant on Crop Biodiversity Assessment based in Indonesia.

• UNHCR is looking for an Education Data and Evidence Officer based in Copenhagen.

• The International Center for Agricultural Research in the Dry Areas (ICARDA) is looking for a remote Site Suitability and Crop Modeling Expert.

• The Gates Foundation is looking for a Senior Strategy Officer, Geospatial Insights based in Seattle.

Just for Fun

NASA visualises a supernova (source).

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 as many fans as a multispectral image has bands… 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 Mapping: AI blends text and satellite data for better insights.

• Healthcare Planning: AI optimiser improves hospital placement and reduces travel times.

• Irrigation Risks: Water use cools air but increases dangerous humid heat.

• Smoke Impacts: Wildfire particulates raise heart and neurological risks in children.

• Population Data: New dataset offers global population projections through 2100.

Subscribe now

Research you should know about

1. Teaching AlphaEarth to understand cities

If you’ve used satellite images before, then you’ve most likely used it for some of the most common use cases like detecting changes in deforestation or urban sprawl. However, remote sensing struggles to capture the ‘human’ side of cities, like socioeconomic status or specific building functions. A new framework called AETHER fixes this gap by combining Earth Observation data (specifically Google’s AlphaEarth) with text-based Points of Interest. The researchers found that while satellite data sees the physical form, the text data explains the function. So blending them gives you a much richer picture of urban environments.

To make this work, the researchers used a technique called multimodal alignment to link visual embeddings with text descriptions. They adopted a dual-buffer approach that looks at a 50-metre radius for the specific site and a 100-metre radius for the surrounding context. By doing this, the model learns what a location looks like AND what happens there. It pretty much forces the satellite data to learn from the semantic richness of the POI text. This creates a better representation of urban spaces than pixel data could manage on its own.

The team tested this in London and saw some pretty big improvements. The AETHER model outperformed standard baselines on tasks like Land Use Classification and Socioeconomic Distribution Mapping. It turns out that injecting human-centred semantics into the mix lowers the error rate significantly when trying to map out things like population density or occupation types. Who woulda thought…

2. A new framework for mapping healthcare demand

Access to hospital care should be easy for everyone, yet even in wealthy regions, some communities face pretty big hurdles. As the population ages, these gaps in access risk widening and leaving underserved districts with higher health costs. A new paper from researchers at Saarland University tackles this by introducing a unified framework called EA-GeoAI. Previous studies have generally looked at travel times or population changes in isolation, so this approach advances the field by bringing everything together into a single decision tool to guide hospital placement.

The researchers combine district-level demographic shifts, ageing population density and infrastructure data into a unified Equity Index. They use an interpretable Agentic AI optimiser to allocate beds and identify new facility sites. The system acts like an intelligent agent that perceives the healthcare landscape through multiple data sources and proactively generates solutions. It balances the need for efficiency with fairness by minimising travel times and ensuring that vulnerable populations receive adequate coverage. It’s a smart way to ensure that hospital planning keeps up with future needs through 2030.

The results show that this AI-driven approach works much better than the status quo or simple population-based models. The model suggested placing new hospitals in the northern and eastern districts of Saarland where travel times were poorest and the elderly population was most vulnerable. By clustering new facilities in these underserved areas, the model cut average travel times significantly and improved equity scores. It provides a scalable and transparent framework that policymakers can use to make data-driven decisions that actually help the people who need it most.

You can access the code here.

3. Irrigation is cooling some heat extremes but is quietly worsening others

We often assume irrigation helps cool the local climate through evaporation, acting as a buffer against rising temperatures. However, a new study in Nature Communications explores a surprising trade-off in how this water use interacts with future warming. The authors developed a new dataset to model future irrigation techniques under different socioeconomic pathways to see how they impact local climate. They looked at a ‘green road’ scenario where efficiency improves and a ‘rocky road’ scenario where irrigation expands rapidly without efficiency upgrades, particularly in developing regions like Africa. This allowed them to analyse how these choices impact heat stress over the next 50 years.

The findings reveal a pretty big divergence between dry heat and moist heat. While pouring water on crops reduces dry-heat extremes by cooling the air, it simultaneously pumps humidity into the atmosphere. This spikes ‘moist-heat’ stress (measured by wet-bulb temperature), which is actually more dangerous for human health as it limits the body’s ability to cool down. Under the high-emissions scenario, the study predicts that new irrigation hot spots will emerge. Consequently, the combination of global warming and increased humidity means frequent exposure to dangerous moist-heat levels will likely outpace the benefits of local cooling.

It turns out that irrigation alone can’t reverse the warming trend driven by greenhouse gases. In fact, in places like South Asia, the study shows that irrigation amplifies the hours of exposure to extreme moist heat. The research highlights that limiting the expansion of unsustainable irrigation and switching to efficient methods like drip or sprinkler systems is crucial. These efficient techniques apply less water and therefore limit the humidity surge. Ultimately, this suggests that without cutting emissions and improving water efficiency, agricultural regions face a compounding risk of pretty severe humid heat.

You can access the data here and code here.

4. Turns out wildfire smoke impacts more than just lungs

Landscape fires are becoming a frequent headline, and we generally assume the smoke is bad for our lungs. However, a new study in Nature Communications suggests the health impacts on children are far broader than previously thought. The researchers analysed daily hospital admission records from over 1,000 communities across seven countries, including Brazil, Australia, and Canada. By using a machine learning model to calibrate satellite data with ground observations, they created a precise picture of exposure to fine particulate matter specifically sourced from landscape fires (LFS PM2.5).

The results reveal that the danger extends well beyond simple breathing difficulties. The data indicates that exposure significantly raises hospital admissions for a wide array of other conditions, including infectious diseases, cardiovascular problems, and neurological disorders. For every 10 µg/m³ increase in smoke-related particles, hospital admissions rose across the board. It’s worth noting that respiratory and neurological risks appear to climb even at very low exposure levels, whereas risks for conditions like diabetes and cardiovascular disease tend to spike only after the pollution concentration hits a higher threshold of around 15-20 µg/m³.

Geography and economics play a massive role in how these health impacts play out locally. The study found that children in lower socioeconomic regions faced a heavier burden of disease, which is likely due to differences in housing quality and access to healthcare. In terms of age, children between five and nine years old were the most vulnerable group for infectious disease admissions. This implies that while the smoke itself is a global issue, the actual health fallout is unevenly distributed based on where you live and local economic conditions.

You can access the data and code here.

Geospatial Datasets

1. Population projection dataset

This new WorldPop FuturePop release provides global 1 km population projections for every five years from 2025 to 2100, across all five SSP scenarios. The grids spatially allocate national-level projections using subnational estimates and settlement-growth models, making them directly compatible with CMIP climate frameworks.

2. Bioclimactic and topographic variables dataset

This dataset delivers 16 ENVIREM bioclimatic and topographic variables at 30-arcsecond (~1 km) resolution, which provides richer ecological information than standard WorldClim layers by incorporating metrics such as aridity, thermicity, continentality, and growing degree days.

3. Forest condition anomaly maps

This dataset provides nationwide forest condition anomaly maps for Germany from 2016–2024, derived from Sentinel-2 tree-species-specific reflectance time series. You can also check out the monitor here.

4. Soil and vegetation temperatures dataset

This global dataset offers monthly mean surface soil and vegetation temperatures at 0.05° (~5 km) resolution from 2003–2023, generated using the FuSVeT algorithm applied to MODIS LST and ERA5-Land data. It provides 504 GeoTIFF layers, neatly packaged by year, season, and temperature component.

Other useful bits

• Sentinel-6B is heading to orbit to extend the world’s most important sea-level monitoring record, continuing over 30 years of precise ocean height measurements that underpin climate planning and coastal protection. Once launched on a SpaceX Falcon 9, it’ll fly in tandem with its twin for cross-calibration before taking over as the primary sea-level sentinel.

• Real-time GIS is giving Amazonian law-enforcement teams a shared operational picture for the first time, letting Brazil, Colombia, Ecuador and Peru track illegal mining, logging and wildlife trafficking as a single connected system. By fusing satellite imagery, field reports and cross-border intelligence on one live map, the UAE-backed I2LEC platform is helping dismantle environmental crime networks that once hid in jurisdictional gaps.

• A huge community push has unlocked 465 TB of Google’s AlphaEarth embeddings on Source Cooperative, thanks to an impressive collaboration across the open-geo ecosystem. Asterisk Labs has shared a simple demo showing how to read these embeddings directly as Major TOM products. I think it’s a small but exciting step toward making large-scale geospatial AI far more open, usable and remixable.

• Real-time welfare tracking is becoming essential as governments face overlapping shocks, prompting a shift toward systems that blend surveys, big data, geospatial inputs, and modelling to generate timely insights. The World Bank’s new guidance emphasises choosing the “best fit” approach for each policy question and modernising traditional surveys so they can anchor faster, more adaptive monitoring that protects vulnerable communities when crises hit.

Jobs

• UNICEF is looking for a Digital Health and Geospatial Health Consultant based in New York.

• Mapbox is looking for a Software Development Engineer II based in the UK for their Navigation, Traffic team.

• ESA is looking for an Internal Research Fellow (PostDoc) in Geospatial Foundation Models for EO based in Frascati.

• Enveritas is looking for a remote Backend Software Engineer to be part of their EUDR engineering team.

Just for Fun

In case you didn’t recognise it, this is a map of Scotland, created in 1457 map of Scotland, by John Hardyng.

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 (sorry)... 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:

• Wealth Inequality: Local wealth gaps predict economic mobility.

• Farm Size Projections: Global farms could triple by 2100.

• Multimodal Foundation Models: Survey covers geospatial AI advances.

• CO₂ Mapping: Fusing satellite and ground data improves resolution.

• WeatherNext 2: Google’s AI model generates forecasts in seconds.

Subscribe now

Research you should know about

1. Wealth inequality matters more than income inequality for mobility

A new study published in Nature Communications looks at how growing up in areas with high wealth inequality affects your chances of moving up the income ladder. The author combines local wealth inequality estimates from GEOWEALTH-US with intergenerational mobility data from Opportunity Insights to examine outcomes for children born between 1978 and 1983 across 724 US commuting zones. The results are pretty nuts: children from low-income families (25th percentile) who grew up in areas with relatively low wealth inequality (Gini of 0.70) climbed to around the 47th income percentile in adulthood. Their peers in high-inequality areas (Gini of 0.85) only reached the 37th percentile. Interestingly, static simulations suggest that local wealth inequality is more strongly associated with upward mobility than income inequality itself. A hypothetical 50% reduction in local wealth inequality would boost predicted mobility from the 42nd to the 53rd percentile, while the same reduction in income inequality barely moves the needle.

The study points to education as a key channel linking wealth inequality to reduced mobility. In areas with higher wealth inequality, fewer children from low-income families complete community college degrees. This matters because most low-income children don’t compete for elite universities. They rely on local educational infrastructure, and community colleges are critical stepping stones. The mediation analysis suggests about 30% of the wealth inequality-mobility link can be explained by differences in community college attendance. The mechanism likely works through multiple pathways: property taxes fund local schools, so wealthier areas attract better services; high-wealth households can monopolise opportunities and drive up costs (e.g. skyrocketing university fees); and wealth inequality simply amplifies economic disparities more than income inequality does.

The spatial patterns are telling. Upward mobility is lowest across the South, particularly in the cotton belt, and highest in the Midwest. Wealth inequality shows roughly the inverse pattern. The negative association between local wealth inequality and mobility holds up across a battery of robustness checks, including controlling for racial segregation, restricting the sample to white children only, and using alternative mobility measures. One limitation worth noting is that the wealth inequality data is from 2000, matching when children appeared on their parents’ tax returns during early adolescence. Models using wealth inequality measured before the children were born or when they reached their 30s show no association with mobility, suggesting the timing of exposure during childhood really does matter.

You can access the code here.

2. Global farm sizes could triple by 2100

A new study published in Nature Communications introduces an interesting way to think about farm sizes. Instead of just measuring the physical area of farms (which typically relies on satellite imagery), the authors use what they call ‘socio-economic farm size’ (SFS). This is essentially the total agricultural land area divided by the number of farms. They argue this is an important distinction because two regions with identical physical farm sizes can have vastly different SFS values depending on rural population density and labour availability.

The historical trends are pretty interesting. Between 1970 and 2000, global average SFS actually declined by about 15%, but then reversed course, increasing by 14% from 2000 to 2020. High-income regions like Europe, North America, and Oceania saw exponential growth in farm sizes over recent decades (with SFS roughly doubling in Europe and North America since 1970), driven by early urbanisation and mechanisation. Meanwhile, regions like India and Sub-Saharan Africa experienced the opposite: farm sizes shrank as population pressures and policies like India’s Land Ceiling Act preserved smallholder economies. China’s an interesting case too. SFS started expanding after 2000, but remains relatively small due to the Household Contract Responsibility System, which created structural fragmentation by dividing land into small, non-tradable plots.

Looking ahead, the projections are dramatic. Under a middle-of-the-road socioeconomic scenario (SSP2), global average SFS could triple by 2100, jumping from about 70 hectares in 2020 to over 300 hectares. Latin America and North America are projected to see the largest expansions (roughly six-fold increases), while Asia and Sub-Saharan Africa would see more modest growth (around 2.4 times current sizes). The main driver is declining rural populations combined with continued urbanisation. African countries like Kenya, Mali, and Nigeria could see their farm sizes start expanding around 2060 as demographic transitions take hold. Of course, these projections come with a bunch of uncertainty. Policy interventions, land reforms, and market dynamics could all alter these trajectories in ways the model doesn’t capture.

You can access the data and code here.

3. A survey of multimodal geospatial foundation models

It’s pretty difficult to go a week in the geospatial space without discussing foundation models. This week is no exception. A new survey provides a comprehensive look at how these models are evolving to handle multiple data types simultaneously. The key insight here is that different remote sensing modalities (optical RGB, SAR, hyperspectral, LiDAR, and text) each have distinct physical properties that fundamentally shape how models need to be designed. E.g., combining optical imagery with SAR is particularly challenging because they have completely different imaging mechanisms, leading to big differences in spatial structures and texture features. Meanwhile, hyperspectral data brings its own headaches. You’re dealing with tens to hundreds of spectral bands compared to just three in standard RGB imagery, which creates issues around spectral redundancy and noise sensitivity.

The survey reveals some interesting patterns in how well these models actually perform. Vision-language models are obviously emerging as the most promising direction, with natural language serving as a sort of semantic bridge for human-machine interaction. Models like RS-MoE use dynamic task-specific prompts to guide multiple lightweight language model experts, enabling specialised parallel processing of diverse tasks like image captioning and visual question answering. But there’s no single model that dominates across all tasks. Instead, different architectures excel at different things. GeoRSCLIP performs well on image-text retrieval thanks to fine-tuning on linguistically diverse datasets, while EarthGPT’s multi-scale visual perception module gives it an edge on visual grounding tasks that require fine-grained spatial understanding.

The practical applications are already pretty impressive, ranging from precision agriculture to disaster response. One notable example is how researchers have used these models for global-scale tree mapping across the Sahara and Sahel, which helps develop our understanding of land degradation and carbon sinks. For disaster monitoring, new approaches are enabling near-real-time building damage estimation by integrating multiple data sources. But the authors are candid about the challenges that remain: most state-of-the-art models are trained end-to-end with limited interpretability, which is a real problem when you’re making high-stakes decisions about things like climate policy or emergency response.

4. Fusing OCO and ICOS data for high-res CO₂ maps

Monitoring CO2 emissions at the local level can be pretty tricky. Local authorities often rely on national-level data or extrapolations from limited ground measurements, which makes it hard to pinpoint specific emission sources or design targeted climate strategies. A new study published in Scientific Reports tackles this by fusing satellite data from NASA’s Orbiting Carbon Observatories (OCO-2 and OCO-3) with ground-level observations from the Integrated Carbon Observation System (ICOS) network and ERA5 weather data. The authors trained a bunch of machine learning models to predict ground-level CO2 from satellite measurements, with a multilayer perceptron neural network achieving the best results: an RMSE of 3.58 ppm and an adjusted R² of over 80%. That’s a pretty solid improvement over a baseline model using satellite data alone (RMSE of 6.21 ppm).

The interesting bit is that the model’s input features come entirely from satellite and reanalysis data, meaning predictions aren’t confined to locations with ground stations. Obviously, this can be an issue since reanalysis data is itself modelled data. In any case, the authors are able to generate high-resolution CO2 maps across Europe and even at the municipal level in southern Sweden. Their SHAP analysis reveals that the satellite-derived column CO2 measurement is the most important predictor, followed by temperature variables (which serve as proxies for vertical CO2 movement) and spatiotemporal information. To fill in gaps where satellite coverage is sparse, they use a weighted K-nearest neighbour interpolation that balances smoothness against local detail.

There are limitations worth noting. The ICOS stations used for training are mostly in rural European locations, so the model may not generalise well to urban or industrial areas, or to other continents. OCO satellites also have uneven coverage, with fewer observations near the poles and during winter months. The authors are upfront that predictions outside Europe can’t be verified without additional ground truth data. Still, for European applications using yearly or multi-year averages, this approach offers a promising way to identify emission hotspots, track changes over time, and support local climate action without needing expensive new monitoring infrastructure.

Geospatial Datasets

1. Forest carbon estimates dataset

This dataset produces fine-scale estimates of forest carbon status, trends, and change. It provides annual county-level forest carbon estimates over 14 years. You can access the data here.

2. Environmental discussions on Twitter (X?)

This dataset captures how environmental issues are discussed on Twitter, drawing on posts from 200,000 users who follow major environmental NGOs across multiple countries. It includes geo-referenced measures of issue prominence across the coterminous United States, showing how topics like decarbonisation or species conservation vary across states and often align with county-level political ideology. The release contains processed data, issue-intensity tables, user tweet IDs, and full reproduction code for the study’s analyses. You can access the data here.

3. Geodiversity dataset

This new geodiversity dataset offers a comprehensive view of Europe’s non-living natural diversity, spanning 78 geological, pedological, geomorphological and hydrological features. It’s available at 1-km and 10-km resolution. You can access the data here.

4. Climate simulations dataset

This dataset offers 9 km resolution climate data, indicators, and impact variables for Austria, produced through the DISTENDER project’s first round of Dynamical DownScaling using the ICON-CLM model driven by EC-Earth3-Veg. It includes simulations for 2011–2020 (historical) and 2041–2050 (future scenarios), based on the GLOBCover-2009 land-use dataset. It was released as part of the EU-funded DISTENDER initiative.

Other useful bits

• Google has launched WeatherNext 2: a faster, higher-resolution AI weather model that can generate hundreds of realistic forecast scenarios in under a minute. The new system now powers forecasts across Google products and is available in Earth Engine, BigQuery, and Vertex AI.

• A new World Bank study shows how AI and synthetic data can help track how research datasets are cited, even when references appear in wildly different forms. By expanding small annotated samples into richer training sets, the approach improves model generalisation. It reveals gaps in how data are used, offering a scalable way to understand the flow of knowledge across disciplines.

• ESA have conducted a study to highlight how satellites can play a central role in climate adaptation: monitoring hazards, ecosystems, agriculture, and health with consistent, decades-long global data. By feeding directly into the Paris Agreement’s adaptation goals, they argue that Earth observation offers a useful way to measure whether resilience efforts are working and where support is most needed. But then again, since you’re here, you probably knew this already…

• A new global crustal stress map has doubled the number of measurements since 2016, revealing where Earth’s crust is most strained, and where faults may be closest to failing. Built from 100,000+ data points, it sharpens earthquake risk assessments and guides safer drilling, geothermal projects, and carbon storage by showing how stress varies from continental scales down to surprising local rotations.

Jobs

• International Water Management Institute (IWMI) is looking for a remote Consultant

• Mapbox is looking for a Software Development Engineer II based in the United Kingdom

• Janaagraha Centre for Citizenship and Democracy is looking for a Associate - Data Science based in Bengaluru, India

Just for Fun

An image of the moon from Turkey last month.

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 almost as niche as GeoDA. 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:

• Forest Warming: Albedo effects can cancel out carbon storage.

• Vegetation Loss: New system tracks global land changes daily.

• Crop Mapping: AI models use rotation logic for better accuracy.

• Mapping Favelas: Specialized satellite AI outperforms generic models.

• New Google Tools: AI models map deforestation and identify wildlife.

Subscribe now

Research you should know about

1. We’re miscalculating the value of forests

It’s easy to view planting trees as a guaranteed win for the climate because they suck up carbon. But a new study in Nature Communications reveals a blind spot in the Voluntary Carbon Market regarding surface albedo. When we plant dark forests over lighter landscapes like snowy fields or grasslands, the land absorbs more sunlight and heats up. This effect can reduce or even cancel out the cooling benefits of the carbon sequestration. The researchers analysed 172 existing reforestation projects to see if our current accounting methods are actually adding up.

The results are pretty crazy. They found that for over 10% of the projects analysed, the warming caused by the albedo effect entirely negates the climate benefits of the carbon storage. In other words, these projects might actually be warming the planet rather than cooling it. Furthermore, about a quarter of the projects occur in locations where albedo changes wipe out at least half of the mitigation benefit. It isn’t all bad news though. The study found that 9% of projects, mostly in tropical and subtropical areas, actually boost climate mitigation because the new vegetation reflects more sunlight than what was there before.

Right now, carbon market protocols generally ignore these biophysical factors. To fix this, the authors propose a tiered framework for integrating albedo into carbon accounting. This ranges from simple project planning adjustments to strict ineligibility thresholds for sites where the albedo penalty is too high. If we implemented a rule where projects losing more than 50% of their benefit to albedo were ineligible, we would significantly improve the integrity of the market. This approach ensures we prioritise projects that deliver real cooling outcomes rather than just counting trees.

You can access the code here.

2. Some new insights on global vegetation loss

We often struggle to track land cover changes in real time due to cloud cover and long gaps between satellite passes. A new system called DIST-ALERT aims to solve this by leveraging the Harmonized Landsat Sentinel-2 (HLS) dataset. This combines data from NASA and USGS Landsat 8/9 with ESA Sentinel-2 satellites to create a unified 30-metre resolution time series. By blending these sources, the system achieves a revisit rate of just 1 to 4 days globally. It works by comparing every new pixel observation against a rolling baseline of the previous three years within a 31-day seasonal window. This allows the system to flag anomalies almost immediately, detecting everything from logging and mining to insect damage and landslides without waiting for annual composites.

The data from 2023 reveals the massive scale of these shifts:

• Direct human activities, such as agricultural expansion and urbanisation, converted 28.6 million hectares (Mha) of land in a single year.

• Fires that resulted in permanent land cover conversion accounted for an additional 14.9 Mha.

When combined, these dynamics impacted approximately 0.3% of the global land surface, which is roughly equivalent to the entire area of California. It’s also interesting to see that natural variations, such as drought and green-up events, actually constituted the largest share of change, representing more than two-thirds of all identified anomalies (1371 Mha).

To capture these changes accurately, DIST-ALERT employs two parallel algorithms.

1. To map vegetation cover for every observation and flags losses relative to the baseline minimum

2. To identify generic spectral anomalies where reflectance falls outside typical historical distributions.

This dual approach proves pretty effective, with validation results showing that high-confidence vegetation loss alerts achieved a user accuracy of 94.2%. While the system captures forest loss and agricultural shifts with high precision, it’s naturally less sensitive to changes in urban environments where structural damage might not significantly alter the spectral signal at a 30-metre resolution.

You can access the code here.

3. A smarter way to map crops over time

It’s now kind of standard practice to use deep learning to classify crop types from satellite imagery, but these models often treat each year as an isolated event. That’s a bit of an oversight because agriculture follows specific rules. Farmers rarely plant crops at random. Instead, they follow rotation cycles where one crop naturally follows another to maintain soil health. A new study from the University of Trento tackles this limitation by combining Deep Learning with Bayesian modelling to capture these long-term patterns.

The researchers propose a ‘cascade classification’ approach that mixes two distinct methods. First, they use a Transformer Encoder to analyse the raw spectral data from Sentinel-2 images. Then, they layer a Hidden Markov Model (HMM) on top of that. The HMM acts as a logic check by calculating the probability of one crop type following another. It essentially looks at the sequence of labels to ensure the transition from year to year makes agronomic sense rather than just guessing based on the spectral signature of a single season.

They tested this setup on a massive dataset in Austria covering 47 different crop types over six years. The results showed that adding the HMM layer boosted accuracy pretty clearly compared to using the Transformer model on its own. By enforcing temporal consistency, the model avoided making unlikely predictions for crop rotations. This suggests that future mapping efforts need to look at the full timeline of the land to get the best results.

4. Turns out bigger isn’t always better for mapping model

Mapping informal settlements like Rio de Janeiro’s favelas can be a massive headache because they develop so rapidly and unpredictably. Traditional field surveys are far too slow and older automated techniques usually require complex manual tweaking. That’s why researchers are increasingly turning to deep learning to do the heavy lifting. A new study investigates whether it’s better to use massive, general-purpose AI models or ones built specifically for satellite imagery to spot these areas.

The team compared two distinct approaches using data from Rio. They tested generic networks trained on huge internet databases like ImageNet which contain millions of everyday photos. They pitched these against CROMA, a Remote Sensing Foundation Model (RSFM) trained on a smaller but more relevant set of satellite images (if you’re wondering what a foundation model is, then check this out). They divided the city into 150m grids and fed these into the models to see which could better distinguish favelas from formal city structures.

The results were pretty clear. The satellite-specific model, CROMA, beat the generic ones with an F1-score of 0.81 compared to 0.72. It turns out that specific training on aerial views is more valuable than simply having a massive volume of training data. This is a promising sign for using these specialised foundation models to map informal settlements globally since they handle the unique textures and patterns of satellite imagery much better than models trained on standard photos.

Geospatial Datasets

1. Particle number concentrations map

This new global dataset provides the first 1-km resolution maps of particle number concentrations (PNC) and ultrafine particles (UFPs) worldwide, covering annual averages from 2010–2019. You can access the data here and the code here.

2. Global natural forest map

This 10 m resolution natural forest map for 2020 offers a high-quality baseline for monitoring deforestation and degradation across tropical, temperate, and boreal regions.

3. Gridded combustible mass estimates

COMBUST provides a first-of-its-kind, gridded estimate of the combustible mass of the built environment across the conterminous United States from 1975–2020, mapped at 250 m resolution. The dataset includes historical backcasts, material-specific layers, and a companion product (COMBUST Plus) for analysing exposure of buildings, population, and biomass. You can access the data here.

Other useful bits

• Google is rolling out new AI tools to help protect nature, including a high-resolution deforestation risk model, large-scale species range mapping using graph neural networks, and an upgraded bioacoustics model, Perch 2.0, for identifying wildlife from sound.

  

• Europe’s new Copernicus Sentinel-4 mission has released its first images, providing hourly, continent-wide views of key air pollutants from a geostationary orbit. These early results already show clear hotspots of NO₂, ozone, and SO₂, a major step toward faster, more precise air-quality forecasts and health warnings across Europe.

  

• The World Bank’s latest subnational poverty data reveals pretty big contrasts within countries, showing clear “movers” where poverty has fallen and “stayers” where it has barely shifted. By pairing poverty rates with new prosperity gap measures, the update highlights how far households are from secure, middle-class living standards.

Jobs

• WorldPop is looking for a Research Fellow in Evaluation and Impact, based in the UK.

• Save the Children is looking for a GIS specialist in Nigeria.

• The Rainforest Alliance is looking for a Senior Associate in Deforestation Risk Monitoring in Cameroon.

Just for Fun

Google is exploring space-based AI data centres. They’re proposing constellations of solar-powered satellites that could run AI models using abundant orbital energy while reducing pressure on land and water resources on Earth. Under Project Suncatcher, the first prototypes are planned for 2027.

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 support group for the geospatially-curious. 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:

• LLMs and Earth Data: Can agents analyse satellite imagery.

• Walkability Emotions: Attachment to neighbourhood shapes walking.

• Disaster Detection: Training-free model runs directly in orbit.

• Energy Cooperation: Coordinated grids cut clean power costs.

• Roman Roads: Most detailed digital network of the empire.

Subscribe now

Research you should know about

1. Can we use LLMs to analyse satellite images?

Say you want to figure out how many days last year saw more than 25% of Chicago experiencing surface temperatures above 300K, using Landsat 8 data. That’s not something you can answer by just looking at a satellite image. You need to download the right data, calculate brightness temperatures, apply thresholds across hundreds of images, and aggregate the results. Current multimodal LLMs can describe what’s in a single image, but they can’t actually do this kind of multi-step quantitative analysis. Earth-Agent, introduced in a new study, tackles this by turning the LLM into a controller rather than a doer. Instead of trying to process the data itself, the model decides which specialised tool to call at each step, like calculating NDVI, estimating land surface temperature, or running change detection algorithms. The framework includes 104 domain-specific tools that handle the actual computation, while the LLM figures out the sequence of steps needed to answer the question.

To test how well this actually works, the researchers created Earth-Bench, a dataset of 248 expert-curated problems that require an average of 5.4 reasoning steps to solve. Unlike existing benchmarks that focus on simple perceptual tasks with single images, Earth-Bench includes problems across three modalities (raw spectral data, processed Earth products, and RGB imagery) and demands genuine quantitative analysis. The results are pretty interesting. Even the best-performing models like GPT-5 and DeepSeek-V3.1 only achieve around 50 to 65% accuracy on the final answers. What’s particularly surprising is that models are pretty good at identifying which tools they need to use, but they struggle with executing the exact sequence correctly and getting the parameters right.

The framework does show clear advantages over both general-purpose agents and existing multimodal LLMs though. General agents like those from OpenAI or Coze completely fail on certain modalities (some couldn’t complete a single RGB task), while Earth-Agent with GPT-5 achieves 55.8% accuracy across all modalities. When compared to remote sensing-specific models like LHRS-Bot or VHM on tasks like classification and object detection, Earth-Agent outperforms them substantially. So who knows, this might be yet another step in the ongoing quest to derive insights from satellite images using only natural language.

You can access the data here and the code here. More info on their project page.

2. The emotional side of walkability

The research is in. Urban design isn’t just about streets and sidewalks. It’s about how people feel about where they live. As someone who’s spent a couple of years living in the densest city in the world, I can attest to this… Anyway, a study published in Scientific Reports looks at whether feeling attached to your neighbourhood actually makes you walk more. The researchers surveyed over 2,000 adults in Calgary, Canada, measuring two types of place attachment:

1. place identity (the emotional bond you have with your neighbourhood) and

2. place dependence (how much you rely on it for activities).

They then matched this data with objective neighbourhood walkability, categorising areas by street pattern into grid (high walkability), warped grid (medium), and curvilinear (low walkability). The results show that both place identity and place dependence are positively associated with walking for transportation and recreation, regardless of neighbourhood type. People with stronger attachment to their neighbourhood were more likely to hit the recommended 150 minutes per week of walking and walked more frequently overall.

The really interesting bit is how neighbourhood design modifies these relationships. The associations between place attachment and walking were strongest in grid neighbourhoods (those with high connectivity, mixed land use, and lots of destinations). For instance, the link between place identity and sufficient recreational walking was strongest in grid neighbourhoods (OR 1.82), followed by curvilinear (OR 1.58), with no significant association in warped grid areas. One surprising finding: place dependence had its strongest association with sufficient transportation walking in curvilinear (low walkability) neighbourhoods (OR 1.92), suggesting that people in car-oriented suburbs need a particularly strong attachment to their area to overcome built environment barriers and still walk for transport.

Grid neighbourhoods, with their high pedestrian connectivity and destination density, seem to amplify the walking benefits of place attachment. But even in less walkable areas, stronger emotional and functional connections to the neighbourhood can encourage more walking.

3. Training-free AI for disaster detection in orbit

One of the biggest bottlenecks in using satellite imagery for disaster response is getting the data from space down to Earth. There’s limited bandwidth, and you can’t just beam everything down instantly. So researchers are increasingly interested in processing data on-board the satellite itself, prioritising the most important stuff for downlinking. The problem, though is that most AI models require massive computational resources for training, which you simply don’t have on a satellite. A new study published in Scientific Reports introduces something called a Physics Aware Neuromorphic Network (PANN) that sidesteps this entirely. It’s a training-free model that can detect changes caused by natural disasters in satellite imagery without ever needing traditional ground-based training.

The PANN is inspired by physical neural networks made of memristors (basically resistors with memory). Unlike conventional deep learning models where weights are trained through computationally expensive backpropagation, the PANN’s weights continuously update in response to new inputs according to physical laws. So instead of pre-training the model on the ground and then uploading it to the satellite, the PANN actively learns as new images come in from the sensor. The researchers tested it on Sentinel-2 imagery covering four types of natural disasters: fires, floods, hurricanes and landslides. For each disaster event, the model takes a sequence of five images (four before, one after) and produces a change map highlighting affected regions.

The results are pretty impressive. When benchmarked against RaVAEn (a state-of-the-art model specifically designed for on-board satellite use), the PANN achieved comparable or better performance across all disaster categories. It was especially strong for floods, scoring 14% higher than RaVAEn. The model also generalised reasonably well when tested on LandSat-8 data, despite never being trained on it. The whole thing runs on CPUs with about 1GB of memory, processing a 25 km² region in around 19 seconds. Since there’s no training overhead, you avoid the usual cycle of downlinking data, retraining models on the ground, and uplinking updated versions.

The code is available here and the data used to train the model is here.

4. Turns out sharing power grids is three times cheaper

A new study in Nature Communications looks at whether South American countries would be better off coordinating their electricity grids as they transition to low-carbon systems. The researchers used an optimisation model to simulate 80 different future scenarios for five countries (Argentina, Brazil, Chile, Paraguay, and Uruguay) under various technology assumptions and emissions targets. The headline finding is pretty nuts: achieving a 90% cut in electricity emissions by 2050 is totally doable with only modest cost increases (around 5 to 18%), and these costs drop substantially when countries coordinate their grids rather than planning independently. The study finds that limiting coordination forces countries to overbuild generation capacity, costing over three times more than simply expanding cross-border transmission lines (14.7 to 22.8 billion USD versus 3.5 to 7.0 billion USD).

The main reason coordination works so well comes down to complementary resources and grid balancing. Chile has excellent solar potential but struggles with nighttime power needs, while Argentina has strong wind resources and natural gas for backup. Under full coordination, Chile can import wind and hydropower from Argentina at night instead of installing its own (lower quality) wind turbines or relying heavily on battery storage. This kind of trade smooths out the daily and seasonal swings of intermittent renewables across the region. The model shows that coordinated scenarios actually deploy less total wind capacity but generate more wind power, because they’re cherry-picking only the highest quality sites rather than each country building suboptimal projects domestically.

The benefits don’t distribute evenly across countries though. Argentina and Paraguay emerge as net exporters (mainly wind and hydropower), while Brazil becomes increasingly reliant on imports to meet its growing demand. Paraguay continues its historical role exporting hydropower to Brazil, while Argentina’s central position and mix of wind and gas makes it crucial for balancing the regional grid. Chile’s pathway shifts dramatically depending on coordination: under limited coordination, it must build domestic wind capacity to complement its solar; under full coordination, it focuses purely on solar while importing power for nighttime needs. Clearly this creates energy interdependence risks, and political and institutional barriers aren’t modelled here. But for regions with geographically variable renewable resources, the economic case for coordination looks compelling.

Geospatial Datasets

1. Crop yield impact dataset

This new Human Climate Horizons (HCH) dataset provides high-resolution global projections of climate-driven changes in agricultural yields for six staple crops across 19,000+ subnational regions. You can access the data via the HCH data platform.

2. Human footprint map

HIBR-10 is a new 10-m resolution human footprint map for all of Brazil, designed to match the fine spatial scales at which species like primates actually use their habitats. It combines Sentinel-2 land cover, Microsoft building footprints, transport networks and waterways into a single human impact index across 86.5 billion grid cells. You can access the data and code here.

3. Building morphology dataset

The Gauntlet dataset provides a rich set of 65 building-morphology features for more than 131 million structures across the United States. It’s derived from FEMA’s USA Structures footprints dataset. You can access the data here and the code here.

4. Roman Empire road dataset

You Roman map fetishists are in for a treat. Itiner-e is the most comprehensive and spatially detailed digital dataset of Roman roads ever created. Each road segment is digitised at high resolution using archaeological evidence, historical maps, milestones, remote sensing and topographic data, and tagged with certainty levels. You can access the data and code here.

Other useful bits

• NASA’s ECOSTRESS mission has produced the first detailed map of Los Angeles’ street-level temperatures, using 10-metre thermal data collected from the ISS. The work is now helping the LA28 Olympics team plan heat-mitigation strategies for venues and transport routes.

• Google Maps is adding Gemini as a conversational “copilot”, letting users ask natural language questions about routes, nearby places, and landmarks directly within the app.

• A new global satellite survey of 151 waste sites shows that methane emissions are far more uncertain than existing reports suggest, with little correlation between satellite-based estimates and official figures. The study also finds that unmanaged dumps emit far more methane per area than managed landfills, highlighting how high-resolution satellites can guide more accurate monitoring and targeted mitigation.

Jobs

• UNEP’s International Methane Emissions Observatory (IMEO) is looking for a Lead Developer for their data platform based in Paris.

• UNOPS is looking for a Data Scientist based in Luxembourg.

• West Virginia University is looking for a Teaching Assistant Professor of Forensic GIS at their Department of Geology and Geography.

• Esri is looking for a Global Operations Sustainability Intern based in Redlands.

Just for Fun

Scientists are rushing to study 3I/ATLAS, only the third known interstellar object to pass through our solar system, as it speeds past the Sun and towards its closest approach to Earth. Observatories and spacecraft from Hubble to Perseverance are tracking the comet to understand its size, composition, and origins.

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