Spatial Intelligence in Climate Change Research

🌊 AI keeping a sharp eye on our restless coasts 🌍 Beach erosion threatens lives and livelihoods—storms hit harder, seas keep rising, and floods loom larger. What if spatial intelligence could shift the tide for coastal resilience? Our team’s been tackling this head-on, using smart tech and fieldwork to protect vulnerable shores, like the beachfront near San Juan International Airport, the Caribbean’s biggest travel hub. We’ve built a new way to monitor coasts that’s precise and practical. With tools like the Segment Anything Model (SAM), we map water-land boundaries clearly, handling challenges like distorted images or changing light. Add Dynamic Mode Decomposition (DMD) to spot patterns and monoplotting with DEM for accurate terrain mapping, and you’ve got a system that changes the game. Want the full story? Check out our paper, An Integrative Framework for AI-Supported Coastal Hydrodynamics Monitoring and Analysis. It’s about equipping coastal communities—especially those with limited resources—to stand stronger against climate threats. 📍 What’s your take—how can spatial tech reshape coastal resilience? #ClimateChange #CoastalResilience #SpatialIntelligence #AI #EnvironmentalMonitoring #Innovation 🔗 https://lnkd.in/evJmdSkz Thanks for all the teamwork Gustavo Pacheco-Crosetti, @Christian Villalta Calderon, Emily Smyth, and Joel Cohen Vazquez

This is a fantastic example of modern geospatial analytics in action. A new paper from Andreas Christen and the team at the University of Freiburg demonstrates how AI can help cities balance two competing goals: urban densification and heat mitigation. The real power here lies in the orchestration of multiple complex datasets to drive actionable insights. The study didn't just map temperature; it fused LiDAR point clouds, 3D semantic city models, and historical weather data into a unified AI workflow. Instead of traditional, computationally expensive physical simulations, they used AI models to rapidly predict "thermal comfort" at a hyper-local scale. This allows for: - Data Fusion: distinct datasets (geometry, vegetation, climate) working together. - Prescriptive Analytics: Moving beyond descriptive maps to automated optimization identifying exactly where to plant trees or place buildings for maximum cooling. It’s a glimpse into the future of urban planning, where geospatial data and AI doesn't just describe the problem, but actively designs the solution. Congrats to the team and great paper/read! Read the paper here: https://lnkd.in/eqBCym9Z 🌎 I'm Matt Forrest and I talk about modern GIS, earth observation, AI, and how geospatial is changing. 📬 Want more like this? Join 12k+ others learning from my daily newsletter → forrest.nyc

NASA just trained a 3 billion parameter model on 100 million MODIS satellite images. Google released foundation models that reason across geospatial datasets. Yet most institutional investors still use Excel to assess physical climate risk. I met with a CRO of a $200B AUM fund last week. They were proud of their "advanced" climate risk system. It was a spreadsheet with color-coded cells. This gap between new technology and status quo is where revenue opportunity lives. Today's geospatial foundation models don't just find patterns. They understand causality across space and time. SatVision-TOA can predict the shape of objects in cloud-obscured images with 93% accuracy while spotting features for deeper analysis. Let's explore what this means for institutional investors: 1. Risk assessment is becoming multi-dimensional - models understand how risks compound across variables - demographic shifts, infrastructure resilience, economic activity, and climate patterns. 2. The speed of insight has accelerated exponentially - What used to take months of analysis can now be generated in minutes. 3. Power is now the only constraint, and space infra investment is now viable - Space solar power, orbital data centers, in-orbit manufacturing: geospatial AI can model the terrestrial economic impacts of these technologies years before deployment. (I've watched portfolio managers' eyes widen when we discussed how we can project the value of space-based solar transmission to specific grid-constrained regions) At Sust Global , we're embedding these foundation models into our geospatial AI platform. Not just layering data, but enabling true cross-domain reasoning. Last quarter, a client used our platform to identify real estate assets with both high climate resilience and proximity to emerging demographic booms. They executed a $300M allocation based on insights that didn't exist in any conventional dataset. That's the real breakthrough: finding opportunities others can't see by connecting domains others don't combine. Climate risk data can't exist in isolation. Neither can space technology. The future belongs to those who can reason across all these domains simultaneously. Curious how geospatial foundation models can unlock insights for your portfolio? Let's connect.

Comparing Flood Inundation Map Features and Diagnosing Decision Support Design Challenges -- https://lnkd.in/gZuNUJcR  <-- shared paper -- H/T Anne Jefferson “The increasing frequency and intensity of hydrometeorological events such as floods driven by climate change necessitate reliable, spatially explicit decision support tools like Flood Inundation Maps (FIMs). Developing effective FIMs is challenging, as varying data complexities need to be managed whilst effectively communicating forecasts and uncertainties to diverse audiences. Visualisation literature offers some empirical evidence for designing effective user-controlled decision support tools such as FIMs. Still, research and operational gaps persist, particularly with respect to whether FIMs are appropriately designed, communicated, translated, and interpreted to support effective near-term flood response decisions. [Their] study draws from research in visualisation and user-centred design literature to conduct a structured diagnostic assessment of eight (inter)national FIM forecast visualisations using independent task-based usability questionnaires and guided workshops. [They] identified challenges such as unclear key messages, inconsistent colour schemes, ambiguous symbols, unclear legends, and inefficient interface layouts, likely reducing the usability and decision support value of these eight FIMs. [They] recommend identifying product key messages; designing user interfaces around those key messages; ensuring that visual features such as colours aid heuristic decision-making and cognitive processing; and incorporating dynamic, user-controlled features to enhance usability and decision-making for technical and non-technical audiences. Finally, [they] provide evidence-informed design considerations that will improve the accessibility, interpretability, and effectiveness of FIMs as decision support tools, ultimately improving the process and outcomes of flood response decisions…” #GIS #spatial #mapping #climatechange #extremeweather #pluvial #fluvial #water #surfacewater #precipitation #flood #flooding #floodinnundation #innundation #NOAA #FIM #floodinnundationmaps #model #modeling #spatialanalysis #spatiotemporal #floodresponse #response #naturalhazard #monitoring #forecasting #forecast #visualisation #FIMAN #remotesensing #Copernicus #impactassessment #research #emergencymanagement #humanimpact #safety #publicsafety #risk #hazard #infrastructure #FloodMapper #floodwatch #flashflood FEMA | NOAA: National Oceanic & Atmospheric Administration | U.S. Geological Survey (USGS)

𝗪𝗵𝗮𝘁 𝗶𝗳 𝘆𝗼𝘂 𝗰𝗼𝘂𝗹𝗱 𝗷𝘂𝘀𝘁 𝗰𝗵𝗮𝘁 𝘄𝗶𝘁𝗵 𝘀𝗮𝘁𝗲𝗹𝗹𝗶𝘁𝗲 𝗱𝗮𝘁𝗮 𝘁𝗼 𝘂𝗻𝗰𝗼𝘃𝗲𝗿 𝗰𝗹𝗶𝗺𝗮𝘁𝗲 𝗿𝗶𝘀𝗸𝘀? 𝗡𝗼𝘄 𝘆𝗼𝘂 𝗰𝗮𝗻 𝘄𝗶𝘁𝗵 𝗙𝗦𝗤 𝗦𝗽𝗮𝘁𝗶𝗮𝗹 𝗔𝗴𝗲𝗻𝘁. The most critical climate datasets — heatwave projections, precipitation models, land surface temperature, drought indices — live as 𝗿𝗮𝘀𝘁𝗲𝗿 𝗱𝗮𝘁𝗮: dense grids of pixel values derived from satellite sensors and climate models. Turning them into actionable intelligence requires specialized GIS tooling, resampling pipelines, CRS transformations, and significant engineering overhead before joining them with contextual data like population density or land use. This friction is why climate risk analysis has historically been slow, expensive, and inaccessible outside specialist teams. 𝗙𝗦𝗤 𝗛3 𝗛𝘂𝗯 𝗰𝗵𝗮𝗻𝗴𝗲𝘀 𝘁𝗵𝗮𝘁 𝗲𝗾𝘂𝗮𝘁𝗶𝗼𝗻 𝗲𝗻𝘁𝗶𝗿𝗲𝗹𝘆. 𝗙𝗦𝗤 𝗦𝗽𝗮𝘁𝗶𝗮𝗹 𝗔𝗴𝗲𝗻𝘁 𝗽𝘂𝘁𝘀 𝗶𝘁 𝘁𝗼 𝘄𝗼𝗿𝗸. FSQ H3 Hub's proprietary indexing pipeline converts raw raster datasets into 𝗛3 𝗵𝗲𝘅𝗮𝗴𝗼𝗻𝗮𝗹 𝗰𝗲𝗹𝗹𝘀 — making satellite-derived climate data available in clean, tabular form at a consistent spatial resolution. Every dataset shares the same H3 grid, so joining a Copernicus heatwave projection with a CHELSA precipitation model, a wildfire risk layer, and population density becomes a simple SQL join on a cell ID. No resampling. No CRS headaches. No bespoke ETL. 𝗙𝗦𝗤 𝗦𝗽𝗮𝘁𝗶𝗮𝗹 𝗔𝗴𝗲𝗻𝘁, built on this foundation, lets you converse with that unified data layer to surface climate insights at scale. 𝗦𝗼 𝘄𝗲 𝗽𝘂𝘁 𝗶𝘁 𝘁𝗼 𝘁𝗵𝗲 𝘁𝗲𝘀𝘁: "Do a temporal climate risk analysis for Europe — pick an area with the most interesting future climate impacts." The agent selected 𝗔𝗻𝗱𝗮𝗹𝘂𝘀𝗶𝗮, 𝗦𝗼𝘂𝘁𝗵𝗲𝗿𝗻 𝗦𝗽𝗮𝗶𝗻 — citing Mediterranean climate sensitivity, agricultural economy, water scarcity, and dense coastal populations. It tessellated the region into 113,437 𝗛3 𝗰𝗲𝗹𝗹𝘀 at resolution 8 (~460m), drawing on five datasets spanning climate projections (Copernicus RCP 8.5, CHELSA SSP370), environmental risk (Drivers of Forest Loss), population exposure (Global Population 2020), and land use (MODIS Land Cover). 𝗪𝗵𝗮𝘁 𝘁𝗵𝗲 𝗮𝗻𝗮𝗹𝘆𝘀𝗶𝘀 𝗿𝗲𝘃𝗲𝗮𝗹𝗲𝗱: By late century, Andalusia faces a compounding climate trajectory: +23.7 heatwave days/year in extreme risk zones (32% of the region); +2.13°C average warming by 2070–2100; 53% projected "Extremely Drier" with over 600mm precipitation loss; 5,519 high-risk cells with significant population exposure; and a wildfire-climate feedback loop accelerating vegetation loss and further warming. 𝗥𝗮𝘀𝘁𝗲𝗿 𝗱𝗮𝘁𝗮 𝗮𝘁 𝘁𝗵𝗲 𝘀𝗽𝗲𝗲𝗱 𝗼𝗳 𝗶𝗻𝘀𝗶𝗴𝗵𝘁. The world's most detailed climate record is largely trapped in formats accessible only to specialists. FSQ H3 Hub and FSQ Spatial Agent change that — delivering climate risk intelligence that scales as fast as the questions you can ask. Download Foursquare 𝗦𝗽𝗮𝘁𝗶𝗮𝗹 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 to get started.

🌍 SIG GeoAI Roadtrip: Day 2 Recap – Advancing Localized GeoAI for Environmental Solutions 🚀 Another incredible day in Ecuador, where Fernanda Lopez Ornelas and I continued our deep dive into GeoAI-driven environmental solutions with Fundación EcoCiencia and FAO The conversations today highlighted the critical role of AI-powered geospatial technologies in tackling some of the region’s most pressing environmental challenges. 🔍 Key Takeaways from Day 2: 💧 Water Management & Ecosystem Services – We explored a potential initiative focused on integrating GeoAI into ecosystem service quantification for water resource management in the Amazon Basin. Discussions included embedding field classifiers, wetland mapping, and illegal mining detection to strengthen environmental monitoring. 🌱 Land Cover Monitoring & Agriculture – Our conversation with FAO centered on AI-enhanced land classification and its role in tracking land use changes, supporting national reporting efforts, and improving agricultural monitoring for food security. The integration of AI models will refine crop classification, accuracy assessments, and geospatial workflows. 🔥 Carbon Monitoring & Fire Risk Assessment – We also examined new approaches for mapping carbon stock leveraging Woodwell Climate Research Center, transitioning from MODIS to Landsat for higher-resolution assessments. These advancements are crucial for strengthening carbon sequestration models, fire monitoring, and cross-border environmental accountability. These collaborations reinforce the need to localize GeoAI applications—ensuring that cutting-edge technology is not just innovative, but actionable and tailored to meet regional needs. Excited for what’s ahead as we continue shaping a more data-driven, resilient, and sustainable future! #GeoAI #EarthObservation #CarbonMonitoring #WaterManagement #LandCoverMapping #SustainableDevelopment #SIGRoadtrip

🌾New Dataset Out 🌾 🌾 How do we make crop monitoring truly climate-aware at scale? In many EO/ML pipelines, we can model #crop dynamics reasonably well — but linking them consistently with #weather variability, drought, and #climate extremes across large geographies is still difficult. A major reason is simple: 👉 the community still lacks large-scale, multimodal, ML-ready datasets that unify satellites + climate signals + agricultural outcomes. So my PhD student Adrian Höhl (Technical University of Munich) built one. 📢 Very excited to share our new #ScientificData paper introducing #CropClimateX: a large-scale, multi-task, multi-sensory dataset for climate-aware crop monitoring in the contiguous US (2018–2022). 🔍 What makes CropClimateX different? ✅ 15,500 “minicubes” (each 12×12 km) spanning 1,527 counties ✅ Multi-source EO inputs (including Sentinel-1/2, Landsat-8, MODIS) ✅ Climate + extremes context (e.g., Daymet, U.S. Drought Monitor, heat/cold wave indicators) ✅ Supporting multi-task learning targets such as crop yield and broader crop monitoring applications To keep the dataset representative yet scalable, we use an optimized sampling strategy (Sliding Grid + Genetic Algorithm), reducing redundancy while retaining broad cropland coverage. 🚀 Why we hope this helps CropClimateX is designed to support research on: 🌱 climate-aware crop modeling 🛰️ multi-sensor fusion & spatiotemporal learning 🌍 generalizable EO foundation models for agriculture If you’re working on crop monitoring, climate resilience, or geospatial ML, take a look at CropClimateX. 🔗 Link to paper: https://lnkd.in/d3W3mnFZ 🔗 Link to dataset: https://lnkd.in/dVp4s-Mh 🔗 Link to Github: https://lnkd.in/d8DvYkMD This is a collaboration with Stella Ofori-Ampofo, Miguel Ángel Fernández Torres (Universidad Carlos III de Madrid), and Rıdvan Salih (German Aerospace Center (DLR)). The project is funded by the Deutsche Raumfahrtagentur im DLR in the framework of #ML4Earth (project page: ml4earth.de) #RemoteSensing #EarthObservation #GeospatialAI #ClimateAI #AgTech #CropMonitoring #Datasets #MachineLearning International Future AI4EO Lab, TUM School of Engineering and Design (ED)