Remote Sensing Data Integration

𝐓𝐞𝐫𝐫𝐚𝐅𝐌: 𝐔𝐧𝐢𝐟𝐲𝐢𝐧𝐠 𝐒𝐀𝐑 𝐚𝐧𝐝 𝐎𝐩𝐭𝐢𝐜𝐚𝐥 𝐃𝐚𝐭𝐚 𝐟𝐨𝐫 𝐄𝐚𝐫𝐭𝐡 𝐎𝐛𝐬𝐞𝐫𝐯𝐚𝐭𝐢𝐨𝐧 Current EO models face a fundamental limitation: they're often designed for single sensor types, missing the complementary information available when combining radar and optical data. This fragmentation means we can't fully leverage the wealth of satellite observations monitoring our planet. Danish et al. introduced TerraFM, a foundation model that unifies multisensor Earth observation in an unprecedented way. 𝐖𝐡𝐲 𝐭𝐡𝐢𝐬 𝐦𝐚𝐭𝐭𝐞𝐫𝐬: Earth observation data comes from diverse sensors—optical imagery captures surface details but is limited by clouds and darkness, while SAR radar penetrates clouds and works day-night but provides different information types. Many current models handle these separately, but the real world requires integrated understanding. Climate monitoring, disaster response, and agricultural assessment all benefit from fusing these complementary data streams. 𝐊𝐞𝐲 𝐢𝐧𝐧𝐨𝐯𝐚𝐭𝐢𝐨𝐧𝐬: ◦ 𝐌𝐚𝐬𝐬𝐢𝐯𝐞 𝐬𝐜𝐚𝐥𝐞 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠: Built on 18.7M global tiles from Sentinel-1 SAR and Sentinel-2 optical imagery, providing unprecedented geographic and spectral diversity ◦ 𝐋𝐚𝐫𝐠𝐞 𝐬𝐩𝐚𝐭𝐢𝐚𝐥 𝐭𝐢𝐥𝐞𝐬: Uses 534×534 pixel tiles to capture broader spatial context compared to traditional smaller patches, enabling better understanding of landscape-scale patterns ◦ 𝐌𝐨𝐝𝐚𝐥𝐢𝐭𝐲-𝐚𝐰𝐚𝐫𝐞 𝐚𝐫𝐜𝐡𝐢𝐭𝐞𝐜𝐭𝐮𝐫𝐞: Modality-specific patch embeddings handle the unique characteristics of multispectral and SAR data rather than forcing them through RGB-centric designs ◦ 𝐂𝐫𝐨𝐬𝐬-𝐚𝐭𝐭𝐞𝐧𝐭𝐢𝐨𝐧 𝐟𝐮𝐬𝐢𝐨𝐧: Dynamically aggregates information across sensors at the patch level, learning how different modalities complement each other ◦ 𝐃𝐮𝐚𝐥-𝐜𝐞𝐧𝐭𝐞𝐫𝐢𝐧𝐠: Addresses the long-tailed distribution problem in land cover data using ESA WorldCover statistics, ensuring rare classes aren't overshadowed 𝐓𝐡𝐞 𝐫𝐞𝐬𝐮𝐥𝐭𝐬: TerraFM sets new benchmarks on GEO-Bench and Copernicus-Bench, demonstrating strong generalization across geographies, modalities, and tasks, including classification, segmentation, and landslide detection. The model achieves the highest accuracy on m-EuroSat while operating at significantly lower computational cost compared to other large-scale models. 𝐁𝐢𝐠𝐠𝐞𝐫 𝐢𝐦𝐩𝐚𝐜𝐭: TerraFM represents a shift toward unified systems that can seamlessly combine different sensor types to provide more reliable insights. This approach could transform applications from precision agriculture and climate monitoring to disaster response, where the ability to integrate multiple data sources can mean the difference between accurate assessment and missed critical changes. paper: https://lnkd.in/ev_VhSPA code: https://lnkd.in/eQVYrJZV model: https://lnkd.in/eqaeD3dW #EarthObservation #FoundationModels #RemoteSensing #MachineLearning #GeospatialAI

Recently there have been lots of studies investigating the fusion of SAR and optical satellite imagery for water body and flood mapping. Unfortunately, most of these studies treat SAR images as if they are nothing but additional spectral channels of the optical images. This ignores the fact that the information content and uncertainties are very different for these two data sources. As a result, one obtains maps of surface water extent that are undefined. Is it the total surface water extent? … No, this is hardly ever the case! Or is it the union of surface water areas observable in the optical data and SAR data respectively? More likely, but only if the algorithm favors water detection over other signals, which call for troubles in other places. To address this fundamental problem, Davide Festa, Muhammed Hassaan and I have developed a physics-aware approach for fusing SAR and optical surface water data sets. This allows users of the derived data to understand its limitations, i.e. not only the extent of surface water bodies, but also areas of high uncertainty (e.g. deserts or densely vegetated terrain) and locations where water bodies cannot be observed (e.g. forests or cities). See the preprint here: Festa, D., Hassaan, M., & Wagner, W. (2026) SAR and optical imagery for dynamic global surface water monitoring: Addressing sensor-specific uncertainty for data fusion, SSRN, https://lnkd.in/d-eid9Es One important bonus effect: This approach can be used to fuse existing water body and flood datasets that reside in different data centers, i.e. there is no need to bring all optical and SAR images together on one platform. #SAR #MultiSpectral #Sentinel1 #Sentinel2 #Landsat #WaterBodies #Flood Figure(from the preprint) illustrating the fusion of Sentinel-1 (masked for dense vegetation, topography, etc.) and Sentinel-2 (masked for clouds, forests, etc.) for providing a more complete and more accurate map of surface water extent.

I’m excited to share highlights from my recent presentation during the drone school under the GEANTech on “#Hybrid #Drone‑#Satellite Systems for Advanced #Irrigation Water #Management”, where we explored how cutting‑edge remote sensing and #data‑#fusion techniques can revolutionize precision agriculture. 🔹 Why hybrid systems? By combining high‑resolution UAV imagery (RGB, multispectral & thermal) with multispectral satellite data (Sentinel‑2, Landsat), we get both the fine #spatial detail and broad #temporal coverage needed to monitor crop health and water stress at scale. 🔹 Data Fusion & AI: • #Multi‑scale fusion calibrates drone data to satellites, ensuring model consistency • #Machine #learning algorithms automate the processing of fused imagery for real‑time insights • #Decision‑support systems translate these insights into actionable irrigation schedules 🔹 Case studies: • Italian vineyards: NDVI‑derived maps guided autonomous irrigation, cutting water use by 20% while improving vine vigor • Tunisian olive groves: Targeted interventions in water‑stress zones boosted yield resilience under arid conditions 🔹 #Challenges & next steps: • Overcoming sensor‑format heterogeneity & regulatory constraints • Reducing costs for smallholder adoption • Scaling up with drone swarms, IoT integration & AI‑driven predictive models A big thank you to everyone who joined the discussion and shared valuable questions—your engagement drives innovation forward! 💧🚁🛰️ #PrecisionAgriculture #RemoteSensing #GeoAI #IrrigationInnovation #Sustainability

Advancing Flood Detection And Mapping - A Review Of Earth Observation Services, 3D Data Integration, And AI-Based Techniques -- https://lnkd.in/gnh6s4sX <-- shared paper -- https://lnkd.in/gCdZRPhG <-- shared @NASA #ARSET #tutorial / overview video (1 of 2) -- https://lnkd.in/gR56vZ9d <-- shared @NASA #ARSET #tutorial / overview video (2 of 2) -- [this post should not be considered an endorsement of a particular organisation, approach, etc] H/T Sona Guliyeva “Can we truly understand a flood… from space? When floods occur, decisions must be taken fast. Identifying flooded areas is essential, but understanding water depth and its impact on people and cities makes the real difference. Today, satellite technologies allow us to map floods almost in real time, even under clouds or at night. However, most of these observations remain two-dimensional: they capture the extent of water but often miss the third dimension: depth. This is where the challenge (and opportunity) lies. We can move beyond simple flood mapping by bringing together:  🛰️ Earth Observation data   🗺️ 3D terrain information   🤖 Artificial Intelligence This integration enables a deeper and more dynamic understanding of floods - delivering insights that are faster, more precise, and actionable for both emergency response and long-term planning. Still, important gaps remain, from data availability to model reliability across different contexts, and the need to better handle uncertainty. These challenges and opportunities are at the core of this paper… which reviews how EO, 3D data, and AI are converging to advance flood detection and mapping. #review #EarthObservation #FloodMapping #RemoteSensing #AI #Geospatial #DisasterRisk #ClimateChange #flood #flooding #satellite #model #modeling #depth #volume #risk #hazard #evaluation #GIS #spatial #mapping #detection #3D #terrain #elevation #landscape #hydrogeomorphology #integration #satellite #emergency #response #planning #management #extremeweather #DisasterRisk #ClimateChange #GIS #spatial #mapping Space It Up!