LA Fires - Palisades fire January 2025: Building Damage Assessment

Microsoft AI for Good Lab ran their damage assessment AI models on images provided by Planet and have mapped out the affected buildings in Sumatra, Indonesia.

Microsoft AI for Good Lab ran their damage assessment AI models for the La Guiara Coastline - 26,142.

Microsoft AI for Good Lab ran their damage assessment AI models in East Catia La Mar covering 24,732 buildings.

Date of Image(s): January 9, 2025, January 13, 2025, January 21, 2025 Summary: This raster dataset (TIF) represents likely damaged/destroyed urban areas in Los Angeles, California, during the fires of January 2025. The map is the result of a coherent change detection analysis of interferometric Sentinel-1 radar (InSAR) images from January 2025 in comparison with pre-disaster reference images from 2022-2025. Coherent change detection analysis is used to show change across the entire domain, which includes vegetation and forested areas. This analysis is constrained to a snapshot of the FIRIS perimeter domain to highlight the damage to built up areas only. Potentially damaged areas denoted in orange represent data collected on January 9, 2025 from a Sentinel-1 pass over the Altadena/Eaton area. Potentially damaged areas denoted in red represent data collected on January 13, 2025 from a Sentinel-1 pass over the Palisades area. Potentially damaged structures denoted in red represent data collected on January 21, 2025. Date(s) and time(s) covered: Swaths from 9 January 2025, 14 January 2025, and January 21, 2025, with 188 images collected from 2022-12-20 to 2025-01-02 for a pre-disaster reference dataset. Suggested Usage: The map is meant for landscape-level geospatial overlay and visualization purposes of fire damage in urban/built-up regions. For example, the map is useful for tabulating estimates of the number of likely damaged or destroyed structures. Pixel values of 1 represent a region likely damaged or destroyed; pixel values of 0 represent all other regions. Satellite/Sensor: European Space Agency Copernicus Sentinel-1/10 meter spatial resolution processed to 40 meters for interferometric coherence change analysis Resolution: 40 meters Credits: Damage analysis of Copernicus Sentinel-1 satellite data by Corey Scher of CUNY Graduate Center and Jamon Van Den Hoek of Oregon State University. Contact: Jamon Van Den Hoek (jamon.vandenhoek@oregonstate.edu). Data sources: Sentinel-1 https://asf.alaska.edu/datasets/daac/sentinel-1/ Alaska Satellite Facility https://hyp3-docs.asf.alaska.edu/usage_guidelines/ CA Perimeters NIFC FIRIS data (gis.data.cnra.ca.gov/datasets/CALFIRE-Forestry::ca-perimeters-nifc-firis-public-view/) Access and Use Constraints: Likely Damaged Areas: The damage map has not been field-validated and omission/commission errors are likely present. Regions that changed over the course of the reference period or were otherwise dynamic (such as places of construction or destruction or vegetated areas) are likely excluded from the analysis. Service URL: https://gis.earthdata.nasa.gov/portal/home/item.html?id=f8faeec910c74ef8a32f95838ddf0bdc WMS Endpoint: https://gis.earthdata.nasa.gov/portal/services/DISASTERS_202501_FIRE_CA/2501_sentinel1_dmg/ImageServer/WMSServer

Following the June 2026 earthquakes that struck the central coast of Venezuela, the Microsoft AI for Good Lab ran their building damage assessment AI models to map and classify the buildings affected by the earthquakes. The models were applied to satellite imagery captured on 25 and 26 June 2026, producing building footprints with predicted damage across the affected areas of Catia La Mar, La Guaira, and Caraballeda. For each assessed area, the collection provides a reference area map, a valid-area mask describing the extent of the analysis, and a GeoPackage of predicted building damage footprints. This collection mirrors the dataset published on the Humanitarian Data Exchange (HDX) by the Microsoft AI for Good Lab and made available under the Creative Commons Attribution 4.0 International (CC-BY-4.0) license. ## Methodology The Microsoft AI for Good Lab ran their damage assessment AI models on satellite images taken 25 and 26 June 2026 and have mapped out the affected buildings. ## Disclaimer This analysis represents a portion of the damage from the earthquake; other damage in the region is not included in this assessment. While these insights offer a valuable initial overview, they remain preliminary and require on-the-ground verification for a comprehensive understanding of the damage. ## Caveats Please note that the source imagery has orthorectification quality issues, which may cause building footprints to be misaligned with existing basemaps.

Microsoft AI for Good Lab ran their damage assessment AI models in La Guaria.