Venezuela Earthquakes: Building Damage Assessment in Catia La Mar

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

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

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

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

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 over an extended area of Pereira. Google summary: Out of a total of 152,128 building footprints with predictions in the study area, 8,656 were fully obscured by clouds. Of the remaining 143,472 non-cloudy footprints, the model predicted that 752 (0.5%) were damaged to some extent. Overture summary: Out of a total of 77,589 building footprints with predictions in the study area, 6,582 were fully obscured by clouds. Of the remaining 71,007 non-cloudy footprints, the model predicted that 441 (0.6%) were damaged to some extent. Microsoft summary: Out of a total of 123,924 building footprints with predictions in the study area, 7,731 were fully obscured by clouds. Of the remaining 116,193 non-cloudy footprints, the model predicted that 650 (0.6%) were damaged to some extent.