Colombia 2026 Earthquake Pereira (Extended)
Published by Microsoft AI for Good Lab
About this dataset
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.