IBM, ESA open-source AI models to analyze weather

IBM Research in Europe and the European Space Agency (ESA) have open-sourced new datasets which use satellite images and artificial intelligence (AI) to improve preparation and response to natural disasters like floods and wildfires.

Recent floods in Mozambique and Kenya are among hundreds of the extreme weather events captured in the global, multi-modal dataset called ImpactMesh.

The dataset is multi-temporal, meaning it features before-and-after snapshots of flooded or fire-scorched areas. The footage was captured by the Copernicus Sentinel-1 and Sentinel-2 satellites over the last decade on their orbits around Earth.

To provide a clearer picture of landscape-level changes, each of the extreme events in the dataset is represented by three types of observations – optical images, radar images and an elevation map of the impacted area.

When storm clouds and smoky fires block optical sensors from seeing the extent of flood and wildfires from space, radar images and the altitude of the…