Google Research said on March 12, 2026 that it is rolling out urban flash flood forecasts with up to 24 hours of advance notice. The system uses a Groundsource dataset built from public reports and extends Google’s flood coverage beyond river flooding toward rapid-onset urban disasters.
On March 12, 2026, Google introduced Groundsource, a Gemini-powered method that converted public reports and Google Maps signals into a dataset covering more than 2.6 million historical flood events across 150 countries. Google says the resulting model can forecast urban flash floods up to 24 hours in advance and is now available in Flood Hub.
On March 12, 2026, Google Research said it is expanding Flood Hub with urban flash-flood predictions that can give up to 24 hours of advance notice. The company says it trained the model with a Groundsource dataset built by using Gemini to extract past flood-event details from public news reports.
Google said on Mar 19, 2026 that it integrated AI contrail forecasts into American Airlines’ existing flight-planning software. Across a trial tied to 2,400 scheduled transatlantic flights, the company says flights that executed the avoidance plan saw a 62% lower contrail formation rate than the control group.
Google on Mar 12, 2026 introduced Groundsource, a Gemini-powered method for turning public reports into historical disaster data. The company says the system identified more than 2.6 million flood events across over 150 countries and now supports urban flash-flood forecasts up to 24 hours in advance.
Google Research says its March 12, 2026 rollout adds urban flash flood forecasts to Flood Hub with up to 24 hours of advance notice. The system is trained in part on Groundsource, a dataset built by using Gemini to extract structured flood events from public news reports.