Google built a flash-flood prediction tool using Gemini and old news reports

"Google tasked Gemini with sorting through 5 million news articles from around the world and isolating flood reports. It transformed this data into a geo-tagged series of chronological events. Next, researchers trained a model to ingest current weather forecasts and leverage the Groundsource data to determine the likelihood of a flash flood in a given area."

"The model can only identify risk across a 20-square-kilometer area. It's also not quite as precise as the US National Weather Service's flood alert system, because Google's model doesn't integrate local radar data. This data typically enables real-time tracking of precipitation. However, the platform's been designed to work in areas that don't typically have access to that kind of weather-sensing infrastructure."

"We're aggregating millions of reports. It enables us to extrapolate to other regions where there isn't as much information. This is Google's approach to eventually predicting other tricky phenomena including heat waves and mudslides."

Google introduced Groundsource, an innovative flash flood prediction system leveraging Gemini to process 5 million global news articles and extract flood reports. The system converts this data into geo-tagged chronological events, which researchers use to train a model that analyzes current weather forecasts to assess flash flood likelihood. The tool currently covers 150 countries through Google's Flood Hub platform and shares data with emergency response agencies. While less precise than the US National Weather Service system due to lack of local radar integration, Groundsource targets areas without advanced weather infrastructure. The platform operates at 20-square-kilometer resolution and has demonstrated value in helping organizations respond faster to localized weather events. Google plans to expand this technology to predict other phenomena like heat waves and mudslides.

Read at Engadget