Google announced Groundsource, an AI-based methodology that uses Gemini to convert public reports into a historical dataset of urban flash floods. The company said Groundsource identified more than 2.6 million historical flood events across more than 150 countries. Google said it used the dataset to train a model aimed at forecasting urban flash floods up to 24 hours in advance. The forecasts are available on Flood Hub, alongside existing riverine flood forecasts that the company said cover 2 billion people in more than 150 countries. Google said the Groundsource approach could be applied to other hazards such as landslides and heat waves.

Disclaimer: This news brief was created by Public Technologies (PUBT) using generative artificial intelligence. While PUBT strives to provide accurate and timely information, this AI-generated content is for informational purposes only and should not be interpreted as financial, investment, or legal advice. Alphabet Inc. published the original content used to generate this news brief on March 12, 2026, and is solely responsible for the information contained therein.