Google is using old news reports and AI to predict flash floods
By Tim Fernholz
Published on March 12, 2026.
Google is using old news reports and AI to predict flash floods, which are often difficult to predict due to their short-lived and localized nature. The company used its large language model, Gemini, to sort through 5 million news articles from around the world, isolating reports of 2.6 million different floods and creating a geo-tagged time series. This is the first time Google has used language models for this kind of work. The model is now highlighting risks for urban areas in 150 countries on the company's Flood Hub platform and sharing its data with emergency response agencies worldwide. However, there are limitations to the model, which identifies risk across 20-square-kilometer areas and does not incorporate local radar data.
Related Articles
Apple AirTag Is 52% Off, Making Four Singles Is Cheaper Than the 4-Pack
Apple AirTag sales are currently 52% off, offering four Apple AirTags for just $64 each, making them more affordable and easy to set up, reducing stress and convenience.
Iran-linked cyber attack targets US medtech giant Stryker
An Iranian-linked cyber attack targeting US medical tech giant Stryker disrupted its global networks, resulting in extensive data loss and disruption, with ongoing recovery efforts ongoing.
Cleafy raises €12M to stop bank fraud before it starts
Cleafy raises €12 million in Series B funding to enhance predictive security for banks by integrating real-time threat intelligence into its platform, aiming to prevent fraud before it occurs.