Flash floods are among the many deadliest climate occasions on the earth, killing greater than 5,000 folks every year. They’re additionally among the many most tough to foretell. However Google thinks it has cracked that drawback in an unlikely manner — by studying the information.
Whereas people have assembled numerous climate knowledge, flash floods are too short-lived and localized to be measured comprehensively, the way in which the temperature and even river flows are monitored over time. That knowledge hole implies that deep studying fashions, that are more and more able to forecasting the climate, aren’t capable of predict flash floods.
To unravel that drawback, Google researchers used Gemini — Google’s massive language mannequin — to kind by means of 5 million information articles from all over the world, isolating reviews of two.6 million completely different floods, and turning these reviews into a geo-tagged time series dubbed “Groundsource.” It’s the primary time that the corporate has used language fashions for this type of work, in response to Gila Loike, a Google Analysis product supervisor. The analysis and knowledge set was shared publicly Thursday morning.
With Groundsource as a real-world baseline, the researchers trained a model constructed on a Lengthy Quick-Time period Reminiscence (LSTM) neural community to ingest climate world forecasts and generate the likelihood of flash floods in a given space.
Google’s flash flood forecasting mannequin is now highlighting dangers for city areas in 150 nations on the corporate’s Flood Hub platform, and sharing its knowledge with emergency response businesses all over the world. António José Beleza, an emergency response official on the Southern African Growth Neighborhood who trialed the forecasting mannequin with Google, stated it helped his group reply to floods extra rapidly.
There are nonetheless limitations to the mannequin. For one, it’s pretty low decision, figuring out danger throughout 20-square-kilometer areas. And it isn’t as exact because the US Nationwide Climate Service’s flood alert system, partially as a result of Google’s mannequin doesn’t incorporate native radar knowledge, which permits real-time monitoring of precipitation.
A part of the purpose, although, is that the mission was designed to work in locations the place native governments can’t afford to put money into costly weather-sensing infrastructure or don’t have in depth data of meteorological knowledge.
Techcrunch occasion
San Francisco, CA
|
October 13-15, 2026
“As a result of we’re aggregating thousands and thousands of reviews, the Groundsource knowledge set really helps rebalance the map,” Juliet Rothenberg, a program supervisor on Google’s Resilience crew, instructed reporters this week. “It permits us to extrapolate to different areas the place there isn’t as a lot info.”
Rothenberg stated the crew hopes that utilizing LLMs to develop quantitative knowledge units from written, qualitative sources may very well be utilized to efforts to constructing knowledge units about different ephemeral-but-important-to-forecast phenomena, like warmth waves and dust slides.
Marshall Moutenot, the CEO of Upstream Tech, an organization that makes use of comparable deep studying fashions to forecast river flows for purchasers like hydropower firms, stated Google’s contribution is a part of a rising effort to assemble knowledge for deep learning-based climate forecasting fashions. Moutenot co-founded dynamical.org, a gaggle curating a set of machine learning-ready climate knowledge for researchers and startups.
“Knowledge shortage is likely one of the most tough challenges in geophysics,” Moutenot stated. “Concurrently, there’s an excessive amount of Earth knowledge, after which if you need to consider towards reality, there’s not sufficient. This was a very inventive strategy to get that knowledge.”
