Introducing Groundsource: Turning news reports into data with Gemini
Groundsource is a Google Research methodology that uses Gemini to convert global news reports into structured historical records of natural disasters. Its first dataset contains 2.6 million flash-flood events across more than 150 countries from 2000 onward, addressing major gaps in conventional flood databases. Google reports that the system can support near-global urban flash-flood forecasts up to 24 hours in advance. ## The problem: Limited historical disaster data - Floods lack the standardized global sensor infrastructure available for hazards such as earthquakes. - Existing sources, including the Global Flood Database and Dartmouth Flood Observatory, are limited by cloud cover, satellite revisit times, and their focus on large or long-lasting floods. - GDACS contains roughly 10,000 high-impact disaster records but misses many localized and rapidly developing flash floods. - This shortage of reliable historical data makes global forecasting, model training, and validation difficult. ## How Groundsource processes news - The system analyzes news articles where flooding is the primary subject. - Google Read Aloud extracts article text in 80 languages, which is translated into English using Cloud Translation. - Gemini then applies a verification-oriented prompt to: - Distinguish actual past or ongoing floods from warnings, policy discussions, and general risk reports. - Resolve relative dates such as “last Tuesday” using the article’s publication date. - Identify precise locations, including neighborhoods and streets. - Map locations to standardized geographic polygons through Google Maps Platform. ## Accuracy and scale - Manual evaluation found: - 60% of events were accurate in both timing and location. - 82% were sufficiently accurate for practical analysis, such as identifying the correct administrative district or event day. - The resulting dataset contains 2.6 million flood events, greatly exceeding traditional monitoring archives. - Between 2020 and 2026, Groundsource captured 85%–100% of severe flood events listed by GDACS while also recording smaller local incidents. - Coverage is densest in recent years, particularly from 2020 to 2025, reflecting the growth of digitized news. ## Forecasting and future applications - Groundsource data has enabled near-global urban flash-flood forecasts up to 24 hours ahead. - These forecasts are being integrated into Google Flood Hub. - Google plans to improve rural coverage and incorporate additional data sources. - The same approach could help build historical datasets for droughts, landslides, avalanches, and other hazards with limited ground-truth records. Groundsource demonstrates that news archives can serve as a large-scale source of disaster history when combined with language models, translation, and geographic verification. Its open flash-flood dataset could improve forecasting and resilience planning, though its reported accuracy levels make continued validation and refinement important.
Read original(opens in new tab)