Mark RadarMARK RADAR
About
EN
Sign in

Google Launches Groundsource Framework to Turn Global News Into Disaster Data With Gemini AI

1 reports · First detected 2026-03-12 · Last active 2026-03-12

Flash floods develop quickly and affect small areas, while conventional monitoring data often suffer from limited geographic coverage and sparse records. That leaves forecasting models without verifiable historical benchmarks. Google Research created Groundsource to use Gemini to extract and cross-check locations and dates from news reports worldwide, supporting hydrological research, urban planning, government warning systems and emergency response.

Google Research released Groundsource on March 12, 2026, after analyzing more than 5 million news articles. The resulting open-access dataset contains 2.6 million records of historical flash floods across more than 150 countries from 2000 to the present. Human review found that both the location and time were accurate in 60% of records, while 82% were already useful for practical analysis. Related models can provide urban flash-flood forecasts up to 24 hours in advance through Flood Hub.

All Coverage

1 original reports

The Backstory

The history behind this event
After this
Google Maps Integrates Gemini With Three AI Features for Enterprise Geospatial and Image Analysisfirst seen 2026-04-23 · 1 reports · similarity 0.70 · same topic: Google Gemini

Google Maps and Google Earth have long supported navigation, site selection and environmental monitoring. As businesses adopt AI agents, geospatial data is also becoming an important source for understanding the physical world. Google Cloud is integrating Gemini with its mapping platform so companies can directly interpret locations, buildings and changes in terrain while reducing the cost of manual analysis.

Google unveiled three Gemini AI capabilities at its 2026 Cloud Next conference: grounding with Maps imagery, automated satellite-image analysis and an Earth AI imagery model. Businesses can use them to enable AI agents to connect location and visual data, reducing geospatial tasks that once took days or weeks to just minutes.

Mark Radar|MARK RADAR

If you search news on Google, you can set Mark Radar as a preferred source—our coverage will show up more often in your results. Set as preferred source on Google →

All times are in Taipei time (GMT+8)