A new flood-warning model aims to extend early warning coverage beyond hyper-local systems by relying on global weather products and forecasts rather than dense networks of physical sensors.
Specialized, hyper-local early warning systems have already been engineered for flash floods from rainfall in cities including Florida (US), Barranquilla (Colombia), Manila (Philippines), Nakhon Si Thammarat (Thailand), Mayaguez (Puerto Rico), and Barcelona (Spain). Those systems can be highly accurate in specific places, but they are difficult to scale because they require expensive hardware, site-specific calibration algorithms and engineering expertise.
Broader systems such as the WMO’s Flash Flood Guidance System (FFGS), the European Runoff Index based on Climatology (ERIC) flash flood indicator, and the US National Weather Service (NWS) Flash Flood Warnings system provide wider coverage through remote sensing and numerical weather models. But the source text says these systems face major hurdles for global implementation because they depend on high-resolution hydrological maps and radar-based forecasts, which are largely unavailable in the Global South. They also rely on professional hydrologists to interpret model data and issue warnings.
To reach near-global coverage, the model uses only global weather products such as NASA IMERG and NOAA CPC, along with real-time global weather forecasts from the ECMWF Integrated Forecast System (IFS) High Resolution (HRES) atmospheric model and the AI-based medium-range global weather forecasting model by Google DeepMind.
The system currently operates at a 20×20 kilometer spatial resolution, a limit driven by the resolution of the globally available data sources. That makes it less detailed than local sensor networks, but it is designed to work in places where the data and infrastructure needed for more precise systems are not available.
Source: research.google.
Companies can share verified announcements through Newz9’s international press release submission page.
