The scaling problem: Native precision vs. international attain

Specialised, hyper-local early warning techniques have been engineered to handle flash floods from rainfall in particular city settings, with examples in Florida (US), Barranquilla (Colombia), Manila (Philippines), Nakhon Si Thammarat (Thailand), Mayaguez (Puerto Rico), and Barcelona (Spain). These techniques sometimes depend on a community of bodily sensors monitoring variables like direct and radar-inferred precipitation, water ranges and circulate velocities. Whereas extremely correct for his or her particular areas, they’re troublesome to scale due to the excessive prices of {hardware} deployment, the necessity for site-specific calibration algorithms and engineering experience.

At a broader stage, initiatives such because the WMO’s Flash Flood Steerage System (FFGS), the European Runoff Index based mostly on Climatology (ERIC) flash flood indicator, and the US Nationwide Climate Service (NWS) Flash Flood Warnings system present wider protection by distant sensing and numerical climate fashions. These techniques, nevertheless, encounter important hurdles concerning international implementation. A major situation is their dependency on high-resolution hydrological maps and radar-based climate forecasts, assets which are largely unavailable inside the World South. Moreover, the reliance on skilled hydrologists to interpret advanced mannequin information and distribute actionable warnings presents a second main problem.

To realize near-global attain, our mannequin makes use of solely international climate merchandise (NASA IMERG, NOAA CPC) in addition to real-time international climate forecasts from the ECMWF Built-in Forecast System (IFS) Excessive Decision (HRES) atmospheric mannequin and the AI-based medium-range international climate forecasting mannequin by Google DeepMind. The system at the moment operates at a 20×20 kilometer spatial decision, a constraint primarily pushed by the decision of worldwide accessible information sources.