AI for Early Warnings for All — Malawi's Pilot to Integrate the 'Bris' AI Weather Model into National Forecasting

Between May and October 2025, Malawi's Department of Climate Change and Meteorological Services (DCCMS) ran a pilot — executed by the World Meteorological Organization (WMO) and funded through the CREWS initiative — to test whether an AI-based numerical weather prediction model could be integrated into the country's operational forecasting workflow. The pilot deployed "Bris," an AI weather model built by the Norwegian Meteorological Institute (MET Norway) and delivered via ECMWF's "forecast-in-a-box" framework, running on modest local hardware at DCCMS.

The project's roughly USD 245,775 (CHF 245,000) budget covered around 1,751 staff-hours of MET Norway technical engagement plus staff time, travel and equipment for DCCMS's core technical team over the six-month pilot, structured in four phases and timed to report to WMO's Extraordinary Congress in October 2025. Independent reporting found the AI model generated a 5-day forecast in about 10 minutes and a 10-day forecast in under 20 minutes on standard hardware, versus several hours for a comparable traditional numerical weather prediction run.

The pilot is explicitly framed by WMO and its technical partners as an early-stage capability test, not an operational deployment. MET Norway researcher Lene Østvand, quoted in independent coverage, said "we are not at the stage where this could be used on its own for public warnings" and cautioned that "AI models can be wrong — especially outside the conditions they were trained for." WMO's own materials raise open questions about AI's capability to support forecasts and warnings for local high-impact weather, and the pilot's chief output was a roadmap for regional scaling and staff training rather than a measured improvement in forecast accuracy or warning lead time. The initiative also remains dependent on continued external technical support from Norway, an acknowledged sustainability concern for local ownership.

Read the full analysis: https://wmo.int/activities/projects/project-portfolio/climate-risk-and-early-warning-systems-crews-artificial-intelligence-ai-early-warnings-all-ew4all