MW-Nowcast: Six-hour ensemble nowcasting of extreme precipitation

2026-09-28

AI Summary

This study addresses the rapid accuracy degradation and insufficient lead time in severe precipitation nowcasting beyond a few hours by proposing the MW-Nowcast model. This approach innovatively decouples storm-scale structures from local uncertainties through the joint training of a deterministic structure predictor and a generative residual module. By integrating deep learning with generative artificial intelligence, it constructs a six-hour ensemble forecasting system for extreme precipitation. Evaluated across test sets in the United States, Europe, and China, the proposed method significantly enhances severe precipitation detection skill and doubles the effective warning lead time for the most intense rainfall to six hours. These results overcome the inherent limitations of conventional generative models, which are typically restricted to accurate short-term predictions.

Abstract

Extending reliable nowcasting of extreme precipitation could provide critical additional time for warnings and emergency response during high-impact events such as flash floods. Radar-based generative machine-learning models have enabled skilful hyperlocal precipitation nowcasting, but accurate prediction of intense precipitation remains confined to the first few hours. Because storm-scale structure is predictable for longer than individual cells, a natural strategy is to predict that structure while generatively modelling only the uncertain local growth, decay, reorganisation and initiation of storms. Here we present Microsoft Weather Nowcast (MW-Nowcast), a six-hour ensemble radar nowcasting model that jointly learns a deterministic predictor to capture organised precipitation structure shared across ensemble members, and a generator to produce diverse local residuals around this shared prediction. Across independent test data from the United States, Europe and China, MW-Nowcast achieves higher detection skill than leading methods for heavy and extreme precipitation throughout the 6 h horizon. For the most intense rainfall, MW-Nowcast doubles the available warning time across all three regions, delivering 6 h forecasts with skill previously limited to 3 h for the leading generative baseline. A cost-loss decision analysis shows that MW-Nowcast retains substantial value for a broad range of applications even at 4-6 h, where alternative methods offer little benefit. These additional hours can give forecasters and emergency managers the time to warn and act before extreme rainfall strikes, helping to protect lives and property.

Problem

• extreme precipitation
• nowcasting
• ensemble forecasting
• radar
• warning time

Innovation

• Ensemble nowcasting
• Generative machine learning
• Extreme precipitation
• Deterministic predictor
• Joint learning architecture