FlowCast: Advancing Precipitation Nowcasting with Conditional Flow Matching
This addresses flood risk management by providing more efficient and accurate short-term precipitation forecasts, though it is incremental as it builds on existing deep learning methods.
The authors tackled precipitation nowcasting by introducing FlowCast, which uses Conditional Flow Matching to forecast short-term precipitation from radar images, achieving new state-of-the-art accuracy with significantly fewer sampling steps compared to diffusion models.
Radar-based precipitation nowcasting, the task of forecasting short-term precipitation fields from previous radar images, is a critical problem for flood risk management and decision-making. While deep learning has substantially advanced this field, two challenges remain fundamental: the uncertainty of atmospheric dynamics and the efficient modeling of high-dimensional data. Diffusion models have shown strong promise by producing sharp, reliable forecasts, but their iterative sampling process is computationally prohibitive for time-critical applications. We introduce FlowCast, the first model to apply Conditional Flow Matching (CFM) to precipitation nowcasting. Unlike diffusion, CFM learns a direct noise-to-data mapping, enabling rapid, high-fidelity sample generation with drastically fewer function evaluations. Our experiments demonstrate that FlowCast establishes a new state-of-the-art in predictive accuracy. A direct comparison further reveals the CFM objective is both more accurate and significantly more efficient than a diffusion objective on the same architecture, maintaining high performance with significantly fewer sampling steps. This work positions CFM as a powerful and practical alternative for high-dimensional spatiotemporal forecasting.