FlowCast: Advancing Precipitation Nowcasting with Conditional Flow Matching

ICLR 2026 Conference Submission19967 Authors

Keywords: conditional flow matching, precipitation nowcasting, generative models, spatiotemporal forecasting, machine learning in environmental science

TL;DR: FlowCast is the first model to apply Conditional Flow Matching (CFM) to precipitation nowcasting. Our approach outperforms state-of-the-art diffusion models while also leveraging CFM's inherent efficiency to require a small number of sampling steps.

Abstract: 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.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 19967