PixelFlowCast: Latent-Free Precipitation Nowcasting via Pixel Mean Flows
2026-05-11 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMachine LearningMultiagent Systems
AI summaryⓘ
The authors propose PixelFlowCast, a new two-step method to predict short-term rainfall patterns more quickly and accurately. First, a simple model makes a rough forecast of the weather changes. Then, a specialized network refines this forecast with detailed information, allowing precise and fast predictions without losing important weather details. Their tests show PixelFlowCast works better and faster than other methods, especially for longer forecasts, making it useful for real-world weather warnings.
Precipitation nowcastingDiffusion modelsConditional Flow MatchingSpatiotemporal featuresLatent space compressionRadar echo sequencesProbabilistic forecastingInference efficiencySEVIR datasetForecasting accuracy
Authors
Yufeng Zhu, Chunlei Shi, Yongchao Feng, Dan Niu
Abstract
Precipitation nowcasting aims to forecast short-term radar echo sequences for extreme weather warning, where both prediction fidelity and inference efficiency are critical for real-world deployment. However, diffusion-based models, despite their strong generative capability, suffer from slow inference due to multi-step sampling trajectories, limiting their practical usability. Conditional Flow Matching (CFM) improves efficiency via straightened trajectories, but relies on latent space compression, which inevitably discards high-frequency physical details and degrades fine-grained prediction quality. To address these limitations, we propose PixelFlowCast, a two-stage probabilistic forecasting framework that achieves both high-efficiency and high-fidelity prediction without latent compression. Specifically, in the first stage, a deterministic model first produces coarse forecasts to capture global evolution trends. In the subsequent stage, the proposed KANCondNet extracts deep spatiotemporal evolution features to provide accurate conditional guidance. Based on this, a latent-free, few-step Pixel Mean Flows (PMF) predictor employs an $x$-prediction mechanism to generate high-quality predictions, effectively preserving fine-grained structures while maintaining fast inference. Experiments on the publicly available SEVIR dataset demonstrate that PixelFlowCast outperforms existing mainstream methods in both prediction accuracy and inference efficiency, particularly for long sequence forecasting, highlighting its strong potential for real-world operational deployment.