RectiCast: Rectifying Distribution Shift in Cascaded Precipitation Nowcasting

Precipitation nowcasting, which aims to provide high spatio-temporal resolution precipitation forecasts by leveraging current radar observations, is a core task in regional weather forecasting. Recently, the cascaded architecture has emerged as the mainstream paradigm for deep learning-based precipitation nowcasting. This paradigm involves a deterministic model to predict posterior mean, followed by a probabilistic model to generate local stochasticity. However, existing methods commonly conflate the systematic distribution shift in deterministic predictions with local stochasticity, which contaminates the probabilistic component and degrades forecast accuracy, especially over longer lead times. To address this issue, we introduce RectiCast, a two-stage framework that explicitly decouples the rectification of mean-field shift from the generation of local stochasticity via a dual Flow Matching model. In the first stage, a deterministic model generates the posterior mean. In the second stage, a Rectifier explicitly learns the distribution shift to yield a rectified mean, conditioning a Generator that models local stochasticity. Experiments on two radar datasets demonstrate that RectiCast achieves significant performance improvements over existing state-of-the-art methods.