Transport-Guided Factorized Evolution for Precipitation Nowcasting

Precipitation nowcasting predicts the spatial distribution and intensity of precipitation over the next few hours from recent radar observations. Motion-aware methods combine advective transport of existing echoes with intensity updates to model localized growth and decay. However, in recursive rollout, each forecast already incorporates predicted intensity updates and is then fed back as input to the next transport step. This forecast-field feedback carries earlier evolution errors into subsequent transport steps and can compound spatial distortion. We present $\text{T}$ransport-Guided $\text{F}$actorized $\text{Evo}$lution$\text{(TFEvo)}$, an end-to-end framework that breaks this forecast-field feedback by using learned displacement fields to warp the latest observed radar field directly to each forecast horizon. Conditioned on the transported prediction, TFEvo models residual evolution by factorizing the field into spatial coverage and intensity components. This factorization accounts for the zero-inflated sparsity of radar data by representing zero-valued background through the coverage component. These updates are learned with an asymmetric training objective applied to the evolved prediction to penalize the underestimation of extreme rainfall. Across three benchmarks, TFEvo outperforms competitive baselines on most forecasting metrics. Notably, at $384\times 384$ resolution, it improves CSI-M by up to $\text{4.5}$% and reduces LPIPS by up to $\text{40.6}$% relative to a competitive high-resolution baseline, while using less than $\text{1}$% of the baseline's parameters. Code is available at https://anonymous.4open.science/r/TFEvo-CECD.