StormDiT: A generative AI model bridges the 2-6 hour 'gray zone' in precipitation nowcasting

TL;DR

StormDiT is a novel AI model that effectively predicts extreme precipitation in the 2-6 hour 'gray zone' by learning coupled atmospheric processes, outperforming existing methods in stability, accuracy, and interpretability.

Contribution

This work introduces StormDiT, a unified generative model that captures the coupled physics of weather evolution without structural priors, significantly improving long-horizon precipitation nowcasting.

Findings

Maintains skillful prediction for strong convection up to 6 hours.

More than doubles the 1-hour performance for heavy rain.

Establishes the first robust 3-hour forecasting baseline.

Abstract

Accurate short-term warnings for extreme precipitation are critical for global disaster mitigation but are hindered by a persistent predictability barrier at the 2-6 hour horizon -- the "nowcasting gray zone." In this window, traditional observation-based extrapolation fails due to error accumulation, while numerical weather prediction is computationally too slow to resolve storm-scale dynamics. Recent generative AI approaches attempt to bridge this gap by decomposing precipitation into separate deterministic advection and stochastic diffusion components. However, this decomposition can sever fundamental causal links between entangled atmospheric processes, such as the dynamic initiation of convection triggered by boundary advection. Here we present StormDiT, a unified generative model that treats weather evolution as a holistic spatiotemporal problem, learning the coupled physics of the gray zone without human-imposed structural priors. Trained on a massive dataset of 7,720 precipitation events from China, our model achieves a breakthrough in long-horizon stability. On a heavy-rainfall test set, it maintains skillful prediction for strong convection ($\ge$ 35 dBZ) with a Critical Success Index (CSI) near 0.2 across the full 6-hour forecast at 6-minute resolution. Crucially, the model exhibits superior probabilistic calibration, accurately quantifying operational risks. On the public SEVIR benchmark, our unified paradigm more than doubles the state-of-the-art 1-hour performance for heavy rain and establishes the first robust baseline for 3-hour forecasting. Furthermore, interpretability analysis reveals that the model attends to non-local physical precursors, such as outflow boundaries, explicitly validating its emergent understanding of convective organization.