NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters
This work develops NowcastDiT and instantiates this flexibility through two complementary adaptations: a dynamics-aware noise prior for temporally coherent forecasts, and end-to-end reinforcement learning with timestep-aware rewards for meteorological skill.
Hao-Ran Xu, Xing-Zhuo Guo, Yu-Chen Zhang et al.
· 0 citations