AI RESEARCH

Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting

arXiv CS.LG

ArXi:2606.02661v1 Announce Type: cross Accurate precipitation nowcasting is vital for disaster mitigation, but deep learning methods face a key trade-off: regression models produce over-smoothed, spectrally decaying predictions that blur convective details and violate turbulence power laws; diffusion models generate realistic yet unanchored hallucinations lacking physical grounding. We propose Spectral-Decoupled Iterative Refinement (SDIR), a deterministic framework that reformulates nowcasting as progressive frequency-decoupled refinement.