WADEPre: A Wavelet-based Decomposition Model for Extreme Precipitation Nowcasting with Multi-Scale Learning
This work solves the problem of accurate extreme precipitation forecasting for meteorology and disaster management, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackles the problem of extreme precipitation nowcasting by addressing the heavy-tailed nature of precipitation and regression-to-the-mean bias in standard models, resulting in state-of-the-art performance with significant improvements in capturing extreme thresholds and structural fidelity on datasets like SEVIR and Shanghai Radar.
The heavy-tailed nature of precipitation intensity impedes precise precipitation nowcasting. Standard models that optimize pixel-wise losses are prone to regression-to-the-mean bias, which blurs extreme values. Existing Fourier-based methods also lack the spatial localization needed to resolve transient convective cells. To overcome these intrinsic limitations, we propose WADEPre, a wavelet-based decomposition model for extreme precipitation that transitions the modeling into the wavelet domain. By leveraging the Discrete Wavelet Transform for explicit decomposition, WADEPre employs a dual-branch architecture: an Approximation Network to model stable, low-frequency advection, isolating deterministic trends from statistical bias, and a spatially localized Detail Network to capture high-frequency stochastic convection, resolving transient singularities and preserving sharp boundaries. A subsequent Refiner module then dynamically reconstructs these decoupled multi-scale components into the final high-fidelity forecast. To address optimization instability, we introduce a multi-scale curriculum learning strategy that progressively shifts supervision from coarse scales to fine-grained details. Extensive experiments on the SEVIR and Shanghai Radar datasets demonstrate that WADEPre achieves state-of-the-art performance, yielding significant improvements in capturing extreme thresholds and maintaining structural fidelity. Our code is available at https://github.com/sonderlau/WADEPre.