Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet Diffusion
This addresses the need for accurate and efficient kilometer-scale precipitation data for hydrological modeling and extreme weather analysis, representing a strong incremental improvement in geoscience super-resolution.
The paper tackles the problem of generating high-resolution precipitation data at a 1 km scale from coarser 10 km inputs, achieving a 10x spatial super-resolution and a 9x inference speedup over existing methods.
Effective hydrological modeling and extreme weather analysis demand precipitation data at a kilometer-scale resolution, which is significantly finer than the 10 km scale offered by standard global products like IMERG. To address this, we propose the Wavelet Diffusion Model (WDM), a generative framework that achieves 10x spatial super-resolution (downscaling to 1 km) and delivers a 9x inference speedup over pixel-based diffusion models. WDM is a conditional diffusion model that learns the learns the complex structure of precipitation from MRMS radar data directly in the wavelet domain. By focusing on high-frequency wavelet coefficients, it generates exceptionally realistic and detailed 1-km precipitation fields. This wavelet-based approach produces visually superior results with fewer artifacts than pixel-space models, and delivers a significant gains in sampling efficiency. Our results demonstrate that WDM provides a robust solution to the dual challenges of accuracy and speed in geoscience super-resolution, paving the way for more reliable hydrological forecasts.