Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.01354 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908430085652480 |
|---|---|
| author | Yi, Chugang Yu, Minghan Qian, Weikang Wen, Yixin Yang, Haizhao |
| author_facet | Yi, Chugang Yu, Minghan Qian, Weikang Wen, Yixin Yang, Haizhao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01354 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet Diffusion Yi, Chugang Yu, Minghan Qian, Weikang Wen, Yixin Yang, Haizhao Machine Learning Atmospheric and Oceanic Physics 86A10 (Primary) 86A22, 68U10 (Secondary) J.2; I.4.4 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. |
| title | Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet Diffusion |
| topic | Machine Learning Atmospheric and Oceanic Physics 86A10 (Primary) 86A22, 68U10 (Secondary) J.2; I.4.4 |
| url | https://arxiv.org/abs/2507.01354 |