A scalable deep learning framework for daily precipitation downscaling architecture accuracy and adaptability

Authored by Meixiu Yu, Published in 2025

Item Content
Title A scalable deep learning framework for daily precipitation downscaling architecture accuracy and adaptability
Author Xiaolong Liu and Meixiu Yu and Fei Feng and Aftab Nazeer and Dewei Wang
Journal Journal of Water and Climate Change
Year 2025
Volume /
Issue /
Pages jwc2025293
Abstract Global climate models provide essential large-scale climate projections, yet their coarse spatial resolution (0.5°–4°) limits understanding of urbanization’s impact on regional climate dynamics. This study presents the Deep Residual Network for Precipitation Downscaling (DRN-PD), a modular neural architecture designed to enhance spatial precision and modeling interpretability in daily precipitation downscaling. By integrating CMIP6 atmospheric predictors, high-resolution land use data, and CHIRPS observations, DRN-PD advances understanding of climate–land surface interactions. Applied to the Yangtze Delta Megalopolis, the model achieves 18-fold spatial refinement, generating precipitation outputs at 5 km resolution. It consistently reproduces seasonal precipitation patterns, with mean absolute errors of 2.81–7.28 mm and root mean square errors below 11.28 mm. Spatial …
Cited by /
Google Citations view https://scholar.google.com/citations?view%5Fop=view%5Fcitation&hl=en&citation%5Ffor%5Fview=ly9d4IgAAAAJ:ldfaerwXgEUC
Url https://iwaponline.com/jwcc/article/doi/10.2166/wcc.2025.293/110681
Achive </>

Share on:

« PREVIOUS: Forecasting environmental water availability of lakes using temporal fusion transformer case studies of Chinas two largest freshwater lakes
NEXT: Hydrological effects of the cascade reservoir in the Middle Yarlung Zangbo River »