A scalable deep learning framework for daily precipitation downscaling: architecture, accuracy, and adaptability
Open Access
- 23 December 2025
- journal article
- Published by IWA Publishing in Journal of Water and Climate Change
- Vol. 17 (1) , 33-55
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 evaluations show strong agreement with observed rainfall distributions, achieving cosine similarity values exceeding 0.914 and effectively capturing rainfall centers and gradients. Incorporating a data augmentation strategy emphasizing extreme rainfall events, the model improves accuracy in high-intensity rainfall zones, with reduced relative errors and enhanced cosine similarity. These results demonstrate that DRN-PD, combined with appropriate training strategies, can effectively capture precipitation patterns across varying climatic and geographic contexts. This research contributes a practical tool for exploring climate–environment dynamics and supports evidence-based decision-making under increasing climate variability.Keywords
Funding Information
- National Natural Science Foundation of China (42401050)
- Research Project of Nanjing Polytechnic Institute (NJPI-RC-2024-10)
This publication has 47 references indexed in Scilit:
- Advancing long-range daily precipitation ensemble forecasts with deep learning for AustraliaJournal of Hydrology, 2025
- A new conditional generative adversarial neural network approach for statistical downscaling of the ERA5 reanalysis over the Italian PeninsulaEnvironmental Modelling & Software, 2025
- Deep‐learning‐based downscaling of precipitation in the middle reaches of the Yellow River using residual‐based CNNsQuarterly Journal of the Royal Meteorological Society, 2024
- Downscaling long lead time daily rainfall ensemble forecasts through deep learningStochastic Environmental Research and Risk Assessment, 2023
- Evaluation of precipitation in CMIP6 over the Yangtze River BasinAtmospheric Research, 2021
- Statistical downscaling of daily temperature and precipitation over China using deep learning neural models: Localization and comparison with other methodsInternational Journal of Climatology, 2020
- Comparison of CMIP6 and CMIP5 simulations of precipitation in China and the East Asian summer monsoonInternational Journal of Climatology, 2020
- Comparison of multiple linear regression and artificial neural network models for downscaling TRMM precipitation products using MODIS dataEnvironmental Earth Sciences, 2016
- Statistical downscaling and dynamical downscaling of regional climate in China: Present climate evaluations and future climate projectionsJournal of Geophysical Research: Atmospheres, 2016
- A vegetation index based technique for spatial sharpening of thermal imageryRemote Sensing of Environment, 2007