Мақола

Regional-scale intelligent optimization and topography impact in restoring global precipitation data gaps

Jiahan WangCollege of Information Science and Engineering, Hohai University, Changzhou, 213200, ChinaJiaqi ChenCollege of Information Science and Engineering, Hohai University, Changzhou, 213200, ChinaPeng ShenShanghai Aerospace Electronics Co., Ltd, Shanghai, ChinaXiaoling GuanCollege of Information Science and Engineering, Hohai University, Changzhou, 213200, ChinaXiangmei LiuCollege of Artificial Intelligence and Automation, Hohai University, Changzhou, 213200, ChinaChristian MassariNational Research Council (CNR), Research Institute for Geo-Hydrological Protection, Perugia, 06126, ItalyZongzhi WangState Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, Nanjing Hydraulic Research Institute, Nanjing, 210029, ChinaMingming FengKey Laboratory of Wetland Ecology and Environment, Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun, 130102, ChinaQingxuan WangCollege of Information Science and Engineering, Hohai University, Changzhou, 213200, ChinaYinghui LuCollege of Information Science and Engineering, Hohai University, Changzhou, 213200, ChinaErsa WeiCollege of Computer Science and Software Engineering, Hohai University, Nanjing, 210098, ChinaYonghao WangCollege of Information Science and Engineering, Hohai University, Changzhou, 213200, ChinaGulomjon UmirzakovDepartment of Surface Hydrology and Meteorology, National University of Uzbekistan named after Mirzo Ulugbek, Tashkent, 100174, UzbekistanBin YongState Key Laboratory of Water Disaster Prevention, Hohai University, Nanjing, 210098, China

Communications Earth & Environmentjournal2025en

ABI

Аннотация

Ground rainfall observations are essential for improving gauge-adjusted satellite precipitation estimates, particularly in the Global Precipitation Measurement mission era. However, over 60% of countries lack a complete surface-based rainfall gauge network, severely constraining the accuracy of global satellite precipitation retrievals. Here we present a model that integrates regional-scale intelligent optimization, topographic analysis, and an end-to-end neural network to merge multi-source precipitation data and reconstruct global spatiotemporal precipitation fields with resolved data gaps across scales. Our evaluation demonstrates that the model substantially improves satellite precipitation accuracy, increasing the correlation coefficient from 0.66 to 0.77. In particular, satellite estimates at high rain rates and over complex terrains show marked improvement when the model is applied. These findings suggest that the proposed approach holds strong potential for future applications in storm monitoring and flood forecasting, especially in mountainous regions with sparse observational data. Global hydrological research can be improved by a model that imputes and corrects global precipitation data gaps, according to an approach that integrates regional intelligent optimization, topographic analysis, and an end-to-end neural network to merge multi-source precipitation data.

Ҳали таржима қилинмаган

Мавзулар

Precipitation Measurement and Analysis Meteorological Phenomena and Simulations Climate variability and models

Идентификаторлар

DOI: 10.1038/s43247-025-02624-3

Иқтибослар ва манбалар

0 та иқтибос63 та фойдаланилган манба

Кўрсаткичлар — AkademScholar