%0 Dataset
%T Annual Precipitation Dataset for Different Cities and Counties on the Loess Plateau (2015–2100)
%J National Cryosphere Desert Data Center
%I National Cryosphere Desert Data Center(www.ncdc.ac.cn)
%U http://www.ncdc.ac.cn/portal/metadata/407a9e6d-e0cb-4580-8760-9ec95d5378f7
%W NCDC
%R 10.12072/ncdc.loess.db7334.2026
%A ZHANG Baoqing 
%K precipitation;long term;deep learning
%X Precipitation time series data are critical foundational data for global and regional climate research, hydrological modeling, and ecosystem assessments. However, existing future precipitation data series for cities and counties are generally short in duration. This introduces uncertainty in assessing long-term precipitation dynamics and trends at regional scales, particularly for local administrative units such as cities and counties.This study utilizes future precipitation datasets from ACCESS-ESM1-5, IPSL-CM6A-LR, and MIROC-ES2L. A downscaling model based on the U-Net deep learning architecture was constructed to generate a future precipitation data product for the Loess Plateau covering the period from 2015 to 2100. The spatial coverage of the dataset spans from 33.75°N to 41.25°N in latitude and 100.95°E to 114.55°E in longitude.The core advantage of this dataset lies in its provision of a long-term, 86-year precipitation data series from 2015 to 2100. This complete, extended temporal record facilitates the detailed analysis of local climate responses to global change, thereby providing a solid data foundation for long-term climate risk assessment and adaptation planning at the city and county scale.The dataset is stored in Excel format (*.xlsx). Different worksheets correspond to future precipitation data of different cities and counties. ACCESS-ESM1-5, IPSL-CM6A-LR and MIROC-ES2L represent different climate models, while ssp126, ssp245 and ssp585 denote different emission scenarios. The dataset has an annual temporal resolution and covers the period from 2015 to 2100.