降水时序数据是全球和区域气候与水循环研究的重要指标。然而，由于缺乏时空连续的高质量时间序列数据集，目前对全球和区域长期降水动态与变化的评估仍存在较大的不确定性。本研究利用ACCESS-ESM1-5、IPSL-CM6A-LR、MIROC-ES2L未来降水数据集，基于U-Net深度学习架构构建降尺度模型，生成黄土高原2015-2100年未来降水数据产品，空间覆盖范围为33.75°-41.25°N、100.95°-114.55°E，并具备0.1°的高空间分辨率与日时间分辨率。相较于原始模式数据，本数据集的核心优势在于其能更精确刻画复杂地形下的降水细节，显著提升了在区域水文模拟、极端降水事件分析等研究中的实用价值。
\n降水时序数据是全球和区域气候与水循环研究的重要本数据以NetCDF格式（*.nc）存储。数据文件命名格式为LoessPlateauRegion_ACCESS-ESM1-5_ssp126_Prec_2015_2100_merged。其中，LoessPlateauRegion为地区名称，ACCESS-ESM1-5为模型名称，ssp126为未来情景名称。数据文件中daily_precipitation为的日降水量，时空分辨率分别为日、10 km，时间范围为2015-2100年，lat和long分别为模式格点的纬度和经度。
", "ds_source": "高分辨率观测数据采用基于欧洲中期天气预报中心第五代再分析数据（ERA5）开发的MSWX格点化偏差校正气象数据集，该数据集提供了10个近地表气象变量，空间分辨率为0.1°，时间分辨率为3小时，作为模型训练和验证的对照组（https://www.gloh2o.org/mswx/）。基础气候数据来自耦合模式比较计划第六阶段（CMIP6）中3个全球气候模式的输出，包括历史时期（1950-2014年）和三种未来情景（SSP1-2.6, SSP2-4.5, SSP5-8.5，2015-2100年）的逐日模拟，其空间分辨率介于0.7°至2.8°之间（https://esgf-node.llnl.gov/search/cmip6/）
", "ds_process_way": "（1）利用MSWX数据集作为高分辨率观测数据，用于后续偏差校正与模型训练；（2）采用分位数Delta映射方法对CMIP6的3个全球气候模式输出进行偏差校正，校正后的数据用于降尺度输入；（3）基于U-Net深度学习架构构建降尺度模型，针对不同季节分别训练四个独立的U-Net模型，输入包括地形数据与偏差校正后的气象变量，并采用改进的损失函数以提升极端事件模拟能力；（4）利用1982–2014年期间的数据进行模型训练与验证，通过对比MSWX观测数据，从气候均值、极端事件频率及未来变化等多个方面系统评估降尺度数据集的性能。
", "ds_quality": "本研究采用均方根误差（RMSE）、平均偏差（MB）以及对不同等级降水事件（小雨、中雨、大雨、暴雨）频率的刻画能力作为核心验证指标，系统评估了降尺度生成的降水数据与MSWX高分辨率观测数据在1979年至2014年整个历史时期的一致性。验证结果表明，降尺度后数据的精度显著提升：大部分CMIP6模式的降水RMSE从原始输出的约1.00 mm/d降至0.37 mm/d以下；空间上，多模式集合平均的偏差在黄土高原地区被控制在-0.6至0.6 mm/d之间，有效纠正了原始数据普遍存在的系统性高估。同时，降尺度数据能更合理地再现不同强度降水的空间分布特征，尤其对中雨事件的强度分布刻画更为准确。因此，该降尺度降水数据集能够更可靠地反映区域降水的实际情况，可作为黄土高原地区高分辨率水文气候研究的可靠数据基础。
", "ds_acq_start_time": "2015-01-01 00:00:00", "ds_acq_end_time": "2100-12-31 00:00:00", "ds_acq_place": "黄土高原", "ds_acq_lon_east": 114.53333333333333, "ds_acq_lat_south": 33.75, "ds_acq_lon_west": 100.95, "ds_acq_lat_north": 41.25, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "login-access", "ds_total_size": 11792532978, "ds_files_count": 0, "ds_format": "*.nc", "ds_space_res": "10km", "ds_time_res": "日", "ds_coordinate": "WGS84", "ds_projection": "", "ds_thumbnail": "ce7e05d6-888c-4f0c-9551-4d4de8e9b42a.jpeg", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "", "ds_from_station": "", "organization_id": "bf138922-7121-438c-8d1b-19d5f751c907", "ds_serv_man": "李红星", "ds_serv_phone": "0931-4967592", "ds_serv_mail": "ncdc@lzb.ac.cn", "doi_value": "", "subject_codes": [ "170.15" ], "quality_level": 0, "publish_time": "2026-05-21 09:45:27", "last_updated": "2026-05-21 10:49:22", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.ncdc.loess.db7330.2026", "i18n": { "en": { "title": "Long-term daily composite precipitation dataset for the Loess Plateau from 2015 to 2100", "ds_format": "*.nc", "ds_source": "The high-resolution observational data used in this study are based on the MSWX gridded bias-corrected meteorological dataset developed from the European Centre for Medium-Range Weather Forecasts (ECMWF) fifth-generation reanalysis (ERA5). This dataset provides 10 near-surface meteorological variables at a spatial resolution of 0.1° and a temporal resolution of 3 hours, serving as the \"ground truth\" for model training and validation (https://www.gloh2o.org/mswx/). The baseline climate data were derived from outputs of three global climate models participating in the Coupled Model Intercomparison Project Phase 6 (CMIP6), including historical simulations (1950–2014) and daily projections under three future scenarios (SSP1-2.6, SSP2-4.5, and SSP5-8.5, 2015–2100). The spatial resolution of these climate models ranges from 0.7° to 2.8° (https://esgf-node.llnl.gov/search/cmip6/).", "ds_quality": "
This study employs root mean square error (RMSE), mean bias (MB), and the capability to characterize the frequency of precipitation events across different intensity categories (light rain, moderate rain, heavy rain, and torrential rain) as core validation metrics to systematically evaluate the consistency between the downscaled precipitation data and the high-resolution MSWX observational data over the entire historical period from 1979 to 2014.\r\n
The validation results indicate a significant improvement in the accuracy of the downscaled data: the RMSE of precipitation from most CMIP6 models decreased from approximately 1.00 mm/day in the original outputs to below 0.37 mm/day after downscaling. Spatially, the multi-model ensemble mean bias was controlled within the range of -0.6 to 0.6 mm/day over the Loess Plateau, effectively correcting the systematic overestimation commonly present in the raw data. Moreover, the downscaled data more realistically reproduces the spatial distribution characteristics of precipitation at different intensities, with particularly accurate characterization of the intensity distribution for moderate rain events. Therefore, this downscaled precipitation dataset can more reliably reflect the actual regional precipitation conditions and serves as a reliable data foundation for high-resolution hydroclimatic research in the Loess Plateau region.", "ds_ref_way": "", "ds_abstract": "
Precipitation time series data serve as critical indicators for global and regional climate and hydrological cycle research. However, due to the lack of spatiotemporally continuous, high-quality time series datasets, significant uncertainties persist in current assessments of long-term precipitation dynamics and changes at global and regional scales. This study utilizes future precipitation datasets from ACCESS-ESM1-5, IPSL-CM6A-LR, and MIROC-ES2L, and constructs a downscaling model based on the U-Net deep learning architecture to generate a future precipitation data product for the Loess Plateau from 2015 to 2100. The spatial coverage of the dataset spans 33.75°N to 41.25°N and 100.95°E to 114.55°E, with a high spatial resolution of 0.1° and daily temporal resolution. Compared to the original model data, the core advantage of this dataset lies in its high resolution, which enables more precise characterization of precipitation details in complex terrain, significantly enhancing its practical value for regional hydrological modeling and extreme precipitation event analysis, among other research applications.\r\n
The data are stored in NetCDF format (*.nc) with the file naming convention \"LoessPlateauRegion_ACCESS-ESM1-5_ssp126_Prec_2015_2100_merged,\" where LoessPlateauRegion denotes the area name, ACCESS-ESM1-5 represents the model name, and ssp126 indicates the future scenario name. Within the data file, the variable \"daily_precipitation\" provides daily precipitation amounts at a daily temporal resolution and 10 km spatial resolution for the period 2015–2100, while \"lat\" and \"lon\" specify the latitude and longitude of the model grid points, respectively.", "ds_time_res": "", "ds_acq_place": "Loess Plateau", "ds_space_res": "", "ds_projection": "", "ds_process_way": "
(1) The MSWX dataset is utilized as high-resolution observational data for subsequent bias correction and model training.(2) The Quantile Delta Mapping method is applied to perform bias correction on the outputs of three CMIP6 global climate models. The corrected data are then used as inputs for downscaling.(3) A downscaling model is constructed based on the U-Net deep learning architecture. Four independent U-Net models are trained separately for different seasons, incorporating topographic data and bias-corrected meteorological variables as inputs. An improved loss function is employed to enhance the simulation capability for extreme events.(4) Data from the period 1982–2014 are used for model training and validation. The performance of the downscaled dataset is systematically evaluated by comparing it with MSWX observational data across multiple aspects, including climatic means, frequency of extreme events, and future changes.", "ds_ref_instruction": "" } }, "submit_center_id": "ncdc", "data_level": 0, "recommendation_value": 0, "license_type": "https://creativecommons.org/licenses/by/4.0/", "doi_reg_from": "reg_local", "cstr_reg_from": "reg_local", "doi_not_reg_reason": null, "cstr_not_reg_reason": null, "is_paper_in_submitting": false, "belong_to_nieer": false, "ds_topic_tags": [ "降水", "长时序", "深度学习", "高分辨率" ], "ds_subject_tags": [ "大气科学" ], "ds_class_tags": [], "ds_locus_tags": [ "中国", "黄体高原" ], "ds_time_tags": [ 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024, 2025, 2026, 2027, 2028, 2029, 2030, 2031, 2032, 2033, 2034, 2035, 2036, 2037, 2038, 2039, 2040, 2041, 2042, 2043, 2044, 2045, 2046, 2047, 2048, 2049, 2050, 2051, 2052, 2053, 2054, 2055, 2056, 2057, 2058, 2059, 2060, 2061, 2062, 2063, 2064, 2065, 2066, 2067, 2068, 2069, 2070, 2071, 2072, 2073, 2074, 2075, 2076, 2077, 2078, 2079, 2080, 2081, 2082, 2083, 2084, 2085, 2086, 2087, 2088, 2089, 2090, 2091, 2092, 2093, 2094, 2095, 2096, 2097, 2098, 2099, 2100 ], "ds_contributors": [ { "true_name": "张宝庆", "email": "baoqzhang@lzu.edu.cn", "work_for": "兰州大学", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "张宝庆", "email": "baoqzhang@lzu.edu.cn", "work_for": "兰州大学", "country": "中国" } ], "ds_managers": [ { "true_name": "张宝庆", "email": "baoqzhang@lzu.edu.cn", "work_for": "兰州大学", "country": "中国" } ], "category": "气象" }