高时空分辨率、长期可靠的气象再分析数据集对于各种水文和气象应用而言至关重要，尤其在缺乏现场观测数据且开放获取数据有限的地区或时期。
基于第五代再分析数据集（ERA5，由欧洲中期天气预报中心生成，分辨率为 0.25°×0.25°，自 1940 年起）和 CLDAS（中国气象局陆地数据同化系统，分辨率为 0.0625°×0.0625°，自 2008 年起），提出一种新颖的降尺度方法——势能引导注意力网络（GeoAN）。该方法利用了 CLDAS 的高空间分辨率和 ERA5 扩展历史覆盖范围，生成了每日多变量（2m 温度、表面压力和 10m 风速）气象数据集 MDG625。MDG625 覆盖了1940年起，从南纬 0.125°到北纬 64.875°、东经 60.125°至 160.125°的大部分亚洲地区。与其他降尺度方法相比，GeoAN 表现出更好的性能，其中 2m 温度、表面压力和 10m 风速的 R2 值分别达到 0.990、0.998 和 0.781。
MDG625 在空间和时间两个维度上都展现出了卓越的连续性和一致性，可用于亚洲气候研究，并有助于提高1940年以来再分析产品的准确性。", "ds_source": "
数据来源于ESSD网站（https://essd.copernicus.org/articles/17/1501/2025/）。", "ds_process_way": "
基于 ERA5 和 CLDAS ，提出势能引导注意力网络（GeoAN）方法，该方法利用了 CLDAS 的高空间分辨率和 ERA5 扩展历史覆盖范围，生成了每日多变量（2m 温度、表面压力和 10m 风速）气象数据集 MDG625。", "ds_quality": "
数据质量较好。", "ds_acq_start_time": "1940-01-01 00:00:00", "ds_acq_end_time": "2016-12-31 00:00:00", "ds_acq_place": "亚洲", "ds_acq_lon_east": 160.125, "ds_acq_lat_south": 0.125, "ds_acq_lon_west": 60.125, "ds_acq_lat_north": 64.875, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "login-access", "ds_total_size": 482932926470, "ds_files_count": 311, "ds_format": "", "ds_space_res": "0.0625°", "ds_time_res": "日", "ds_coordinate": "无", "ds_projection": "", "ds_thumbnail": "2f11ae6a-97c5-46b9-ab28-3a500f981777.png", "ds_thumb_from": 2, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "", "ds_from_station": null, "organization_id": "d2c052ce-d283-4a48-8962-6a3dbcb03b8e", "ds_serv_man": "敏玉芳", "ds_serv_phone": "0931-4967596", "ds_serv_mail": "ncdc@lzb.ac.cn", "doi_value": "", "subject_codes": [ "170.15" ], "quality_level": 3, "publish_time": "2025-06-27 15:11:28", "last_updated": "2026-01-14 10:55:13", "protected": false, "protected_to": null, "lang": "zh", "cstr": "https://cstr.cn/31253.11.sciencedb.17408", "i18n": { "en": { "title": "MDG625: Meteorological Dataset with 0.0625° resolution produced by GeoAN", "ds_format": "", "ds_source": "
The data is sourced from the ESSD website（ https://essd.copernicus.org/articles/17/1501/2025/ ）.", "ds_quality": "
The data quality is good.", "ds_ref_way": "", "ds_abstract": "
The long-term and reliable meteorological reanalysis dataset with high spatial–temporal resolution is crucial for various hydrological and meteorological applications, especially in regions or periods with scarce in situ observations and with limited open-access data.
Based on the fifth-generation reanalysis dataset (ERA5, produced by the European Centre for Medium-Range Weather Forecasts, 0.25°×0.25°, since 1940) and CLDAS (China Meteorological Administration Land Data Assimilation System, 0.0625°×0.0625°, since 2008), we propose a novel downscaling method Geopotential-guided Attention Network (GeoAN), leveraging the high spatial resolution of CLDAS and the extended historical coverage of ERA5, and produce the daily multi-variable (2 m temperature, surface pressure, and 10 m wind speed) meteorological dataset MDG625. MDG625 (0.0625° Meteorological Dataset derived by GeoAN) covers most of Asia from 0.125° S to 64.875° N and 60.125 to 160.125° E, and contains data starting in 1940. Compared with other downscaling methods, GeoAN shows better performance with R2 (2 m temperature, surface pressure, and 10 m wind speed reach 0.990, 0.998, and 0.781, respectively).
MDG625 demonstrates superior continuity and consistency from both spatial and temporal perspectives. We anticipate that the GeoAN method and this dataset, MDG625, will aid in climate studies of Asia and will contribute to improving the accuracy of reanalysis products from the 1940s.
", "ds_time_res": "日", "ds_acq_place": "Asia", "ds_space_res": "0.0625°", "ds_projection": "", "ds_process_way": "Based on ERA5 and CLDAS, a Potential Energy Guided Attention Network (GeoAN) method is proposed, which utilizes the high spatial resolution of CLDAS and the extended historical coverage of ERA5 to generate a daily multivariate (2m temperature, surface pressure, and 10m wind speed) meteorological dataset MDG625.", "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_outside", "cstr_reg_from": "reg_outside", "doi_not_reg_reason": null, "cstr_not_reg_reason": null, "is_paper_in_submitting": false, "ds_topic_tags": [ "MDG625", "势能引导注意力网络（GeoAN）", "0.0625°", "气象" ], "ds_subject_tags": [ "大气科学" ], "ds_class_tags": [], "ds_locus_tags": [ "亚洲" ], "ds_time_tags": [ 1940, 1941, 1942, 1943, 1944, 1945, 1946, 1947, 1948, 1949, 1950, 1951, 1952, 1953, 1954, 1955, 1956, 1957, 1958, 1959, 1960, 1961, 1962, 1963, 1964, 1965, 1966, 1967, 1968, 1969, 1970, 1971, 1972, 1973, 1974, 1975, 1976, 1977, 1978, 1979, 1980, 1981, 1982, 1983, 1984, 1985, 1986, 1987, 1988, 1989, 1990, 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016 ], "ds_contributors": [ { "true_name": "袁丽娜", "email": "lnyuan@geoai.ecnu.edu.cn", "work_for": "华东师范大学 地理科学学院 地理信息科学教育部重点实验室 ", "country": "中国" }, { "true_name": "刘敏", "email": "mliu@geo.ecnu.edu.cn", "work_for": "华东师范大学 地理科学学院 地理信息科学教育部重点实验室", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "袁丽娜", "email": "lnyuan@geoai.ecnu.edu.cn", "work_for": "华东师范大学 地理科学学院 地理信息科学教育部重点实验室 ", "country": "中国" }, { "true_name": "刘敏", "email": "mliu@geo.ecnu.edu.cn", "work_for": "华东师范大学 地理科学学院 地理信息科学教育部重点实验室", "country": "中国" } ], "ds_managers": [ { "true_name": "袁丽娜", "email": "lnyuan@geoai.ecnu.edu.cn", "work_for": "华东师范大学 地理科学学院 地理信息科学教育部重点实验室 ", "country": "中国" } ], "category": "气象" }