多年冻土的存在与分布不仅深刻影响地表能量平衡、水文过程和生态系统稳定性，还控制着全球陆地碳储量的动态演化，是评估气候变化影响与碳排放反馈机制的关键基础。基于1749个多年冻土与非多年冻土站点，融合气温、降水、积雪日数、海拔、土壤属性等多源高分辨率环境因子，采用最优特征组合和随机森林模型进行建模预测。模型经40次5折交叉验证评估，准确率达到0.936，F1值为0.936，具有良好的泛化性能。在此基础上构建了覆盖欧亚大陆的多年冻土分布数据集，提供2000、2005、2010、2015和2020年五个时段的空间预测结果，空间分辨率为1 km。数据集生成的多年冻土分布图在空间上连续性良好，能够准确反映高纬与高海拔地区的冻土分布格局。该数据可为冻土变化分析、碳释放风险评估、区域气候响应模拟和生态环境监测提供基础支撑。
", "ds_source": "整合了多个公开数据库与文献记录中的多年冻土及非多年冻土站点数据，主要来源包括：全球陆地多年冻土监测网络（GTN-P）；藏北高原冰冻圈特殊环境与灾害国家野外科学观测研究站（CRS）；瑞士多年冻土监测网络（PERMOS）；已发表文献中提取的观测数据；全球历史气候网络（GHCN）中年均气温为 2-10°C 的气象站，用于扩充非多年冻土点位。环境因子数据主要来自以下高分辨率全球数据集：气温与降水量来自 WorldClim 2.1, 为减少年际气候波动对结果的干扰，数据均采用9年滑动平均值（即以目标年份为中心，前后各扩展4年）进行平滑处理；海拔采用哥白尼数字高程模型（Copernicus DEM）；积雪日数由 MODIS 北半球逐日无云雪覆盖产品统计获得；土壤黏粒含量来自 SoilGrids 2.0，原始分辨率 250 m，已重采样至 1 km。
", "ds_process_way": "以多年冻土与非多年冻土站点数据为基础，提取其对应的环境因子信息，采共选取包括气温、降水、积雪日数、海拔、经纬度、土壤属性等 20 个环境因子。模型评估阶段选取13种常见机器学习分类算法，通过网格搜索与40次5折交叉验证进行对比，最终确定随机森林模型为最佳方案。基于模型特征重要性排名，结合特征组合测试确定最优特征组合，并以全体站点数据训练构建最终模型。采用分块策略对欧亚大陆进行预测。最终生成2000、2005、2010、2015和2020年五期1 km分辨率的多年冻土分布图，每期对应一个GeoTIFF格式栅格数据文件。
", "ds_quality": "（1）在站点数据整理过程中，严格筛除坐标异常、标签不明或与区域气候条件不符的点位，确保空间分布代表性与分类准确性。各类栅格因子重采样后按统一网格系统对齐，并剔除缺失值区域，保证输入数据完整性与一致性。\n
\n（2）随机森林模型表现出良好的稳定性和泛化能力。在采用最优特征组合后，多次5折交叉验证结果显示，其在验证集上的平均准确率为0.936，F1分数为0.936，AUC-ROC与AUC-PR均超过0.93。最终预测模型在全体样本上的评估结果更优。
\n（3）预测多年冻土分布显示出明显的高纬与高海拔控制特征，与已有多年冻土分布格局吻合。边界区域过渡平滑，空间连续性良好。通过块处理方式有效控制大范围推理过程中的误差传播与内存开销，保障结果的稳定性与实用性。
", "ds_acq_start_time": "2000-01-01 00:00:00", "ds_acq_end_time": "2020-12-31 00:00:00", "ds_acq_place": "亚欧大陆区域", "ds_acq_lon_east": 25.0, "ds_acq_lat_south": 25.0, "ds_acq_lon_west": 180.0, "ds_acq_lat_north": 84.0, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "open-access", "ds_total_size": 13020923, "ds_files_count": 6, "ds_format": "GeoTIFF", "ds_space_res": "1km", "ds_time_res": "5年", "ds_coordinate": "WGS84", "ds_projection": "", "ds_thumbnail": "51abbe98-99b2-4e03-8005-7886728e0a62.png", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "", "ds_from_station": null, "organization_id": "952adb3f-3ede-4a94-942a-7de772f1bfc5", "ds_serv_man": "李红星", "ds_serv_phone": "0931-4967592", "ds_serv_mail": "ncdc@lzb.ac.cn", "doi_value": "", "subject_codes": [ "170", "170.45", "170.4510" ], "quality_level": 3, "publish_time": "2025-06-24 16:55:11", "last_updated": "2026-05-27 16:50:21", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.NCDC.NIEER.DB6870.2025", "i18n": { "en": { "title": "A 1 km Resolution Permafrost Distribution Dataset over Eurasia from (2000-2020)", "ds_format": "GeoTIFF", "ds_source": "Integrated data from multiple public databases and literature records on permafrost and non permafrost sites, primarily sourced from the Global Terrestrial Permafrost Monitoring Network (GTN-P); National Field Scientific Observation and Research Station for Special Environment and Disasters in the Cryosphere of the Northern Tibetan Plateau (CRS); Swiss Permot Monitoring Network (PERMOS); Observation data extracted from published literature; The Global Historical Climate Network (GHCN) is a meteorological station with an average annual temperature of 2-10 ° C, used to expand non permafrost locations. The environmental factor data mainly comes from the following high-resolution global datasets: temperature and precipitation are from WorldClim 2.1. To reduce the interference of interannual climate fluctuations on the results, the data are smoothed using a 9-year moving average (i.e. centered on the target year and extended by 4 years before and after); The altitude is determined using the Copernicus Digital Elevation Model (DEM); The number of snow covered days is obtained from the MODIS Northern Hemisphere daily cloud free snow coverage product statistics; The soil clay content comes from SoilGrids 2.0, with an original resolution of 250 m, which has been resampled to 1 km
", "ds_quality": "(1) In the process of organizing site data, strictly screen out points with abnormal coordinates, unclear labels, or inconsistent regional climate conditions to ensure spatial distribution representativeness and classification accuracy. After resampling various grid factors, align them according to a unified grid system and remove missing value areas to ensure the integrity and consistency of input data.\r\n
\r\n(2) The random forest model exhibits good stability and generalization ability. After adopting the optimal feature combination, multiple 5-fold cross validation results showed that its average accuracy on the validation set was 0.936, F1 score was 0.936, and both AUC-ROC and AUC-PR exceeded 0.93. The final prediction model has better evaluation results on the entire sample.\r\n
\r\n(3) The predicted distribution of permafrost shows obvious characteristics of high latitude and high altitude control, which is consistent with the existing distribution pattern of permafrost. The boundary area transitions smoothly and has good spatial continuity. Effectively controlling error propagation and memory overhead during large-scale inference through block processing, ensuring the stability and practicality of the results.
", "ds_ref_way": "", "ds_abstract": "The existence and distribution of permafrost not only profoundly affect surface energy balance, hydrological processes, and ecosystem stability, but also control the dynamic evolution of global terrestrial carbon storage. It is a key foundation for evaluating the impact of climate change and carbon emission feedback mechanisms. Based on 1749 permafrost and non permafrost sites, multiple high-resolution environmental factors such as temperature, precipitation, snow days, altitude, and soil properties were integrated, and the optimal feature combination and random forest model were used for modeling and prediction. After 40 rounds of 5-fold cross validation evaluation, the model achieved an accuracy of 0.936 and an F1 value of 0.936, demonstrating good generalization performance. On this basis, a permafrost distribution dataset covering the Eurasian continent was constructed, providing spatial prediction results for five time periods of 2000, 2005, 2010, 2015, and 2020 with a spatial resolution of 1 km. The permafrost distribution map generated by the dataset has good spatial continuity and can accurately reflect the permafrost distribution pattern in high latitude and high altitude areas. This data can provide basic support for permafrost change analysis, carbon release risk assessment, regional climate response simulation, and ecological environment monitoring.
", "ds_time_res": "", "ds_acq_place": "Eurasian continental region", "ds_space_res": "", "ds_projection": "", "ds_process_way": "Based on data from permafrost and non permafrost stations, corresponding environmental factor information was extracted, including 20 environmental factors such as temperature, precipitation, snow days, altitude, latitude and longitude, and soil properties. During the model evaluation phase, 13 common machine learning classification algorithms were selected and compared through grid search and 40 rounds of 5-fold cross validation, ultimately determining the random forest model as the best solution. Based on the ranking of model feature importance, combined with feature combination testing, the optimal feature combination is determined, and the final model is constructed by training with data from all sites. Using a partitioning strategy to predict the Eurasian continent. The final generation includes five periods of 1 km resolution permafrost distribution maps for the years 2000, 2005, 2010, 2015, and 2020, each corresponding to a GeoTIFF formatted raster data file.
", "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": [ "冻土", "多年冻土", "多年冻土分布", "亚欧大陆" ], "ds_subject_tags": [ "地球科学", "地理学", "自然地理学" ], "ds_class_tags": [], "ds_locus_tags": [ "亚欧大陆", "一带一路", "丝绸之路经济带" ], "ds_time_tags": [ 2000, 2005, 2010, 2015, 2020 ], "ds_contributors": [ { "true_name": "肖瑶", "email": "xiaoyao@lzb.ac.cn", "work_for": "中国科学院西北生态环境资源研究院", "country": "中国" }, { "true_name": "刘广岳", "email": "liuguangyue@lzb.ac.cn", "work_for": "中国科学院西北生态环境资源研究院", "country": "中国" }, { "true_name": "赵国辉", "email": "zhgh@lzb.ac.cn", "work_for": "中国科学院西北生态环境资源研究院", "country": "中国" }, { "true_name": "吴晓东", "email": "wxd565@163.com", "work_for": "中国科学院西北生态环境与资源研究所", "country": "中国" }, { "true_name": "赵林", "email": "zhaolin_110@lzb.ac.cn", "work_for": "中国科学院西北生态环境资源研究院", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "肖瑶", "email": "xiaoyao@lzb.ac.cn", "work_for": "中国科学院西北生态环境资源研究院", "country": "中国" } ], "ds_managers": [ { "true_name": "赵国辉", "email": "zhgh@lzb.ac.cn", "work_for": "中国科学院西北生态环境资源研究院", "country": "中国" }, { "true_name": "肖瑶", "email": "xiaoyao@lzb.ac.cn", "work_for": "中国科学院西北生态环境资源研究院", "country": "中国" } ], "category": "冻土" }