东北地区冻融灾害易发性评估数据集基于东北地区冻融灾害的现场调查资料，并采用五种机器学习模型（GAM、GAM、GBM、RF、ANN）及其加权集成方法，构建了东北地区 1000 m 分辨率冻融灾害易发性评估产品。数据以栅格形式表达区域冻融灾害的空间易发性等级，可用于冻土灾害监测、风险评估、生态环境研究及区域规划等领域。\n
冻融灾害等级分为以下5类：\n
1：极低\n
2：低\n
3：中等\n
4：高\n
5：极高", "ds_source": "
基于现场调查及空间环境因子地理数据。", "ds_process_way": "
样本构建：正样本（灾害发生点）来自东北地区的现场调查，记录冻融灾害发生的位置、类型与环境背景。负样本（非灾害点）在灾害未发生区域按一定比例随机采样，确保空间覆盖均匀，避免模型偏向灾害点密集区域。\n
分类特征：根据环境地理数据提取地形、气候、土壤与地表、水文等特征。\n
算法执行：用Python分别训练五类模型，使用 k 折交叉验证（k=5 或 10）评估模型性能，对五个模型的预测结果进行加权平均生成初级产品。\n
后处理：将集成模型输出的连续概率值按五级划分，具体包括自然断点法（Jenks），将预测结果转换为 1000 m 分辨率栅格，投影为 WGS84（EPSG:4326），输出为 GeoTIFF", "ds_quality": "
为于机器学习集成研发的东北地区1000米分辨率冻融灾害易发性产品,数据质量良好，数据分数据可用于多种空间分析任务，识别冻融灾害高风险区、空间聚集区，与地形、气候、土地利用等数据叠加，分析驱动因子。", "ds_acq_start_time": "2010-01-01 00:00:00", "ds_acq_end_time": "2024-12-31 00:00:00", "ds_acq_place": "东北多年冻土区", "ds_acq_lon_east": 134.94166666666666, "ds_acq_lat_south": 38.041666666666664, "ds_acq_lon_west": 112.75, "ds_acq_lat_north": 54.35, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "apply-access", "ds_total_size": 7053078, "ds_files_count": 3, "ds_format": "*.tif", "ds_space_res": "1km", "ds_time_res": "年", "ds_coordinate": "WGS84", "ds_projection": "WGS_1984_Albers", "ds_thumbnail": "6df10e98-614e-4c25-84f4-53e6e9ab5bae.jpg", "ds_thumb_from": 2, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "", "ds_from_station": null, "organization_id": "221ebf56-1b0b-4574-972b-1fb6d3cf1be7", "ds_serv_man": "敏玉芳", "ds_serv_phone": "0931-4967596", "ds_serv_mail": "ncdc@lzb.ac.cn", "doi_value": "", "subject_codes": [ "170.45" ], "quality_level": 3, "publish_time": "2026-04-07 09:00:04", "last_updated": "2026-05-12 15:24:30", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.NCDC.NIEER.DB7284.2026", "i18n": { "en": { "title": "1km freeze-thaw disaster susceptibility data of the permafrost region in Northeast China (2010-2024)", "ds_format": "*.tif", "ds_source": "
Based on on-site investigations and geographical data of spatial environmental factors.", "ds_quality": "
The 1000 meter resolution freeze-thaw disaster prone product developed for machine learning integration in Northeast China has good data quality and can be used for various spatial analysis tasks to identify high-risk areas and spatial clusters of freeze-thaw disasters. It is overlaid with terrain, climate, land use and other data to analyze driving factors.", "ds_ref_way": "", "ds_abstract": "
The susceptibility assessment dataset for freeze-thaw disasters in Northeast China is based on on-site investigation data of freeze-thaw disasters in Northeast China. Five machine learning models (GAM, GAM, GBM, RF, ANN) and their weighted integration methods are used to construct a 1000 meter resolution freeze-thaw disaster susceptibility assessment product for Northeast China. The data expresses the spatial susceptibility level of regional freeze-thaw disasters in grid form, which can be used in fields such as permafrost disaster monitoring, risk assessment, ecological environment research, and regional planning.\r\n
The levels of freeze-thaw disasters are divided into the following 5 categories:\r\n
1: Extremely low\r\n
2: Low\r\n
3: Medium\r\n
4: High\r\n
5: Extremely high", "ds_time_res": "", "ds_acq_place": "Northeast Permafrost Region", "ds_space_res": "", "ds_projection": "", "ds_process_way": "
Sample construction: The positive sample (disaster occurrence point) comes from on-site investigations in Northeast China, recording the location, type, and environmental background of freeze-thaw disasters. Negative samples (non disaster points) are randomly sampled at a certain proportion in areas where disasters have not occurred, ensuring uniform spatial coverage and avoiding model bias towards areas with dense disaster points.\r\n
Classification features: Extract features such as terrain, climate, soil and surface, hydrology, etc. based on environmental geographic data.\r\n
Algorithm execution: Train five types of models separately using Python, evaluate model performance using k-fold cross validation (k=5 or 10), and generate primary products by weighted averaging of the predicted results of the five models.\r\n
Post processing: Divide the continuous probability values output by the integrated model into five levels, including the natural breakpoint method (Jenks), convert the predicted results into a 1000 m resolution grid, project them into WGS84 (EPSG: 4326), and output them as GeoTIFF", "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, "ds_topic_tags": [ "冻土退化", "冻融灾害", "东北", "大兴安岭" ], "ds_subject_tags": [ "地理学" ], "ds_class_tags": [], "ds_locus_tags": [ "东北多年冻土区" ], "ds_time_tags": [ 2010, 2024 ], "ds_contributors": [ { "true_name": "李国玉", "email": "guoyuli@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": "陈敦", "email": "chendun@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": "高凯", "email": "gaokai@nieer.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": "王飞", "email": "wangfei@nieer.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": "曹亚鹏", "email": "caoyapeng@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": "尹国安", "email": "yinguoan@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": "牛富俊", "email": "niufujun@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": "商允虎", "email": "shangyunhu@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": "林峻岑", "email": "linjuncen@nieer.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": "杜青松", "email": "xbdqs@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": "贾寒", "email": "jiahan@nieer.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": "王亚鹏", "email": "wangyapeng@nieer.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": "齐舜舜", "email": "qishunshun@nieer.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": "艾熙惠", "email": "aixihui@nieer.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": "杨佳伟", "email": "yangjiawei@nieer.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": "李兆祥", "email": "lizhaoxiang@nieer.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": "胡美容", "email": "humeirong@nieer.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": "尹国安", "email": "yinguoan@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": "陈敦", "email": "chendun@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": "陈敦", "email": "chendun@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": "灾害" }