本数据集面向勒拿河河冰遥感识别与机器学习研究，基于2024年多时相 Sentinel-2 L2A 影像构建，空间覆盖从源区至三角洲的全河主干走廊。数据集包含1,000个经过人工监督复核的河冰分割样本，按空间与影像来源分组划分为640个训练样本、160个验证样本和200个独立测试样本，共提供约1,944万有效标注像素。标签采用河冰、水体和背景三类体系，空间分辨率为10 m，并覆盖夏季、初冻期和稳定冻结期等典型河冰状态。在监督样本基础上训练河冰分割模型，并将其应用于3,709个全河空间单元的4个观测时段，形成14,836条全河河冰识别记录及相应的掩膜、概率和空间索引产品。该数据集可用于河冰分割算法训练与比较、沿程冻结过程分析，以及后续勒拿河冰情监测和通航环境研究。", "ds_source": "", "ds_process_way": "", "ds_quality": "", "ds_acq_start_time": "2024-01-01 00:00:00", "ds_acq_end_time": "2024-12-31 00:00:00", "ds_acq_place": "勒拿河", "ds_acq_lon_east": 130.17, "ds_acq_lat_south": 53.70583333333334, "ds_acq_lon_west": 104.96000000000001, "ds_acq_lat_north": 73.15777777777778, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "apply-access", "ds_total_size": 2315988793, "ds_files_count": 0, "ds_format": "*csv,*.txt，*.md等", "ds_space_res": "10米", "ds_time_res": "4个季节观测时窗", "ds_coordinate": "无", "ds_projection": "", "ds_thumbnail": "af3da596-359d-4e9a-89d1-efdbd10a2657.png", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "None", "ds_from_station": null, "organization_id": "52b7b79b-860c-49a5-9083-9a70cf8bed5a", "ds_serv_man": null, "ds_serv_phone": null, "ds_serv_mail": null, "doi_value": "", "subject_codes": [ "170" ], "quality_level": 0, "publish_time": "2026-08-26 09:48:29", "last_updated": "2026-08-26 15:21:34", "protected": false, "protected_to": "2027-02-22 00:00:00", "lang": "zh", "cstr": "11738.11.ncdc.hydrology.db7722.2026", "i18n": { "en": { "title": "Sentinel-2 River-Ice Segmentation Dataset for the Full Lena River Main Stem", "ds_format": "*csv,*.txt，*.md等", "ds_source": "", "ds_quality": "", "ds_ref_way": "", "ds_abstract": "
River ice is an important part of the seasonal hydrological process of rivers in cold regions, and high spatial resolution and reusable pixel-level supervision data are still lacking. This dataset is aimed at remote sensing identification of Lena River ice, machine learning training and ice-condition analysis from source to delta. It forms a related product consisting of manual supervision tags, model and reproduction codes, whole river model mapping, and continuous trunk status.\r\n
The data source is Sentinel-2 Level-2A surface reflectance images from July to November 2024. The images are retrieved through the Microsoft Planetary Computer STAC catalog; river network and trunk spatial indexes are built based on OpenStreetMap data. The processing process includes image retrieval and screening, band alignment, 512 pixel segmentation, manually supervised water/river ice pixel labeling, data segmentation for river section isolation, U-Net training and verification set threshold selection, river-wide reasoning, supplementary image processing, along route inspection and continuous product construction. All 1,000 final supervision masks were confirmed by manual supervision, and category values of 0, 1 and 2 represent ignore/background, water and river ice respectively.\r\n
The supervision data includes 1,000 512×512 pixel samples from 656 river sections with a spatial resolution of 10 meters. Among them, 640, 160 and 200 training, verification and river isolation test samples are respectively, containing a total of 19,444,786 valid labeled pixels. The reference line from the source to the delta is 4,440.422 kilometers long and has a spatial range of 104.960°-130.167°E and 53.706°-73.158°N. The entire river product covers 3,709 spatial units and 4 observation time windows: open water surface in summer, early freezing, middle freezing, and late freezing. It contains 14,836 unit-time window records, corresponding geographical registration classification grids and river ice fraction grids; In addition, segmentation results of 2,628 scenes supplementary Sentinel-2 observations, as well as 71,052 continuous trunk state records and supporting evidence grids composed of 17,763 checkpoints with 250-meter spacing are provided.\r\n
Quality control includes image effectiveness screening, fixed river sections grouping, manual label supervision and review, document quantity and path inspection, grid size/category/coordinate reference inspection, SHA-256 verification and river continuity audit. In the river section isolation test, the F1 and IoU of water bodies were 0.985 and 0.970 respectively, and the F1 and IoU of river ice were 0.942 and 0.891 respectively. With the addition of supplementary images, Sentinel-2 supports checkpoint coverage for four time windows is 71.19%-90.44%; continuous products fill in the remaining gaps along the route while retaining the source of observations, and distinguish main observations, supplementary observations, and interpolation along the route based on evidence values. The data can be used for training and comparison of river ice segmentation algorithms, research on the freezing status of the Lena River, and development of the entire river ice condition monitoring system, and provide a continuous ice condition information basis for subsequent navigation environment research.", "ds_time_res": "Four seasonal observation windows", "ds_acq_place": "Lena River", "ds_space_res": "10 m", "ds_projection": "", "ds_process_way": "", "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, "allow_update_data": false, "ds_topic_tags": [ "河冰", "遥感监测", "语义分割" ], "ds_subject_tags": [ "地球科学" ], "ds_class_tags": [], "ds_locus_tags": [ "勒拿河" ], "ds_time_tags": [ 2024 ], "ds_contributors": [ { "true_name": "张泽", "email": "zez@nefu.edu.cn", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "郭子优", "email": "ziyouguo19@gmail.com", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "Leonid Gagarin ", "email": "gagarinleo@yandex.ru", "work_for": "Melnikov Permafrost Institute", "country": "中国" }, { "true_name": "闫庆凯", "email": "yanqingkai@nefu.edu.cn", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "姜昕悦", "email": "jiangxinyue@nefu.edu.cn", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "鞠梦瑶", "email": "2024122057@nefu.edu.cn", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "Andrei Zhang", "email": "zhang0993@yandex.ru", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "Nikolai Torgovkin", "email": "nick1805torg@gmail.com", "work_for": "东北林业大学", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "张泽", "email": "zez@nefu.edu.cn", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "郭子优", "email": "ziyouguo19@gmail.com", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "Leonid Gagarin ", "email": "gagarinleo@yandex.ru", "work_for": "Melnikov Permafrost Institute", "country": "中国" }, { "true_name": "闫庆凯", "email": "yanqingkai@nefu.edu.cn", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "姜昕悦", "email": "jiangxinyue@nefu.edu.cn", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "鞠梦瑶", "email": "2024122057@nefu.edu.cn", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "Andrei Zhang", "email": "zhang0993@yandex.ru", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "Nikolai Torgovkin", "email": "nick1805torg@gmail.com", "work_for": "东北林业大学", "country": "中国" } ], "ds_managers": [ { "true_name": "张泽", "email": "zez@nefu.edu.cn", "work_for": "东北林业大学", "country": "中国" }, { "true_name": "郭子优", "email": "ziyouguo19@gmail.com", "work_for": "东北林业大学", "country": "中国" } ], "category": "水文" }