本数据是从“中国首个 1 米分辨率全国尺度土地覆盖图 SinoLC-1”数据中下载的新疆范围的数据，新疆数据包含13个地州市的tif格式数据，数据分辨率1米，GCS_WGS1984投影坐标，全国范围的数据发布于2023年。
", "ds_source": "中国首个 1 米分辨率全国尺度土地覆盖图 SinoLC-1，利用基于深度学习的框架和开放数据建立，包括全球土地覆盖（GLC）产品、OpenStreetMap（OSM）和谷歌地球影像。通过结合三个 10 米 GLC 产品和 OSM 数据生成了可靠的训练标签。这些训练标签和从谷歌地球衍生出的 1 米分辨率图像被用于训练所提出的框架。 该框架通过结合一个分辨率保持型骨干网络、一个弱监督模块和一个自监督损失函数，解决了因图像与标签分辨率不匹配而产生的标签噪声问题，从而无需人工标注即可自动优化高分辨率土地覆盖结果。基于大存储和计算服务器，处理 73.25 TB 数据集以获取覆盖中国全境（960 万平方公里）的 SinoLC-1，耗时约 10 个月。
", "ds_process_way": "数据作者的最新制图算法被计算机视觉顶会CVPR2024接收(https://arxiv.org/abs/2403.02746), 代码开源在:https://github.com/LiZhuoHong/Paraformer/ ,感兴趣的用户可以利用该代码高效地更新自己数据集的高分土地覆盖图。
", "ds_quality": "SinoLC-1 产品通过一个包含超过 10 万个随机样本的可视化判读验证集和一个从中国政府提供的官方土地调查报告中收集的统计验证集进行了验证。验证结果显示，SinoLC-1 的整体精度为 73.61%，κ系数为 0.6595。对每个省级区域的验证进一步表明了该数据集在中国全境的精度。此外，统计验证结果表明，SinoLC-1 与官方调查报告相符，整体误差率为 6.4%。此外，SinoLC-1 与其他五个广泛使用的 GLC 产品进行了比较。 这些结果表明 SinoLC-1 具有最高的空间分辨率和最精细的景观细节。总之，作为中国首个 1 米分辨率全国尺度土地覆盖地图，SinoLC-1 提供了准确性和为全国相关研究和应用提供了基础支持。
", "ds_acq_start_time": null, "ds_acq_end_time": null, "ds_acq_place": "", "ds_acq_lon_east": null, "ds_acq_lat_south": null, "ds_acq_lon_west": null, "ds_acq_lat_north": null, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "login-access", "ds_total_size": 9550789830, "ds_files_count": 16, "ds_format": "", "ds_space_res": "1米", "ds_time_res": "", "ds_coordinate": "WGS84", "ds_projection": "GCS_WGS84", "ds_thumbnail": "37f59d49-c9b8-40d0-a396-d193773c3196.png", "ds_thumb_from": 2, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "Zhuohong Li, Wei He, Mofan Cheng, Jingxin Hu, Xiao An, Yan Huang, Guangyi Yang, & Hongyan Zhang. (2023). SinoLC-1: the first 1-meter resolution national-scale land-cover map of China created with the deep learning framework and open-access data (Northwest of China) (Northwest of China) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7708740", "ds_from_station": null, "organization_id": "a5877b42-96ea-4f13-af7e-246f355413d6", "doi_value": "", "subject_codes": [ "170.45" ], "quality_level": 1, "publish_time": "2025-08-12 13:49:47", "first_publish_time": null, "last_updated": "2025-08-12 13:49:47", "protected": false, "protected_to": null, "lang": "zh", "cstr": null, "license": null, "extra": null, "files_shape": [ { "name": "SinoLC-1_User Guides v2.4.pdf", "size": 7341309, "is_dir": false }, { "name": "Northwest_Xinjiang", "size": null, "is_dir": true } ], "features": null, "data_level": 0, "i18n": { "en": { "title": "1-meter resolution land cover map of prefectures and cities in Xinjiang", "ds_abstract": "This data is Xinjiang data downloaded from \"SinoLC-1, China's first 1-meter resolution national-scale land cover map\" data. Xinjiang data includes tif format data from 13 prefectures and cities, with a data resolution of 1 meter, and GCS_WGS1984 projection coordinates. National data will be released in 2023.
", "ds_source": "China's first 1-meter resolution national-scale land-cover map SinoLC-1 was built using a framework based on deep learning and open data, including Global Land Cover (GLC) products, OpenStreetMap (OSM) and Google Earth Images. Reliable training tags were generated by combining three 10-meter GLC products and OSM data. These training tags and 1-meter-resolution images derived from Google Earth were used to train the proposed framework. The framework solves the problem of label noise caused by mismatch between image and label resolutions by combining a resolution-maintaining backbone network, a weak supervision module, and a self-supervision loss function, allowing automatic optimization of high-resolution land cover results without manual labeling. Based on a large storage and computing server, it took about 10 months to process a 73.25 TB data set to obtain SinoLC-1 covering the entire territory of China (9.6 million square kilometers).
", "ds_process_way": "The latest mapping algorithm of the data author was received by the Computer Vision Summit CVPR2024 (https://arxiv.org/abs/2403.02746). The code is open source at https://github.com/LiZhuoHong/Paraformer/ Interested users can use this code to efficiently update the high-scoring land cover maps of their own datasets.
", "ds_quality": "The SinoLC-1 product was verified through a visual interpretation verification set containing more than 100,000 random samples and a statistical verification set collected from official land survey reports provided by the China government. The verification results showed that the overall accuracy of SinoLC-1 was 73.61%, and the κ coefficient was 0.6595. Validation of each provincial region further demonstrated the accuracy of the dataset across China. In addition, statistical verification results show that SinoLC-1 is consistent with the official survey report, with an overall error rate of 6.4%. In addition, SinoLC-1 was compared to five other widely used GLC products. These results show that SinoLC-1 has the highest spatial resolution and the finest landscape detail. In short, as China's first national-scale land cover map with 1-meter resolution, SinoLC-1 provides accuracy and basic support for relevant research and applications across the country.
", "ds_ref_instruction": "Zhuohong Li, Wei He, Mofan Cheng, Jingxin Hu, Xiao An, Yan Huang, Guangyi Yang, & Hongyan Zhang. (2023). SinoLC-1: the first 1-meter resolution national-scale land-cover map of China created with the deep learning framework and open-access data (Northwest of China) (Northwest of China) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7708740", "ds_projection": "GCS_WGS84", "ds_space_res": "1 meter" } }, "license_type": null, "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": [ "土地利用", "土地覆被" ], "ds_subject_tags": [ "地理学" ], "ds_class_tags": [], "ds_locus_tags": [ "新疆" ], "ds_time_tags": [ 2023 ], "ds_contributors": [ "李锦" ], "ds_meta_authors": [ "李锦" ], "ds_managers": [ "李锦" ], "category": "土地利用/土地覆被" }