本数据为利用sentinel2号反射率产品数据进行进一步加工，其中原始数据为全疆10米月度哨兵二号反射率镶嵌数据集，土壤盐分通过机器学习进行提取，质量控制主要采用全疆2020-2021年土壤盐分实测数据进行训练样本和验证样本选择，部分利用自然资源部门土壤质量调查数据进行精度检验与评估。
", "ds_source": "哨兵二号反射率数据主要来源为欧空局下载。其余辅助数据来源为实地测量数据，自主产生。
", "ds_process_way": "哨兵二号反射率数据由于已经经过了欧空局处理，故未作进一步处理。用于本模型计算的土壤盐分也通过5点法采集后，在实验室测定电导率数据。本数据集是通过对随机森林，梯度回归，支持向量机等多种机器学习进行验证数据对比后，选择随机森林算法进行土壤盐分反演的反演的计算。
", "ds_quality": "本数据集是通过对随机森林，梯度回归，支持向量机等多种机器学习进行验证数据对比后，选择随机森林算法进行土壤盐分反演的反演的计算。数据分辨率为10m。其中随进森林算法的训练样本包括由吐鲁番哈密地区，艾比湖流域，阿克苏新和县，喀什疏附县等实测土壤地表30cm表层土壤电导率数据进行，土壤电导率的测定方法为电极法，满足（HJ 802-2016）测定要求，本数据在低植被覆盖区域精度较好，但在植被高覆盖度区域精度尚未得到检验。实体数据中部分区域存在空值，主要原因是由于该地区当月云量过大，Sentinel-2卫星无法获得有效影像对该地区土壤盐度进行精确反演，故而出现空值。
", "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": 1318504927960, "ds_files_count": 25, "ds_format": "栅格", "ds_space_res": "10米", "ds_time_res": "月", "ds_coordinate": "WGS84", "ds_projection": "CGCS2000", "ds_thumbnail": "fad6b07f-eab3-4b0e-8bae-f17f275d5cb6.jpg", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "数据来源引用：新疆10m土壤盐度数据集（2021年4-10月）来源于第三次新疆综合科学考察专项 \"空天地网一体化综合科考监测体系建设(2021xjkk1400)\"", "ds_from_station": null, "organization_id": "a5877b42-96ea-4f13-af7e-246f355413d6", "doi_value": "", "subject_codes": [ "170.45" ], "quality_level": 1, "publish_time": "2025-12-04 17:57:44", "first_publish_time": null, "last_updated": "2026-01-14 11:22:50", "protected": false, "protected_to": null, "lang": "zh", "cstr": "33110.11.XIEG.xjsedata.2022.00000114", "license": null, "extra": null, "files_shape": [ { "name": "2021xjkk1400-73-2023031073", "size": null, "is_dir": true } ], "features": null, "data_level": 0, "i18n": { "en": { "title": "Xinjiang 10m soil salinity dataset (April to October 2021)", "ds_abstract": "This data is for further processing using sentinel2 reflectance product data. The original data is the 10-meter monthly Sentinel 2 reflectance mosaic data set in Xinjiang. Soil salt is extracted through machine learning. The quality control mainly uses the 2020-2021 soil salt measurement data in Xinjiang. Training samples and verification samples are selected, and some soil quality survey data from the natural resources department are used for accuracy inspection and evaluation.
", "ds_source": "The main source of Sentinel-2 reflectivity data is downloaded from ESA. The rest of the auxiliary data sources are on-site measurement data and are generated independently.
", "ds_process_way": "The Sentinel-2 reflectivity data were not further processed because they had already been processed by ESA. The soil salinity used for calculation of this model was also collected by the 5-point method and measured the conductivity data in the laboratory. This dataset is based on comparing verification data from various machine learning such as random forest, gradient regression, and support vector machines, and selecting random forest algorithm to carry out soil salt inversion calculation.
", "ds_quality": "This dataset is based on comparing verification data from various machine learning such as random forest, gradient regression, and support vector machines, and selecting random forest algorithm to carry out soil salt inversion calculation. The data resolution is 10m. Among them, the training samples of the continuous forest algorithm include 30cm surface soil conductivity data from measured soil surface in Turpan Hami City, Aibi Lake Basin, Aksu Xinhe County, Kashgar Shufu County, etc. The measurement method for soil conductivity is electrode method, which meets the measurement requirements of (HJ802 -2016). The accuracy of this data is good in areas with low vegetation coverage, but the accuracy has not yet been tested in areas with high vegetation coverage. There are null values in some areas of the physical data, mainly because the cloud amount in this area is too large in the month, and Sentinel-2 satellite cannot obtain effective images to accurately retrieve the soil salinity in this area, so there are null values.
", "ds_ref_instruction": "Data source citation: Xinjiang's 10m soil salinity dataset (April to October 2021) comes from the third Xinjiang comprehensive scientific expedition special project \"Construction of Integrated Comprehensive Scientific Research Monitoring System of Air, Space, Space and Network (2021 xjkk1400)\"", "ds_format": "grid", "ds_projection": "CGCS2000", "ds_space_res": "10 meters", "ds_time_res": "months" } }, "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": [ "土壤盐度" ], "ds_subject_tags": [ "地理学" ], "ds_class_tags": [], "ds_locus_tags": [ "新疆" ], "ds_time_tags": [ 2021 ], "ds_contributors": [ "刘铁", "马勇刚" ], "ds_meta_authors": [ "马勇刚" ], "ds_managers": [ "李锦" ], "category": "哨兵" }