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.

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 30-cm surface soil conductivity data measured from the soil surface in Turpan Hami City, Aibi Lake Basin, Aksu Xinhe County, Kashgar Shufu County, etc.

Quality control mainly uses the measured soil salt data from 2020 to 2021 in Xinjiang for training samples and verification samples, and partially uses the soil quality survey data from the natural resources department for accuracy inspection and evaluation. The measurement method for soil electrical conductivity is the electrode method, which meets the measurement requirements of (HJ 802-2016). 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.