Investigation of the spatial and temporal variation of soil salinity using Google Earth Engine: a case study at Werigan-Kuqa Oasis, West China

Shilong Ma; Baozhong He; Boqiang Xie; Xiangyu Ge; Lijing Han

doi:10.1038/s41598-023-27760-8

Investigation of the spatial and temporal variation of soil salinity using Google Earth Engine: a case study at Werigan-Kuqa Oasis, West China

Sci Rep. 2023 Feb 16;13(1):2754. doi: 10.1038/s41598-023-27760-8.

Authors

Shilong Ma^{1

2

3}, Baozhong He^{4

5

6}, Boqiang Xie^{1

2

3}, Xiangyu Ge^{1

2

3}, Lijing Han^{1

2

3}

Affiliations

¹ College of Geography and Remote Sensing Sciences, Xinjiang University, No. 777 Huarui Street, Xinjiang, 830017, Urumqi, China.
² Xinjiang Key Laboratory of Oasis Ecology, Xinjiang University, 830017, Urumqi, China.
³ Key Laboratory of Smart City and Environment Modelling of Higher Education Institute, Xinjiang University, 830017, Urumqi, China.
⁴ College of Geography and Remote Sensing Sciences, Xinjiang University, No. 777 Huarui Street, Xinjiang, 830017, Urumqi, China. sunnyhe@xju.edu.cn.
⁵ Xinjiang Key Laboratory of Oasis Ecology, Xinjiang University, 830017, Urumqi, China. sunnyhe@xju.edu.cn.
⁶ Key Laboratory of Smart City and Environment Modelling of Higher Education Institute, Xinjiang University, 830017, Urumqi, China. sunnyhe@xju.edu.cn.

Abstract

Large-scale soil salinity surveys are time-costly and labor-intensive, and it is also more difficult to investigate historical salinity, while in arid and semi-arid regions, the investigation of the spatial and temporal characteristics of salinity can provide a scientific basis for the scientific prevention of salinity, With this objective, this study uses multi-source data combined with ensemble learning and Google Earth Engine to build a monitoring model to observe the evolution of salinization in the Werigan-Kuqa River Oasis from 1996 to 2021 and to analyze the driving factors. In this experiment, three ensemble learning models, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), were established using data collected in the field for different years and some environmental variables, After the accuracy validation of the model, XGBoost had the highest accuracy of salinity prediction in this study area, with RMSE of 17.62 dS m^-1, R² of 0.73 and RPIQ of 2.45 in the test set. In this experiment, after Spearman correlation analysis of soil Electrical Conductivity (EC) with environmental variables, we found that the near-infrared band in the original band, the DEM in the topographic factor, the vegetation index based on remote sensing, and the salinity index soil EC had a strong correlation. The spatial distribution of salinization is generally characterized by good in the west and north and severe in the east and south. Non-salinization, light salinization, and moderate salinization gradually expanded southward and eastward from the interior of the western oasis over 25 years. Severe and very severe salinization gradually shifted from the northern edge of the oasis to the eastern and southeastern desert areas during the 25 years. The saline soils with the highest salinity class were distributed in most of the desert areas in the eastern part of the Werigan-Kuqa Oasis study area as well as in smaller areas in the west in 1996, shrinking in size and characterized by a discontinuous distribution by 2021. In terms of area change, the non-salinized area increased from 198.25 in 1996 to 1682.47 km² in 2021. The area of saline soil with the highest salinization level decreased from 5708.77 in 1996 to 2246.87 km² in 2021. overall, the overall salinization of the Werigan-Kuqa Oasis improved.

Abstract

Grants and funding