Estimation of Soil Salinization by Machine Learning Algorithms in Different Arid Regions of Northwest China

• Published in: Remote sensing (Basel, Switzerland) Switzerland), 2022-01, Vol.14 (2), p.347
• Main Authors: Jiang, Xiaofang, Duan, Hanchen, Liao, Jie, Guo, Pinglin, Huang, Cuihua, Xue, Xian
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Arid regions; Arid zones; Artificial intelligence; Artificial neural networks; Climate; Comparative analysis; Correlation coefficient; Correlation coefficients; deep extreme learning machine; Deep learning; Digital Elevation Models; Electrical conductivity; Electrical resistivity; Environmental monitoring; Feature selection; fractional differential transformation; hyperspectral data; Laboratories; Landsat; Learning algorithms; Machine learning; Monitoring; Neural networks; Parameters; Precipitation; Reflectance; Remote sensing; Saline soils; Salinity; Salinity effects; Salinization; Salt; sine cosine algorithm–Elman; Soil salinity; Trigonometric functions
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs14020347

Hyperspectral data has attracted considerable attention in recent years due to its high accuracy in monitoring soil salinization. At present, most existing research focuses on the saline soil in a single area without comparative analysis between regions. The regional differences in the hyperspectral characteristics of saline soil are still unclear. Thus, we chose Golmud in the cold–dry Qaidam Basin (QB–G) and Gaotai–Minghua in the relatively warm–dry Hexi Corridor (HC–GM) as the study areas, and used the deep extreme learning machine (DELM) and sine cosine algorithm–Elman (SCA–Elman) to predict soil salinity, and then selected the most suitable algorithm in these two regions. A total of 79 (QB–G) and 86 (HC–GM) soil samples were collected and tested to obtain their electrical conductivity (EC) and corresponding hyperspectral reflectance (R). We utilized the land surface parameters that affect the soil based on Landsat 8 and digital elevation model (DEM) data, selected the variables using the light gradient boosting machine (LightGBM), and built SCA–Elman and DELM from the hyperspectral reflectance data combined with land surface parameters. The results revealed the following: (1) The soil hyperspectral reflectance in QB–G was higher than that in HC–GM. The soils of QB–G are mainly the chloride type and those of HC–GM mainly belong to the sulfate type, having lower reflectance. (2) The accuracies of some of the SCA–Elman and DELM models in QB–G (the highest MAEv, RMSEv, and Rv2 were 0.09, 0.12 and 0.75, respectively) were higher than those in HC–GM (the highest MAEv, RMSEv, and Rv2 were 0.10, 0.14 and 0.73, respectively), which has flatter terrain and less obvious surface changes. The surface parameters in QB–G had higher correlation coefficients with EC due to the regular altitude change and cold–dry climate. (3) Most of the SCA–Elman results (the mean Rv2 in HC-GM and QB-G were 0.62 and 0.60, respectively) in all areas performed better than the DELM results (the mean Rv2 in HC–GM and QB–G were 0.51 and 0.49, respectively). Therefore, SCA–Elman was more suitable for the soil salinity prediction in HC–GM and QB–G. This can provide a reference for soil salinization monitoring and model selection in the future.