Pedo-transfer functions of the soil water characteristic curves of the vadose zone in a typical alluvial plain area in the lower reaches of the Yellow River using machine learning methods

• Published in: Environmental monitoring and assessment Vol. 194; no. 12; p. 850
• Main Authors: Zhan, Jiang, Li, Zhiping, Yu, Xiaopeng, Zhao, Guizhang, Yuan, Qiaoling
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.12.2022; Springer Nature B.V
• Subjects: Accuracy; Agricultural management; Agricultural production; Algorithms; Alluvial deposits; Alluvial plains; Artificial intelligence; Atmospheric Protection/Air Quality Control/Air Pollution; Bulk density; Dimensions; Earth and Environmental Science; Ecology; Ecotoxicology; Electrical conductivity; Electrical resistivity; Environment; Environmental Management; Environmental monitoring; Environmental science; Floods; Fractal geometry; Hydraulics; Hydrologic cycle; Hydrological cycle; Hydrology; Learning algorithms; Machine learning; Methods; Moisture content; Monitoring/Environmental Analysis; Organic matter; Physicochemical processes; Physicochemical properties; Porosity; Rivers; Root-mean-square errors; Soil mechanics; Soil porosity; Soil properties; Soil water; Spatial variability; Spatial variations; Transfer functions; Unsaturated soils; Vadose water; Water content; Water management; Yellow River; Lower reaches of the Yellow River; Soil water characteristic curve; Random forest; Pedo-transfer function; Machine learning
• ISSN: 0167-6369; 1573-2959
• DOI: 10.1007/s10661-022-10397-x

The soil water characteristic curve (SWCC) is of great significance for studying the hydrological cycle, agricultural water management, and unsaturated soil mechanics. However, it is difficult to effectively obtain a large number of SWCCs because of the cumbersome and expensive determination experiments for SWCCs. Pedo-transfer functions (PTFs) established using soil physicochemical properties have become an effective method for solving this problem. However, due to the limitations of the establishment methods and the wide spatial variability of soil properties, it is still difficult to establish PTFs in a specific region. In order to establish the PTFs of SWCCs for the alluvial plain area of the lower reaches of the Yellow River, 233 soil samples were collected from the vadose zone in a typical area. These data were used as the data sources, and eight variables including clay, silt content, fractal dimension, bulk density, total porosity, pH value, organic matter content, and electrical conductivity were used as the influencing factors. By applying and comparing three machine learning algorithms, the PTFs of the SWCCs based on the random forest algorithm were obtained. Based on the Gini index of the random forest, the insensitive factors were eliminated and the optimal variable input mode was constructed. Based on the verification, there was little difference between the predicted water content and the measured water content. The determination coefficient R 2 is 0.9308; the root mean square error ( RMSE ) is 0.0447; and the mean relative error ( MRE ) is 22.40%.