Mapping Soil Properties in the Haihun River Sub-Watershed, Yangtze River Basin, China, by Integrating Machine Learning and Variable Selection
Open Access
Abstract
Mapping soil properties in sub-watersheds is critical for agricultural productivity, land management, and ecological security. Machine learning has been widely applied to digital soil mapping due to a rapidly increasing number of environmental covariates. However, the inclusion of many environmental covariates in machine learning models leads to the problem of multicollinearity, with poorly understood consequences for prediction performance. Here, we explored the effects of variable selection on the prediction performance of two machine learning models for multiple soil properties in the Haihun River sub-watershed, Jiangxi Province, China. Surface soils (0–20 cm) were collected from a total of 180 sample points in 2022. The optimal covariates were selected from 40 environmental covariates using a recursive feature elimination algorithm. Compared to all-variable models, the random forest (RF) and extreme gradient boosting (XGBoost) models with variable selection improved in prediction accuracy. The R2 values of the RF and XGBoost models increased by 0.34 and 0.47 for the soil organic carbon, by 0.67 and 0.62 for the total phosphorus, and by 0.43 and 0.62 for the available phosphorus, respectively. The models with variable selection presented reduced global uncertainty, and the overall uncertainty of the RF model was lower than that of the XGBoost model. The soil properties showed high spatial heterogeneity based on the models with variable selection. Remote sensing covariates (particularly principal component 2) were the major factors controlling the distribution of the soil organic carbon. Human activity covariates (mainly land use) and organism covariates (mainly potential evapotranspiration) played a predominant role in driving the distribution of the soil total and soil available phosphorus, respectively. This study indicates the importance of variable selection for predicting multiple soil properties and mapping their spatial distribution in sub-watersheds.Keywords
Funding Information
- Jiangxi Geological Bureau Young Science and Technology Leader Training Programme Project (2022JXDZKJRC08, 2022YFD1900601-4)
- National Key Research and Development Program of China (2022JXDZKJRC08, 2022YFD1900601-4)
This publication has 62 references indexed in Scilit:
- Effects of transitioning from conventional to organic farming on soil organic carbon and microbial community: a comparison of long-term non-inversion minimum tillage and conventional tillageBiology and Fertility of Soils, 2024
- UAV-based multispectral and thermal cameras to predict soil water content – A machine learning approachComputers and Electronics in Agriculture, 2022
- Regional mapping of soil organic matter content using multitemporal synthetic Landsat 8 images in Google Earth EngineCATENA, 2022
- Soil organic carbon prediction using phenological parameters and remote sensing variables generated from Sentinel-2 imagesCATENA, 2021
- Land use drives the spatial variability of soil phosphorus in the Hexi Corridor, ChinaBiogeochemistry, 2021
- Digital mapping of the soil thickness of loess deposits over a calcareous bedrock in central FranceCATENA, 2021
- Machine learning for digital soil mapping: Applications, challenges and suggested solutionsEarth-Science Reviews, 2020
- Mapping stocks of soil total nitrogen using remote sensing data: A comparison of random forest models with different predictorsComputers and Electronics in Agriculture, 2019
- Phosphorus fractions in subtropical soils depending on land useEuropean Journal of Soil Biology, 2018
- Estimation of prediction error by using K-fold cross-validationStatistics and Computing, 2009