Predicting active-layer soil thickness using topographic variables at a small watershed scale.

Aidi Li,Jie Zhu,Hongbin Liu,Xing Tan,Wei Wu,Claudionor R Silva

doi:10.1371/journal.pone.0183742

Aidi Li, Jie Zhu + Show 4 more

Open Access

https://doi.org/10.1371/journal.pone.0183742

Copy DOI

Abstract

Knowledge about the spatial distribution of active-layer (AL) soil thickness is indispensable for ecological modeling, precision agriculture, and land resource management. However, it is difficult to obtain the details on AL soil thickness by using conventional soil survey method. In this research, the objective is to investigate the possibility and accuracy of mapping the spatial distribution of AL soil thickness through random forest (RF) model by using terrain variables at a small watershed scale. A total of 1113 soil samples collected from the slope fields were randomly divided into calibration (770 soil samples) and validation (343 soil samples) sets. Seven terrain variables including elevation, aspect, relative slope position, valley depth, flow path length, slope height, and topographic wetness index were derived from a digital elevation map (30 m). The RF model was compared with multiple linear regression (MLR), geographically weighted regression (GWR) and support vector machines (SVM) approaches based on the validation set. Model performance was evaluated by precision criteria of mean error (ME), mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). Comparative results showed that RF outperformed MLR, GWR and SVM models. The RF gave better values of ME (0.39 cm), MAE (7.09 cm), and RMSE (10.85 cm) and higher R2 (62%). The sensitivity analysis demonstrated that the DEM had less uncertainty than the AL soil thickness. The outcome of the RF model indicated that elevation, flow path length and valley depth were the most important factors affecting the AL soil thickness variability across the watershed. These results demonstrated the RF model is a promising method for predicting spatial distribution of AL soil thickness using terrain parameters.

Highlights

Active-layer (AL) soil thickness, defined as the top layer of soil, is one of the most important factors affecting soil quality and productivity, vegetation growth, soil moisture pattern, surface and subsurface flow, and shallow landslide [1,2,3,4,5,6]
All had intermediate variability with coefficient of variation (CV) varying between 28.82% and 84.46%
Seven quantitative terrain indexes including elevation, aspect, relative slope position, valley depth, flow path length, slope height, and topographic wetness derived from digital elevation models (DEMs) were applied with multiple linear regression (MLR), support vector machines (SVM), and random forest (RF) methods

Summary

Introduction

Active-layer (AL) soil thickness, defined as the top layer of soil, is one of the most important factors affecting soil quality and productivity, vegetation growth, soil moisture pattern, surface and subsurface flow, and shallow landslide [1,2,3,4,5,6]. Predicting active-layer soil thickness using random forest. AL soil thickness is beneficial to hydro-ecological modeling, precision agriculture, and land resource management [7]. The information of AL soil thickness is derived from conventional soil survey. This method cannot offer sufficient information to satisfy the special planning (e.g. land-use planning and cropping pattern), and the application is obstructed by the high costs on time, expense and labors. Some authors used a constant value to represent AL soil thickness across the entire landscape [8, 9] that the variability of it is ignored . AL soil thickness is not constant over space in areas with complex terrain conditions. Alternative approaches are proposed to meet the demands of many applications

Objectives

Methods

Results

Discussion

Conclusion