A Comparative Assessment of Geostatistical, Machine Learning, and Hybrid Approaches for Mapping Topsoil Organic Carbon Content

Abstract

Accurate digital soil mapping (DSM) of soil organic carbon (SOC) is still a challenging subject because of its spatial variability and dependency. This study is aimed at comparing six typical methods in three types of DSM techniques for SOC mapping in an area surrounding Changchun in Northeast China. The methods include ordinary kriging (OK) and geographically weighted regression (GWR) from geostatistics, support vector machines for regression (SVR) and artificial neural networks (ANN) from machine learning, and geographically weighted regression kriging (GWRK) and artificial neural networks kriging (ANNK) from hybrid approaches. The hybrid approaches, in particular, integrated the GWR from geostatistics and ANN from machine learning with the estimation of residuals by ordinary kriging, respectively. Environmental variables, including soil properties, climatic, topographic, and remote sensing data, were used for modeling. The mapping results of SOC content from different models were validated by independent testing data based on values of the mean error, root mean squared error and coefficient of determination. The prediction maps depicted spatial variation and patterns of SOC content of the study area. The results showed the accuracy ranking of the compared methods in decreasing order was ANNK, SVR, ANN, GWRK, OK, and GWR. Two-step hybrid approaches performed better than the corresponding individual models, and non-linear models performed better than the linear models. When considering the uncertainty and efficiency, ML and two-step approach are more suitable than geostatistics in regional landscapes with the high heterogeneity. The study concludes that ANNK is a promising approach for mapping SOC content at a local scale.

Investigating Spatial and Vertical Patterns of Wetland Soil Organic Carbon Concentrations in China’s Western Songnen Plain by Comparing Different Algorithms

“…OK is a geostatistical technique and is widely used. Based on regionalized variables, it can generate an optimal unbiased estimated surface based on a semivariogram [15]. This semivariogram can be constructed with GS+ (version 9.0, Leland Stanford Junior University, Stanford, CA, USA).…”

“…Studies revealed that the prediction techniques for soil attributes are based mainly on spatial correlation, including autocorrelation and mutual correlation [14]. Commonly used autocorrelation technologies include inverse distance weighting (IDW) and ordinary kriging (OK) [15]. Spatial mutual-correlation-based predictions integrate field observations and environmental variables through quantitative relationships [16].…”

Remote Sensing Applications in Monitoring of Protected Areas

“…Remote sensing has unique advantages in monitoring frontier lands, which are always in remote and difficult-to-reach locations. Examples have included: satellite-observed dynamics of lake-rich regions across the Tibetan Plateau and the Arctic; forest disturbance and dynamics in Siberia; the assessment of the complex Amur tiger and Far Eastern leopard habitats in the Russian Far East; in the landscape and ecosystem characterizations in China and Southeast Asia; in conservation efforts of tree kangaroos in Papua New Guinea; and in PAs in the Albertine Rift of Africa [46][47][48][49][50][51][52][53][54][55][56][57][58][59][60][61][62]. Remote sensing has advantages in monitoring vast habitats both inside and surrounding the PAs.…”

Remote Sensing Applications in Monitoring of Protected Areas

“…Remote sensing has unique advantages in monitoring frontier lands, which are always in remote and difficult-to-reach locations. Examples have included: satellite-observed dynamics of lake-rich regions across the Tibetan Plateau and the Arctic; forest disturbance and dynamics in Siberia; the assessment of the complex Amur tiger and Far Eastern leopard habitats in the Russian Far East; in the landscape and ecosystem characterizations in China and Southeast Asia; in conservation efforts of tree kangaroos in Papua New Guinea; and in PAs in the Albertine Rift of Africa [46][47][48][49][50][51][52][53][54][55][56][57][58][59][60][61][62]. Remote sensing has advantages in monitoring vast habitats both inside and surrounding the PAs.…”