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.
Highlights
Soil organic carbon (SOC) is the organic carbon component of soil, consisting of living soil biota and dead biotic material derived from biomass
To map the spatial distribution of a vital ecological indicator of soil quality, SOC content, six digital soil mapping (DSM) methods were developed with soil properties, climatic data, relief factors and spectral indices being environmental variables
The performance ranking of six methods from high to low was artificial neural networks kriging (ANNK), support vector machines for regression (SVR), artificial neural networks (ANN), geographically weighted regression kriging (GWRK), ordinary kriging (OK) and geographically weighted regression (GWR) based on the prediction accuracy measured by RMSE, ME, R2 and the consistency with measured values
Summary
Soil organic carbon (SOC) is the organic carbon component of soil, consisting of living soil biota and dead biotic material derived from biomass. Small changes in the SOC could result in significant impacts on the atmospheric carbon concentration [3]. This makes SOC an important ecological indicator of the greenhouse effect, as well as a major global change driver, due to its high sensitivity to human disturbance [4,5]. SOC is involved in soil quality and ecosystem services like food production. It plays a significant role in supplying nutrients and the formation of improving soil structure [8]. Accurate SOC content mapping is critically important for monitoring the baseline of the carbon pool, as well as its role in climate change and food security [9,10]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
