Digital Mapping of Soil Organic Carbon Using UAV Images and Soil Properties in a Thermo-Erosion Gully on the Tibetan Plateau

Thermo-erosion gullies (TGs) are typical thermokarst features in upland permafrost; the soil organic carbon (SOC) of TGs has an important influence on soil quality in cold regions. The objectives of this study were to estimate the spatial distribution of SOC content in a typical TG on the northeastern Tibetan Plateau in China by using soil properties from seven different TGs and covariates from unmanned aerial vehicle (UAV) images, and to characterize the SOC content changes in four representative landscape regions (NO-Slumping, Slumping1, Slumping2, and Slumped) within this typical TG. The support vector machine (SVM) was the optimal machine learning algorithm for SOC content prediction, which explained 53.06% (R-2) of the SOC content variation. Silt content was the most influential factor which demonstrated a positive relationship with SOC content in different TGs. In addition, the SOC content in the TGs was related to the landscapes. Severe Slumping (Slumping2: 150.79 g center dot kg(-1)) had a lower SOC content than NO-Slumped (163.29 g center dot kg(-1)) and the initial slumping stage (Slumping1: 169.08 g center dot kg(-1)). The results suggested that SVM was an effective algorithm to obtain a profound understanding of the SOC content over space, while future research needs to pay more attention to the SOC content distribution in the different TGs.

Automated summary

This study estimated the spatial distribution of soil organic carbon (SOC) content in a typical thermo-erosion gully (TG) on the northeastern Tibetan Plateau in China, and characterized the SOC content changes in different landscape regions within the TG. The support vector machine (SVM) was found to be an optimal machine learning algorithm for predicting SOC content. Silt content was the most influential factor affecting SOC content in the TGs, and SOC content varied among different landscape regions. The study highlights the importance of understanding the distribution of SOC content in different TGs using SVM.