Soil organic matter mapping using INLA-SPDE with remote sensing based soil moisture indices and Fourier transforms decomposed variables

Abstract

Generating accurate spatial information on soil organic matter (SOM) is increasingly important in the context of global environmental change. Both prediction models and environmental covariates influence the mapping results and accuracy, making them important factors in SOM mapping. The Bayesian spatial model INLA-SPDE is an emerging model, that has shown potential in digital soil mapping (DSM), but its application is still limited. Soil moisture, which affects soil water status and the decomposition of SOM, can be a potential predictor for mapping SOM. However, the difficulty of obtaining soil moisture measurements over a large area using ground-based methods hinders its application. Recently, high spatial resolution remote sensing (RS) has provided a possible way to generate soil moisture indices over a large area. However, the effectiveness of RS-based soil moisture indices on SOM mapping is unknown. Fourier transforms decomposed (FTD) variables based on vegetation indices have been proven effective in detecting time-series patterns of crop growth, thereby improving the mapping accuracy of farmland. Yet, the effectiveness of FTD variables has not been verified in other vegetation-covered areas. This paper examines the use of INLA-SPDE with three RS-based soil moisture indices (NSDSIs) and six FTD variables for SOM mapping compared to Random Forest (RF), in a study area with diverse vegetation cover in Anhui Province, China. The finding indicates that with the optimal combination of environmental covariates, INLA-SPDE yields a higher prediction accuracy than RF, with an increase of 18% in R2. Either the RS-based soil moisture indices covariates or the FTD variables are effective in mapping SOM. When compared to using only natural environmental covariates, the best combination including RS-based soil moisture indices and FTD variables improved the mapping accuracy by 25% in terms of R2, 21% of LCCC, and 11% of RMSE. Furthermore, quantitative prediction uncertainty maps are derived based on the INLA-SPDE. This study demonstrates the effectiveness of INLA-SPDE model with the RS-based soil moisture indices and Fourier transforms decomposed variables for SOM mapping.