Predicting spatial distribution of soil organic carbon and total nitrogen in a typical human impacted area

The relationship between soil properties and environmental covariates is mostly nonlinear for human impacted areas. Herein, we proposed a model mapping organic carbon (SOC) total nitrogen (TN) in typical area (a small watershed of Poyang Lake, China), namely radial basis function neural network combined with agricultural land use (RBFNN_ALU). results showed that the RBFNN_ALU performs better than ordinary kriging (OK), OK (OK_ALU), geographically weighted regression (GWR), multiple linear (MLR), MLR (MLR_ALU) RBFNN. In addition, provided more detailed accurate description spatial SOC TN patterns. indicate when predicting distribution areas, non-linear models are critical properties.