Digital soil mapping using soilgrids and national soil data in Cameroon

This study evaluates the SoilGrids as predictor, using point data from the Cameroon national soil profiles data compilation, together with a set of covariates representing soil forming factors. Much effort was placed on the preparation of the Cameroon soil database (‘Camsodat 0.1’). We predicted Soil Organic Carbon (SOC) and clay content at 250 m resolution in the test region (North Region of Cameroon), at standard GlobalSoilMap depths. Random forest regression provided models fitting with R² up to 0.59. The inclusion of SoilGrids as additional covariates could slightly improve predictions with R² up to 0.61.