Available technologies for Earth observation offer a wide range of predictors relevant to Digital Soil Mapping (DSM). However, models with a large number of predictors, as well as, the existence of multicollinearity among the data, may be ineffective in the mapping of classes and soil properties. The aim of this study was to use the Principal Component Analysis (PCA) to reduce the number of predictors in the multinomial logistic regression (MLR) used in soil mapping. Nine environmental covariates, related to the relief factor of soil formation, were derived from a digital elevation model and named the original variables, which were submitted to PCA and transformed into principal components (PC). The MLR were developed using the terrain attributes and the PC as explanatory variables. The soil map generated from three PC (65.6% of the original variance) had a kappa index of 37.3%, lower than the 48.5% achieved by the soil map generated from all nine original variables.
pedometric; multivariate statistical analysis; soil survey
