Digital soil mapping of soil classes using soil maps in the arid region southeastern Iran

Maps that predict the spatial distribution of soil taxonomic classes are of interest in many countries because they inform soil use and management decisions. Digital soil mapping (DSM) may have advantages over conventional soil mapping approaches as it may better capture observed spatial variability and reduce the need to aggregate soil types. A key component of any DSM activity is the method used to define the relationship between soil observations and environmental covariates. Our objective was to compare multiple logistic regression models and covariate sets for predicting soil taxonomic classes in Bam district, Kerman province. The covariate sets including (1) variables derived from digital elevation models, remote sensing and geomorphology map, (2) variables derived digital elevation model, remote sensing, geomorphology map and the soil map. Stratified sampling scheme were defined in 100000 hectares, and 126 soil profiles were excavated and described. The results of accuracy model showed that data set 2 by entering the soil maps, increased accuracy including purity of map, kappa index, Brier score, user accuracy and reliability of the producer. The results showed that machine learning techniques such as multiple logistic regression can promote traditional soil mapping, and has increased efficiency maps to transfer data and information, in addition it could be used to large group of other scientific fields