Digital soil mapping (DSM) has been shown to be feasible to use in soil survey. Although several methods have been exploited, there is a lack in defining methodologies for doing DSM. This study tests five decision trees algorithms that have been identified as suitable (Simple Chart, Random Tree, REP Tree, BF Tree, and J48) and three digital elevation models (AsterGDEM, SRTM and SRTM V3) for DSM at semidetailed level in situations where the main differentiating factor between soil types is the relief. The use of MDE Aster GDEM and decision three algorithms J48, Simple Tree e BF Tree produced decision tree models capable of produce soil maps with larger accuracy related to reference soil maps.
soils, pedology; soil survey; data mining
