Data mining to infer soil-landscape relationships in digital soil mapping

Abstract

The objective of this work was to develop a methodology for digital soil mapping at a 1:100,000 scale by applying data mining techniques to preexisting relief descriptors and data from pedological and geological maps. A digital database was created from topographic and thematic maps, and allowed the generation of a digital elevation model (DEM) of the Dois Córregos (SP, Brazil) sheet (1:50,000 scale). The slope gradient, slope profile, contour profile, basin contributing area, and diagonal distance to drainage geomorphometric parameters were extracted from the DEM. The matrix which associated this georeferred data was analyzed by means of decision trees within the Weka machine-learning environment, and a model for soil mapping unit prediction was generated. The overall model accuracy increased from 54 to 61% when soil classes with no chances of being predicted were excluded. The association of data mining techniques with geographical information systems produced digital soil maps feasible to be used in studies requiring less detail than those made with the original reference soil maps.