Decision trees for digital soil mapping on subtropical basaltic steeplands
DOI:
https://doi.org/10.1590/S0103-90162011000200006Keywords:
GIS, soil survey, terrain analysisAbstract
When soil surveys are not available for land use planning activities, digital soil mapping techniques can be of assistance. Soil surveyors can process spatial information faster, to assist in the execution of traditional soil survey or predict the occurrence of soil classes across landscapes. Decision tree techniques were evaluated as tools for predicting the ocurrence of soil classes in basaltic steeplands in South Brazil. Several combinations of types of decicion tree algorithms and number of elements on terminal nodes of trees were compared using soil maps with both original and simplified legends. In general, decision tree analysis was useful for predicting occurrence of soil mapping units. Decision trees with fewer elements on terminal nodes yield higher accuracies, and legend simplification (aggregation) reduced the precision of predictions. Algorithm J48 had better performance than BF Tree, RepTree, Random Tree, and Simple Chart.Downloads
Download data is not yet available.
Downloads
Published
2011-04-01
Issue
Section
Soils and Plant Nutrition
License
All content of the journal, except where identified, is licensed under a Creative Common attribution-type BY-NC.How to Cite
Decision trees for digital soil mapping on subtropical basaltic steeplands . (2011). Scientia Agricola, 68(2), 167-174. https://doi.org/10.1590/S0103-90162011000200006