Prediction of soil orders with high spatial resolution: response of different classifiers to sampling density

Authors

  • Eliana Casco Sarmento UFRGS
  • Elvio Giasson UFRGS
  • Eliseu José Weber UFRGS
  • Carlos Alberto Flores EMBRAPA CLIMA TEMPERADO
  • Heinrich Hasenack UFRGS

DOI:

https://doi.org/10.1590/S1678-3921.pab2012.v47.11133

Keywords:

appellation of origin, decision tree, digital elevation model, geographic information systems, neural network, soil mapping

Abstract

The objective of this work was to evaluate sampling density on the prediction accuracy of soil orders, with high spatial resolution, in a viticultural zone of Serra Gaúcha, Southern Brazil. A digital elevation model (DEM), a cartographic base, a conventional soil map, and the Idrisi software were used. Seven predictor variables were calculated and read along with soil classes in randomly distributed points, with sampling densities of 0.5, 1, 1.5, 2, and 4 points per hectare. Data were used to train a decision tree (Gini) and three artificial neural networks: adaptive resonance theory, fuzzy ARTMap; self‑organizing map, SOM; and multi‑layer perceptron, MLP. Estimated maps were compared with the conventional soil map to calculate omission and commission errors, overall accuracy, and quantity and allocation disagreement. The decision tree was less sensitive to sampling density and had the highest accuracy and consistence. The SOM was the less sensitive and most consistent network. The MLP had a critical minimum and showed high inconsistency, whereas fuzzy ARTMap was more sensitive and less accurate. Results indicate that sampling densities used in conventional soil surveys can serve as a reference to predict soil orders in Serra Gaúcha.

Author Biographies

Eliana Casco Sarmento, UFRGS

Engenheira Agrônoma, Bióloga e mestre em Ciência do Solo, todos concluídos na UNIVERSIDADE FEDERAL DO RIO GRANDE DO SUL (UFRGS). Atualmente, estudante de doutorado no Programa de Pós-Graduação em Ciência do Solo, também pela mesma instituição.

Elvio Giasson, UFRGS

Engenheiro Agrônomo

Mestre em Ciência do Solo

Doutor em Ciência do Solo

Professor da Universidade Federal do Rio Grande do Sul

Eliseu José Weber, UFRGS

Engenheiro Agrônomo

Mestre em Sensoriamento Remoto

Doutor em Fitotecnia

Professor da Universidade Luterana do Brasil e pesquisador na Universidade Federal do Rio Grande do Sul

Carlos Alberto Flores, EMBRAPA CLIMA TEMPERADO

Engenheiro Agrônomo

Mestre em Agronomia

Pesquisador do Centro de Pesquisa Agropecuária de Clima Temperado

Heinrich Hasenack, UFRGS

Geógrafo

Mestre em Ecologia

Professor da Universidade Federal do Rio Grande do Sul

Published

2012-11-09

How to Cite

Sarmento, E. C., Giasson, E., Weber, E. J., Flores, C. A., & Hasenack, H. (2012). Prediction of soil orders with high spatial resolution: response of different classifiers to sampling density. Pesquisa Agropecuaria Brasileira, 47(9), 1395–1403. https://doi.org/10.1590/S1678-3921.pab2012.v47.11133