EVALUATION OF DECISION TREE CLASSIFICATION ACCURACY TO MAP LAND COVER IN CAPIXABA, ACRE

Main Article Content

Symone Maria de Melo Figueiredo Luis Marcelo Tavares de Carvalho

Abstract

This study evaluated the accuracy of mapping land cover in Capixaba, state of Acre, Brazil, using decision trees. Eleven attributes were used to build the decision trees: TM Landsat datafrom bands 1, 2, 3, 4, 5, and 7; fraction images derived from linear spectral unmixing; and the normalized difference vegetation index (NDVI). The Kappa values were greater than 0,83, producing excellent classification results and demonstrating that the technique is promising for mapping land cover in the study area.

Article Details

How to Cite
FIGUEIREDO, Symone Maria de Melo; CARVALHO, Luis Marcelo Tavares de. EVALUATION OF DECISION TREE CLASSIFICATION ACCURACY TO MAP LAND COVER IN CAPIXABA, ACRE. CERNE, [S.l.], v. 12, n. 1, p. 038-047, sep. 2015. ISSN 2317-6342. Available at: <http://cerne.ufla.br/site/index.php/CERNE/article/view/397>. Date accessed: 22 sep. 2019.
Keywords
digital image classification, data mining, linear spectral unmixing, NDVI
Section
Article