Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables

Citation
Ja. Blackard et Dj. Dean, Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables, COMP EL AGR, 24(3), 1999, pp. 131-151
Citations number
33
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Agriculture/Agronomy
Journal title
COMPUTERS AND ELECTRONICS IN AGRICULTURE
ISSN journal
0168-1699 → ACNP
Volume
24
Issue
3
Year of publication
1999
Pages
131 - 151
Database
ISI
SICI code
0168-1699(199912)24:3<131:CAOANN>2.0.ZU;2-0
Abstract
This study compared two alternative techniques for predicting forest cover types from cartographic variables. The study evaluated four wilderness area s in the Roosevelt National Forest, located in the Front Range of northern Colorado. Cover type data came from US Forest Service inventory information , while the cartographic variables used to predict cover type consisted of elevation, aspect, and other information derived from standard digital spat ial data processed in a geographic information system (GIS). The results of the comparison indicated that a feedforward artificial neural network mode l more accurately predicted forest cover type than did a traditional statis tical model based on Gaussian discriminant analysis. (C) 1999 Elsevier Scie nce B.V. All rights reserved.