APPLICATION OF AN ARTIFICIAL NEURAL NETWORK TO LAND-COVER CLASSIFICATION OF THEMATIC MAPPER IMAGERY

This paper explores the applicability of an artificial neural network (ANN) approach to land-cover classification of Thematic Mapper imagery. The ANN is presented training site examples to "learn" the association between these sites and the desired land-cover classes. The classification produced by the neural network is comparable to a conventional supervised classification using the same training sites. The ANN used in this research is a software simulation developed at the Jet Propulsion Laboratory. The motivations for the research are to substantiate the efficacy of a neural network for satellite image processing and to determine design parameters for future hardware implementation. © 1990.