Burned area mapping system and fire detection system, based on neural networks and NOAA-AVHRR imagery
Abstract:New automatic systems for mapping burned areas and for fire detection, based on neural networks, were developed. The Supervised ART-II artificial neural network was employed. These two newly developed systems were applied for mapping burned areas and for fire detection in the eastern part of Spain, which suffered damage during July 1994. Images from the National Oceanic and Atmospheric Administration Advanced Very High Resolution Radiometer (NOAA-AVHRR) were used. These systems were tested using different sizes of training sets and different dynamic parameters. The data description and methodology are discussed. The full algorithm is listed.
Document Type: Research Article
Affiliations: Laboratory of Remote Sensing, LATUV, Department of Applied Physics-I, Faculty of Sciences, University of Valladolid, 47071 Valladolid, Spain
Publication date: July 10, 2001