作者: Anthony M. Filippi , Christian Brannstrom , Iliyana Dobreva , David M. Cairns , Daehyun Kim
关键词:
摘要: The Brazilian Cerrado is threatened by agricultural land use conversion. Accurate quantification of overall and subtype distributions essential for regional monitoring. In this research, unsupervised fuzzy ARTMAP was compared against conventional k-means classification agriculture, based on Hyperion satellite data. We systematically tested a range parameters, determining the best parameter combinations. effect an additional surface liquid-water input vector also tested. Similar results were obtained when only apparent reflectance data used; ARTMAP, however, generally markedly more accurate than included.