adaptive neuro-fuzzy inference system application for hydrothermal alteration mapping using aster data

the main problem associated with the traditional approach to image classification for the mapping of hydrothermal alteration is that materials not associated with hydrothermal alteration may be erroneously classified as hydrothermally altered due to the similar spectral properties of altered and unaltered minerals. the major objective of this paper is to investigate the potential of a neuro-fuzzy system in overcoming this problem. the proposed system is applied to the northwestern part of the kerman cenozoic magmatic arc (kcma), which hosts many areas of porphyry and vein-type copper mineralization. a software program based on an adaptive neuro-fuzzy inference system (anfis) was developed using the matlab anfis toolbox. the anfis program was used to classify advanced space-borne thermal emission and reflection radiometer (aster) data based on the spectral properties of altered and unaltered rocks. the anfis result was then compared with other classified images based on artificial neural networks (ann) and the maximum likelihood classifier (mlc). the verification of the results, based on field and laboratory investigations, revealed that the anfis method produces a more accurate map of the distribution of alteration than that obtained using ann or mlc.