Separation of alteration units has an important role in exploration of ore deposits. In the past, classical methods were used for this purpose. Recently, the support vector machine (SVM), one of the most important data driven models, has been applied for geological purp More
Separation of alteration units has an important role in exploration of ore deposits. In the past, classical methods were used for this purpose. Recently, the support vector machine (SVM), one of the most important data driven models, has been applied for geological purpose. This algorithm is a useful learning system based on constrained optimization theory. In this study, the SVM algorithm with various kernels and maximum likelihood method were used to separate the alteration units of the Takht-e-Gonbad district situated in Chahar Gonbad sheet by using satellite images of the ASTER sensor. The results were analyzed and evaluated according to the field studies. Based on the achieved results and field studies, the SVM method with the RBF kernel function compared to other kernels and the maximum likelihood method had the highest accuracy (89.17%) and kappa coefficient (0.83). Thus, the SVM method for classification of alteration is more accurate compared to other discussed methods.
Manuscript profile