A Comparative Study of SVM and RF Methods for Classification of Alteration Zones Using Remotely Sensed Data

Identification and mapping of the significant alterations are the main objectives of the exploration geochemical surveys. The field study is time-consuming and costly in order to produce the classified maps. Therefore, processing of the remotely sensed data, which provides timely and multi-band (multi-layer) data, can be substituted for the field study. In this work, the Advanced Space borne Thermal Emission and Reflection Radiometer (ASTER) imagery is used for alteration classification by applying two new methods of machine learning including random forest and support vector machine. The 14 band ASTER and 19 derivative data layers extracted from ASTER including band ratio and PC imagery are used as the training datasets in order to improve the results. Comparison of the analytical results achieved from the two mentioned methods confirm that the SVM model has a sufficient accuracy and a more powerful performance than the RF model for alteration classification in the studied area.