Application of Dirichlet Process and Support Vector Machine Techniques for Mapping Alteration Zones Associated with Porphyry Copper Deposit Using ASTER Remote Sensing Imagery

The application of machine learning (ML) algorithms for processing remote sensing data is momentous, particularly mapping hydrothermal alteration zones associated with porphyry copper deposits. unsupervised Dirichlet Process (DP) and the supervised Support Vector Machine (SVM) techniques can be executed main objective this investigation to practice an algorithm that accurately model best training as input methods such SVM. For purpose, Zefreh deposit located in Urumieh-Dokhtar Magmatic Arc (UDMA) central Iran was selected used data. Initially, using ASTER data, different were detected by Band Ratio, Relative Depth (RBD), Linear Spectral Unmixing (LSU), Feature Fitting (SFF), Orthogonal Subspace Projection (OSP) techniques. Then, DP method, exact extent each determined. Finally, alterations identify similar full scene SVM Angle Mapper (SAM) methods. Several high potential identified study area. Field surveys laboratory analysis validate image results. This demonstrates deposits broadly applicable prospectivity many metallogenic provinces around world.