Comparison of different methods of Remote Sensing and Convolutional Neural Network, Support Vector Machine and Decision Tree to determine high-potential mineralization areas in Siyah-Cheshmeh and Dizaj, West-Azerbaijan province

Nowadays, different Remote Sensing methods are one of the most practical methods in the field of mineral exploration in mountainous, border areas and without valid geochemical samples and waterway sediments in recognition phase. Spectral methods such as Mixture Tuned Matched Filtering, Spectral Angle Mapper and Linear Spectral Unmixing. The spectrum of each pixel in the image identifies different effects. This study was conducted to determine the areas of alteration, separation of different rocks and minerals, classification of images and finally to determine high potential areas of Ophiolite mineralization, Serpentinites, serpentinized harbors, Listvenites, Chromite and Manganese in Siahcheshmeh and Dizajj areas. In the processing stage, the new Automated Spectral Hourglass method based on spectral methods has been used in order to determine the altered areas and separate the minerals. In order to classify the images, Deep Convolutional Neural Network (CNN), Support Vector Machine (SVM) and Decision Tree J48 (DT) have been used. Finally, the performance of different models was compared based on different evaluation criteria and the CNN model with 98% accuracy compared to the two SVM and DT models with 96% accuracy has been used as the best model for preparing the classification map.