Classification of Minerals Using Machine Learning Methods

Abstract

Minerals are the structures formed by the combination of one or more elements as a result of geological process. The discipline which examines all aspects of minerals is called mineralogy. In mineralogy science, the definition and classification of minerals are made by taking into account many properties such as physical and chemical properties, internal crystal structures and optical properties. The classification of minerals has an important place in many engineering fields and such as geology, mining, geophysics, environment and in many fields such as mineral exploration, gemology, prospecting, ore processing. Both in the field environment and then in the laboratory environment, determination of all the properties of the mineral found in the field, is quite a long process. In addition, the researcher should have a good experience in the identification and classification process. In order to shorten this process in this study, it is aimed to classify minerals taken directly from the field and photographed, with AlexNet one of the convolutional neural network (CNN) architectures. In this study, 1491 images were used in 8 classes.