Potassic and Phyllic Alteration Zoning Based on the Results of 3D Modeling of Fluid Inclusion Data by Artificial Neural Networks

In recent years, economic geology studies have become very popular method in mineral exploration studies. Modeling fluid inclusion data is one of the common studies in economic geology. In this research artificial neural networks method, as one of the machine learning algorithms, is used for three-dimensional modeling and application of the results of fluid inclusion analysis in Sungun porphyry copper deposit. For this purpose, fluid inclusion data is used for directly separation of related alteration zones with mineralization (Potassic, Phyllic and Potassic- Phyllic). Due to the relation that exists between alteration zones and mineralization areas, based on 173 fluid inclusion data the separation of alteration zones is modeled by artificial neural networks method in Sungun porphyry copper deposit. According to the validation studies, it can be concluded that precision of this model is appropriate (83%) and trained model could be used for separation of alteration zones in Sungun porphyry copper deposit.