Machine learning based approach for zircon classification and origin

Abstract

Zircon, a stable paragenetic mineral in various geological environments, has been recognized as a great tool to study the ages of primary rocks. Trace elements of zircons thus can record the geological evolution processes. Zircon-associated trace elements have been long studied for zircon classification and formation traditionally using binary diagram technique, classical examples including Th-U and LaN-(Sm/La)N diagrams. However, with the massive increase of zircon research, the traditional binary diagrams currently cannot precisely classify zircon types because the binary plot cannot demonstrate the higher dimensional information. It therefore significantly restricts a clear understanding of zircon formation. To address the research gap, we performed the machine-learning-based approaches on 3498 zircon trace-element data of different zircon genetic types, producing high-dimensional zircon-classification diagram plots. We applied and tested four machine learning methods (random forest, support vector machine, artificial neural network, and k-nearest neighbor) and proposed that support vector machine can best contribute to zircon genetic classification study, with an 86.8% accuracy in the prediction of zircon type and formation. In addition to the high-dimensional zircon classification diagram, this work massively improves the accuracy of zircon formation analyses by trace elements, which benefit future studies in zircons. Using the machine learning approach on zircon trace element big data is an effective multidisciplinary exploration of the modern data science technique in the geochemistry study.