The discrimination of tectonic settings using trace elements in magmatic zircons: A machine learning approach

Zircon is the most important accessory mineral in geological research, and it records information on isotopes and trace elements, which is of great significance in Earth science research. Trace elements in zircons can be used to analyze the genesis of zircons, calculate the magma temperature and oxygen fugacity, and trace the magma source. Due to the limitation of visual dimensions, zircon information is mainly shown by low-dimensional diagrams in present studies, so high-dimensional relationships are difficult to determine during trace element analysis of zircons. However, with the development of machine learning, mining the high-dimensional relationships during trace element analysis of zircons has become possible. In this paper, four supervised learning algorithms including random forest, support vector machine, decision tree, and eXtreme Gradient Boosting, were implemented to analyze the trace elements of 3907 magmatic zircons from the GEOROC database, and a precise 13-dimensional data classifier model was established to distinguish the volcanic rift, ocean island, and convergent margin tectonic settings. Based on the results of accuracy, precision, recall, and F1 score, eXtreme Gradient Boosting is the best machine learning approach in this paper and its results for accuracy, precision, recall, and F1 score are 0.906, 0.907, 0.907, and 0.905, respectively. In summary, eXtreme Gradient Boosting could provide a high-dimensional discriminative approach to distinguish tectonic settings.