Machine Learning for Identification of Primary Water Concentrations in Mantle Pyroxene

The H2O content of clinopyroxene (cpx) phenocrysts in basaltic magma has become an important way to evaluate the H2O content of Earth’s mantle. However, due to the diversity of substitution mechanisms for H in cpx, it is difficult to ascertain using traditional geochemical methods whether hydrogen (H) measured in cpx phenocrysts represents a primary signature that can ultimately inform estimates of the mantle water content. The Support Vector Machine (SVM) is a powerful and mature machine learning method that can classify samples into one of two groups based on the analysis of high-dimensional datasets. In this study, we collated the data on the H2O content of cpx phenocrysts in mafic rocks from around the globe, and conducted machine learning on the major element compositions and H2O content of cpx phenocrysts (1904 samples in total). Using the SVM, we defined a classifier (overall accuracy >92%) that can separate cpx that have undergone H diffusion, and thus modification of their original water content, from those that have not experienced H diffusion. As a complement to traditional geochemical methods, our SVM model is a novel approach with broad implications for refining estimates of the water content of Earth’s mantle and understanding variations of water content in magmatic systems and the water cycle in the deep Earth.

Article information: Chen, H., Su, C., Tang, Y.-Q., Li, A.-Z., Wu, S.-S., Xia, Q.-K., & Zhang Zhou, J. (2021). Machine learning for identification of primary water concentrations in mantle pyroxene. Geophysical Research Letters, 48, e2021GL095191. https://doi.org/10.1029/2021GL095191

Figure1. Operational flow chart for the support vector machine modeling.

Figure 2. (a) FeO, (b) CaO, (c) Al2O3, and (d) SiO2 compared with MgO for cpx from: positive examples, negative examples, and the test and application group.