Machine Learning thermo-barometry to compare the architecture of volcanic plumbing systems across tectonic settings

Abstract:

We introduce a new approach, based on Machine Learning (ML), to estimate pre-eruptive temperatures and storage depths using clinopyroxene-melt pairs and clinopyroxene-only chemistry. The model is calibrated for magmas of a wide compositional range, it complements existing models, and it can be applied independently of tectonic setting. Additionally, it allows the identification of the main chemical exchange mechanisms occurring in response to pressure and temperature variations on the base of experimental data without a-prioriassumptions. This also implies that we can include all chemical components, which improves the performance of the thermo-barometer with respect to existing models. The general applicability of this model will promote the comparison of the architecture of plumbing systems across tectonic settings and between petrologic and geophysical studies. On the base of these initial results we are now developing a ML approach that includes all mineral phases present in volcanic products to further improve the resolution of our method.