Machine learning determines the Mg2SiO4 P-T phase diagram

TL;DR

This paper introduces a machine learning-based workflow that efficiently maps the Mg2SiO4 phase diagram, including phase boundaries and melting curves, at high pressures and temperatures relevant to Earth's mantle.

Contribution

It develops a novel machine learning-driven method combining thermodynamic integration and coexistence simulations for large-scale, accurate phase diagram determination.

Findings

Constructed a comprehensive Mg2SiO4 P-T phase diagram.

Evaluated the melting curve of forsterite.

Reduced computational costs compared to ab initio methods.

Abstract

Phase transitions among Mg2SiO4 and its high-pressure polymorphs (wadsleyite and ringwoodite) are central to mantle dynamics and deep-mantle material cycling. However, the locations and Pressure-Temperature (P-T) dependences of these phase boundaries remain debated, largely due to experimental limitations at extreme conditions and the high computational cost of first-principles free-energy calculations. Here, a machine-learning-potential driven workflow combining non-equilibrium thermodynamic integration (NETI) and two-phase coexistence simulations is employed to enable large-scale, long-timescale molecular dynamics sampling. Within this workflow, the melting curve of forsterite is evaluated and a complete P-T phase diagram is constructed. Relative to conventional ab initio approaches, this strategy reduces computational expense while retaining thermodynamic consistency in phase-stability assessment. The workflow is applicable to efficient evaluation of phase stability and thermodynamic properties in deep-Earth silicate systems.