Refining Machine Learning Potentials through Thermodynamic Theory of Phase Transitions

TL;DR

This paper introduces a top-down fine-tuning method for machine learning potentials that corrects phase transition temperature predictions to match experimental data, enhancing accuracy for material simulations.

Contribution

It presents a novel, model-agnostic fine-tuning strategy using Differentiable Trajectory Reweighting to improve phase diagram predictions of ML potentials.

Findings

Accurately corrects Titanium phase transition temperatures within tenths of kelvins.

Improves liquid-state diffusion constant predictions.

Applicable to multi-component systems with various phase transitions.

Abstract

Foundational Machine Learning Potentials can resolve the accuracy and transferability limitations of classical force fields. They enable microscopic insights into material behavior through Molecular Dynamics simulations, which can crucially expedite material design and discovery. However, insufficiently broad and systematically biased reference data affect the predictive quality of the learned models. Often, these models exhibit significant deviations from experimentally observed phase transition temperatures, in the order of several hundred kelvins. Thus, fine-tuning is necessary to achieve adequate accuracy in many practical problems. This work proposes a fine-tuning strategy via top-down learning, directly correcting the wrongly predicted transition temperatures to match the experimental reference data. Our approach leverages the Differentiable Trajectory Reweighting algorithm to minimize the free energy differences between phases at the experimental target pressures and temperatures. We demonstrate that our approach can accurately correct the phase diagram of pure Titanium in a pressure range of up to 5 GPa, matching the experimental reference within tenths of kelvins and improving the liquid-state diffusion constant. Our approach is model-agnostic, applicable to multi-component systems with solid-solid and solid-liquid transitions, and compliant with top-down training on other experimental properties. Therefore, our approach can serve as an essential step towards highly accurate application-specific and foundational machine learning potentials.