Data-efficient fine-tuning of foundational models for first-principles quality sublimation enthalpies

TL;DR

This paper introduces a data-efficient fine-tuning protocol for foundational models to accurately predict sublimation enthalpies and physical properties of molecular crystal polymorphs at finite temperature and pressure.

Contribution

It presents a novel fine-tuning method that achieves high accuracy with minimal training data, enabling practical simulations of molecular crystals at correlated electronic structure levels.

Findings

Achieves sub-kJ/mol accuracy in sublimation enthalpies with only tens of training structures.

Attains less than 1% error in densities of ice polymorphs at finite temperature and pressure.

Successfully simulates physical properties of ice consistent with experimental data.

Abstract

Calculating sublimation enthalpies of molecular crystal polymorphs is relevant to a wide range of technological applications. However, predicting these quantities at first-principles accuracy -- even with the aid of machine learning potentials -- is a challenge that requires sub-kJ/mol accuracy in the potential energy surface and finite-temperature sampling. We present an accurate and data-efficient protocol based on fine-tuning of the foundational MACE-MP-0 model and showcase its capabilities on sublimation enthalpies and physical properties of ice polymorphs. Our approach requires only a few tens of training structures to achieve sub-kJ/mol accuracy in the sublimation enthalpies and sub 1 % error in densities for polymorphs at finite temperature and pressure. Exploiting this data efficiency, we explore simulations of hexagonal ice at the random phase approximation level of theory at experimental temperatures and pressures, calculating its physical properties, like pair correlation function and density, with good agreement with experiments. Our approach provides a way forward for predicting the stability of molecular crystals at finite thermodynamic conditions with the accuracy of correlated electronic structure theory.