Modelling complex proton transport phenomena -- Exploring the limits of fine-tuning and transferability of foundational machine-learned force fields

TL;DR

This study demonstrates that machine-learned force fields, with minimal fine-tuning, can accurately model proton transport in solid acids over long timescales, surpassing traditional AIMD simulations in capturing experimental behaviors.

Contribution

The paper shows that a foundation MLFF can be fine-tuned with minimal data to accurately simulate proton transport phenomena in solid acids, improving upon prior AIMD limitations.

Findings

MLFF achieves near-quantitative agreement with AIMD after minimal fine-tuning

Long-term MD with MLFF captures correct diffusion and activation energy trends

MLFF-based simulations align with experimental observations, unlike previous AIMD results

Abstract

The solid acids CsH$_2$PO$_4$ and Cs$_7$(H$_4$PO$_4$)(H$_2$PO$_4$)$_8$ pose significant challenges for the simulation of proton transport phenomena. In this work, we use the recently developed machine-learned force field (MLFF) MACE to model the proton dynamics on nanosecond time scales for these systems and compare its performance with long-term ab initio molecular dynamics (AIMD) simulations. The MACE-MP-0 foundation model shows remarkable performance for all observables derived from molecular dynamics (MD) simulations, but minor quantitative discrepancies remain compared to the AIMD reference data. However, we show that minimal fine-tuning -- fitting to as little as 1 ps of AIMD data -- leads to full quantitative agreement between the radial distribution functions of MACE force field and AIMD simulations. In addition, we show that traditional long-term AIMD simulations fail to capture the correct qualitative trends in diffusion coefficients and activation energies for these solid acids due to the limited accessible time scale. In contrast, accurate and convergent diffusion coefficients can be reliably obtained through multi-nanosecond long MD simulations using machine-learned force fields. The obtained qualitative and quantitative behavior of the converged diffusion coefficients and activation energies now matches the experimental trends for both solid acids, in contrast to previous AIMD simulations that yielded a qualitatively wrong picture.