An AI-ready fine-tuning framework for accurate machine-learning interatomic potentials in solid-solid battery interfaces

TL;DR

This paper introduces FIRE, a fine-tuning framework that combines efficient sampling and replay strategies to develop highly accurate, data-efficient interatomic potentials for solid-solid battery interfaces, enabling predictive simulations at near-quantum accuracy.

Contribution

FIRE is a novel, generalizable framework that significantly improves the accuracy and efficiency of machine-learning interatomic potentials for complex battery interfaces.

Findings

Achieves sub-1 meV/atom energy errors across six systems

Requires only 10% of original training data

Reproduces experimental mechanical and electrochemical properties

Abstract

Atomistic modeling of solid-solid battery interfaces is essential for understanding electro-chemo-mechanical coupling, but the complex interfacial chemistry and heterogeneous environments pose major challenges for quantum-accurate, data-efficient modeling. Herein, we propose an approach of fine-tuning with integrated replay and efficiency (FIRE), a general framework for universal machine-learning interatomic potentials by combining efficient configurational sampling with a replay-argumented continual strategy, achieving quantum-level accuracy at moderate cost. Across six solid-solid battery interface systems, FIRE consistently achieves root-mean-square errors in energy below 1 meV/atom and in force near 20 meV/angstrom, marking an order-of-magnitude improvement over existing models while requiring only 10% of the original datasets. In addition, the fine-tuned model successfully reproduces key mechanical and electrochemical properties of the materials, in close agreement with experimental data. The FIRE offers a generalizable and data-efficient approach for developing accurate interatomic potentials across diverse materials, enabling predictive simulations beyond the reach of first-principles methods.