MACE Foundation Models for Lattice Dynamics: A Benchmark Study on Double Halide Perovskites

TL;DR

This study benchmarks MACE foundation models against DFT data for predicting the dynamic stability of double halide perovskites, revealing strengths in weakly anharmonic materials and highlighting sources of prediction errors.

Contribution

It provides a comprehensive benchmark of MACE models for inorganic solids, emphasizing the impact of training data size and analyzing error sources in stability predictions.

Findings

Model accuracy improves with more training data.

Weakly anharmonic materials are predicted more accurately.

Main error source is force amplification in phonon property prediction.

Abstract

Recent developments in materials informatics and artificial intelligence has led to the emergence of foundational energy models for material chemistry, as represented by the suite of MACE-based foundation models, bringing a significant breakthrough in universal potentials for inorganic solids. As to all method developments in computational materials science, performance benchmarking against existing high-level data with focusing on specific applications, is critically needed to understand the limitations in the models, thus facilitating the ongoing improvements in the model development process, and occasionally, leading to significant conceptual leaps in materials theory. Here, using our own published DFT (Density Functional Theory) database of room-temperature dynamic stability and vibrational anharmonicity for $\sim2000$ cubic halide double perovskites, we benchmarked the performances of four different variants of the MACE foundation models for screening the dynamic stabilities of inorganic solids. Our analysis shows that, as anticipated, the model accuracy improves with more training data. The dynamic stabilities of weakly anharmonic materials (as predicted by DFT) are more accurately reproduced by the foundation model, than those highly anharmonic and dynamically unstable ones. The predominant source of error in predicting the dynamic stability arises predominantly from the amplification of errors in atomic forces when predicting the harmonic phonon properties through the computation of the Hessian matrix, less so is the contribution from possible differences in the range of the configurational spaces that are sampled by DFT and the foundation model in molecular dynamics. We hope that our present findings will stimulate future works towards more physics-inspired approaches in assessing the accuracy of foundation models for atomistic modelling.