Machine learning interatomic potentials (MLIPs) with broad chemical flexibility are important for atomistic simulations of compositionally complex materials such as high-entropy alloys. Here, we study two state-of-the-art MLIP frameworks, the neuroevolution potential (NEP) and the graph atomic cluster expansion (GRACE), for 16 elemental metals and multicomponent alloys. GRACE potential with Finnis-Sinclair type shows substantially higher training efficiency and consistently, though only slightly, better accuracy for mechanical properties, thermal stability, and chemical extrapolation. In contrast, NEP achieves an approximately 60-fold higher inference speed, making it attractive for million-atom molecular dynamics simulations. We further examine uncertainty quantification strategies and find that ensemble-based uncertainty correlates robustly with model error, whereas D-optimality is less reliable for the systems considered here. Large-scale nonequilibrium molecular dynamics simulations of shock propagation further show that NEP, combined with ensemble-based uncertainty quantification, enables efficient and reliable simulations under extreme dynamic conditions.
@article{arxiv.2604.01642,
title = {Machine Learning Interatomic Potentials for Million-Atom Simulations of Multicomponent Alloys},
author = {Fei Shuang and Penghua Ying and Kai Liu and Zixiong Wei and Fengxian Liu and Zheyong Fan and Minqiang Jiang and Poulumi Dey},
journal= {arXiv preprint arXiv:2604.01642},
year = {2026}
}