Benchmarking Chemically Scalable Machine-Learning Interatomic Potentials for Large-Scale Simulations of Multicomponent Alloys

Abstract

Machine learning interatomic potentials (MLIPs) with broad chemical flexibility are essential for atomistic simulations of compositionally complex alloys, but their deployment in large-scale molecular dynamics requires a balance among accuracy, efficiency, stability, transferability, and uncertainty quantification. Here, we benchmark two chemically scalable MLIP frameworks, neuroevolution potential (NEP) and graph atomic cluster expansion (GRACE), for 16 elemental metals and their multicomponent alloys. GRACE-FS shows higher training efficiency and generally better average accuracy, chemical transferability, and finite-temperature robustness, whereas UNEP-v1 provides substantially higher inference speed and remains competitive in selected stress and large-error metrics. We further show that chemical transferability is closely linked to high-temperature MD stability in highly multicomponent environments and that ensemble-based uncertainty provides a more reliable error indicator than D-optimality for the heterogeneous systems considered here. Finally, three-million-atom shock simulations demonstrate that UNEP-v1, combined with ensemble uncertainty, enables uncertainty-aware simulations under extreme dynamic conditions, yielding robust global spall-strength predictions while revealing model sensitivity in local damage pathways. These results provide practical guidelines for selecting and deploying MLIPs in large-scale simulations of multicomponent alloys.