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.

References in corpus (15)

• VASPKIT: A User-friendly Interface Facilitating High-throughput Computing and Analysis Using VASP Code
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• Active learning of linearly parametrized interatomic potentials
• Probing the ultimate limits of metal plasticity
• Scalable Parallel Algorithm for Graph Neural Network Interatomic Potentials in Molecular Dynamics Simulations
• General-purpose machine-learned potential for 16 elemental metals and their alloys
• Maximum strength and dislocation patterning in multi-principal element alloys
• Molecular dynamics simulations of heat transport using machine-learned potentials: A mini review and tutorial on GPUMD with neuroevolution potentials
• Efficiency, Accuracy, and Transferability of Machine Learning Potentials: Application to Dislocations and Cracks in Iron
• Highly efficient path-integral molecular dynamics simulations with GPUMD using neuroevolution potentials: Case studies on thermal properties of materials
• Machine-learning interatomic potentials from a users perspective: A comparison of accuracy, speed and data efficiency
• NEP89: Universal neuroevolution potential for inorganic and organic materials across 89 elements
• Universal machine learning interatomic potentials poised to supplant DFT in modeling general defects in metals and random alloys
• Efficient GPU-Accelerated Training of a Neuroevolution Potential with Analytical Gradients