Machine Learning Interatomic Potentials for Million-Atom Simulations of Multicomponent Alloys
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917381926813696 |
|---|---|
| author | Shuang, Fei Ying, Penghua Liu, Kai Wei, Zixiong Liu, Fengxian Fan, Zheyong Jiang, Minqiang Dey, Poulumi |
| author_facet | Shuang, Fei Ying, Penghua Liu, Kai Wei, Zixiong Liu, Fengxian Fan, Zheyong Jiang, Minqiang Dey, Poulumi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01642 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Machine Learning Interatomic Potentials for Million-Atom Simulations of Multicomponent Alloys Shuang, Fei Ying, Penghua Liu, Kai Wei, Zixiong Liu, Fengxian Fan, Zheyong Jiang, Minqiang Dey, Poulumi Materials Science 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. |
| title | Machine Learning Interatomic Potentials for Million-Atom Simulations of Multicomponent Alloys |
| topic | Materials Science |
| url | https://arxiv.org/abs/2604.01642 |