General-purpose machine-learned potential for 16 elemental metals and their alloys
Machine-learned potentials (MLPs) have exhibited remarkable accuracy, yet the lack of general-purpose MLPs for a broad spectrum of elements and their alloys limits their applicability. Here, we present a promising approach for constructing a unified general-purpose MLP for numerous elements, demonstrated through a model (UNEP-v1) for 16 elemental metals and their alloys. To achieve a complete representation of the chemical space, we show, via principal component analysis and diverse test datasets, that employing one-component and two-component systems suffices. Our unified UNEP-v1 model exhibits superior performance across various physical properties compared to a widely used embedded-atom method potential, while maintaining remarkable efficiency. We demonstrate our approach's effectiveness through reproducing experimentally observed chemical order and stable phases, and large-scale simulations of plasticity and primary radiation damage in MoTaVW alloys.
Authors
- Eric Lindgren (ORCID: https://orcid.org/0000-0002-8549-6839)
- Ligang Sun (ORCID: https://orcid.org/0000-0003-4661-5476)
- Zheyong Fan (ORCID: https://orcid.org/0000-0002-2253-8210)
- Ting Liang (ORCID: https://orcid.org/0000-0002-3116-365X)
- Wanlin Guo (ORCID: https://orcid.org/0000-0002-2302-8044)
- Haikuan Dong (ORCID: https://orcid.org/0000-0001-9870-0467)
- Keke Song
- Junjie Wang (ORCID: https://orcid.org/0000-0003-1411-3324)
- Yanjing Su (ORCID: https://orcid.org/0000-0003-2773-4015)
- Paul Erhart (ORCID: https://orcid.org/0000-0002-2516-6061)
- Ke Wei Xu (ORCID: https://orcid.org/0000-0001-5254-5297)
- Ping Qian (ORCID: https://orcid.org/0000-0003-3120-2556)
- Zhuhua Zhang (ORCID: https://orcid.org/0000-0001-6406-0959)
- Penghua Ying (ORCID: https://orcid.org/0000-0002-5758-2369)
- Shunda Chen (ORCID: https://orcid.org/0000-0002-5506-7507)
- Tapio Ala-Nissilä (ORCID: https://orcid.org/0000-0002-3210-3181)
- Jiahui Liu (ORCID: https://orcid.org/0009-0001-3396-3482)
- Yong Wang (ORCID: https://orcid.org/0000-0003-1335-8629)
- Yue Chen (ORCID: https://orcid.org/0000-0001-5811-6936)
- Jian Sun (ORCID: https://orcid.org/0000-0001-6172-9100)
- Rui Zhao (ORCID: https://orcid.org/0000-0002-0312-8478)
- Zhiqiang Zhao (ORCID: https://orcid.org/0000-0003-0272-4988)
- Nan Xu (ORCID: https://orcid.org/0000-0003-3986-6883)
- Zezhu Zeng (ORCID: https://orcid.org/0000-0001-5126-4928)
- Shuang Lyu
- Shirong Liang
- Jiuyang Shi
- Yanzhou Wang
Institutions
- Loughborough University (GB)
- Tel Aviv University (IL)
- Hunan University (CN)
- Chinese University of Hong Kong (HK)
- George Washington University (US)
- Harbin Institute of Technology (CN)
- Quzhou University (CN)
- Collaborative Innovation Center of Advanced Microstructures (CN)
- Beijing Advanced Sciences and Innovation Center (CN)
- Chalmers University of Technology (SE)
- Zhejiang University (CN)
- Nanjing University (CN)
- University of Hong Kong (HK)
- University of Science and Technology Beijing (CN)
- Bohai University (CN)
- Nanjing University of Aeronautics and Astronautics (CN)
- Aalto University (FI)
Publication Details
- Journal
- Nature Communications
- Published
- 2024-11-25
- DOI
- https://doi.org/10.1038/s41467-024-54554-x
- Citations
- 133
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 15.58
Funders
- Stiftelsen för Strategisk Forskning
- National Natural Science Foundation of China
- Academy of Finland
- Vetenskapsrådet