General-purpose machine-learned potential for 16 elemental metals and their alloys
Journal article, 2024
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.
Author
Keke Song
University of Science and Technology Beijing
Rui Zhao
Hunan University
Jiahui Liu
University of Science and Technology Beijing
Yanzhou Wang
University of Science and Technology Beijing
Aalto University
Eric Lindgren
Chalmers, Physics, Condensed Matter and Materials Theory
Yong Wang
Nanjing University
Shunda Chen
The George Washington University School of Engineering and Applied Science
Ke Xu
Chinese University of Hong Kong
Ting Liang
Chinese University of Hong Kong
Penghua Ying
Tel Aviv University
Nan Xu
College of Chemical and Biological Engineering, Zhejiang University
Institute of Zhejiang University-Quzhou
Zhiqiang Zhao
Nanjing University of Aeronautics and Astronautics
Jiuyang Shi
Nanjing University
Junjie Wang
Nanjing University
Shuang Lyu
The University of Hong Kong
Zezhu Zeng
The University of Hong Kong
Shirong Liang
Harbin Institute of Technology
Haikuan Dong
Bohai University
Ligang Sun
Harbin Institute of Technology
Yue Chen
The University of Hong Kong
Zhuhua Zhang
Nanjing University of Aeronautics and Astronautics
Wanlin Guo
Nanjing University of Aeronautics and Astronautics
Ping Qian
University of Science and Technology Beijing
Jian Sun
Nanjing University
Paul Erhart
Chalmers, Physics
Tapio Ala-Nissila
Loughborough University
Aalto University
Yanjing Su
University of Science and Technology Beijing
Zheyong Fan
Bohai University
Nature Communications
2041-1723 (ISSN) 20411723 (eISSN)
Vol. 15 1 10208Hydrogen trapping by carbides in steel
Swedish Research Council (VR) (2021-05072), 2021-12-01 -- 2025-11-30.
SwedNESS
Swedish Foundation for Strategic Research (SSF) (GSn15-0008), 2017-01-01 -- 2020-12-31.
Swedish Foundation for Strategic Research (SSF) (GSn15-0008), 2016-07-01 -- 2021-06-30.
Phase behavior and electronic properties of mixed halide perovskites from atomic scale simulations
Swedish Research Council (VR) (2020-04935), 2020-12-01 -- 2024-11-30.
Subject Categories
Condensed Matter Physics
DOI
10.1038/s41467-024-54554-x
Related datasets
Source Data for the manuscript: General-purpose machine-learned potential for 16 elemental metals and their alloys [dataset]
DOI: https://doi.org/10.5281/zenodo.13956357