arrow
返回

Simple machine-learned interatomic potentials for complex alloys

delete2022-08-11
delete22
delete
OA
AI
J
Jesper Byggmästar *
K
K. Nordlund
G
G. Eckerlin
DOI:10.1103/PhysRevMaterials.6.083801delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Developing data-driven machine-learning interatomic potential for materials containing many elements becomes increasingly challenging due to the vast configuration space that must be sampled by the training data. We study the learning rates and achievable accuracy of machine-learning interatomic potentials for many-element alloys with different combinations of descriptors for the local atomic environments. We show that for a five-element alloy system, potentials using simple low-dimensional descriptors can reach meV/atom-accuracy with modestly sized training datasets, significantly outperforming the high-dimensional SOAP descriptor in data efficiency, accuracy, and speed. In particular, we develop a computationally fast machine-learned and tabulated Gaussian approximation potential (tabGAP) for Mo-Nb-Ta-V-W alloys with a combination of two-body, three-body, and a new simple scalar many-body density descriptor based on the embedded atom method.
Keyword:
EMBEDDED-ATOM-METHOD
APPROXIMATION
IMPURITIES
ENERGY

期刊

Physical Review Materials 封面图
Physical Review Materials
IF:
3.4
论文数:
5.2K
被引数:
1.7W

机构

U
university of helsinki
学者数:
4.1W
论文数: 3.6W
被引数: 51
引用论文

引用论文

Machine Learning a General-Purpose Interatomic Potential for Silicon机器学习硅的通用原子间潜力
err2018-12-14
err480
errOAAI
errBartok, Albert P.; Kermode, James; Bernstein, Noam; Csanyi, Gabor
err分享
err收藏
err分享
err收藏
Photocatalytic Degradation of p-Cresol by Zinc Oxide under UV Irradiation
err2011-12-27
err0
errOAAI
errYadollah Abdollahi; Abdul Halim Abdullah; Zulkarnain Zainal; Nor Azah Yusof
err分享
err收藏
学者 查看更多内容