Local-environment-guided selection of atomic structures for the development of machine-learning potentials

Li, Renzhe1,2; Zhou, Chuan1; Singh, Akksay1,3,4; Pei, Yong2; Henkelman, Graeme3,4; Li, Lei1

2024-02-21

10.1063/5.0187892

JOURNAL OF CHEMICAL PHYSICS   影响因子和分区

0021-9606

1089-7690

Machine learning potentials (MLPs) have attracted significant attention in computational chemistry and materials science due to their high accuracy and computational efficiency. The proper selection of atomic structures is crucial for developing reliable MLPs. Insufficient or redundant atomic structures can impede the training process and potentially result in a poor quality MLP. Here, we propose a local-environment-guided screening algorithm for efficient dataset selection in MLP development. The algorithm utilizes a local environment bank to store unique local environments of atoms. The dissimilarity between a particular local environment and those stored in the bank is evaluated using the Euclidean distance. A new structure is selected only if its local environment is significantly different from those already present in the bank. Consequently, the bank is then updated with all the new local environments found in the selected structure. To demonstrate the effectiveness of our algorithm, we applied it to select structures for a Ge system and a Pd13H2 particle system. The algorithm reduced the training data size by around 80% for both without compromising the performance of the MLP models. We verified that the results were independent of the selection and ordering of the initial structures. We also compared the performance of our method with the farthest point sampling algorithm, and the results show that our algorithm is superior in both robustness and computational efficiency. Furthermore, the generated local environment bank can be continuously updated and can potentially serve as a growing database of feature local environments, aiding in efficient dataset maintenance for constructing accurate MLPs.

SCI ; EI

英语

第一 ; 通讯

National Natural Science Foundation of Chinahttps://doi.org/10.13039/501100001809[2022YFA1503102] ; National Key R&D Program of China[92270103] ; National Natural Science Foundation of China[ZDSYS20210709112802010] ; Shenzhen Key Laboratory of Micro/Nano-Porous Functional Materials (SKLPM)[JCYJ20210324115809026]

Chemistry ; Physics

Chemistry, Physical ; Physics, Atomic, Molecular & Chemical

WOS:001168136100003

AIP Publishing

CHEMISTRY

Web of Science

1.Southern Univ Sci & Technol, Shenzhen Key Lab Micro Nanoporous Funct Mat SKLPM, Dept Mat Sci & Engn, Shenzhen 518055, Peoples R China
2.Xiangtan Univ, Coll Chem, Xiangtan 411105, Hunan Province, Peoples R China
3.Univ Texas Austin, Dept Chem, Austin, TX 78712 USA
4.Univ Texas Austin, Inst Computat Engn & Sci, Austin, TX 78712 USA

Li, Renzhe,Zhou, Chuan,Singh, Akksay,et al. Local-environment-guided selection of atomic structures for the development of machine-learning potentials[J]. JOURNAL OF CHEMICAL PHYSICS,2024,160(7).

Li, Renzhe,Zhou, Chuan,Singh, Akksay,Pei, Yong,Henkelman, Graeme,&Li, Lei.(2024).Local-environment-guided selection of atomic structures for the development of machine-learning potentials.JOURNAL OF CHEMICAL PHYSICS,160(7).

Li, Renzhe,et al."Local-environment-guided selection of atomic structures for the development of machine-learning potentials".JOURNAL OF CHEMICAL PHYSICS 160.7(2024).