論文

2018年6月21日

Linearized machine-learning interatomic potentials for non-magnetic elemental metals: Limitation of pairwise descriptors and trend of predictive power

Journal of Chemical Physics
  • Akira Takahashi
  • ,
  • Atsuto Seko
  • ,
  • Isao Tanaka

148
23
開始ページ
234106
終了ページ
記述言語
英語
掲載種別
研究論文(学術雑誌)
DOI
10.1063/1.5027283
出版者・発行元
American Institute of Physics Inc.

Machine-learning interatomic potential (MLIP) has been of growing interest as a useful method to describe the energetics of systems of interest. In the present study, we examine the accuracy of linearized pairwise MLIPs and angular-dependent MLIPs for 31 elemental metals. Using all of the optimal MLIPs for 31 elemental metals, we show the robustness of the linearized frameworks, the general trend of the predictive power of MLIPs, and the limitation of pairwise MLIPs. As a result, we obtain accurate MLIPs for all 31 elements using the same linearized framework. This indicates that the use of numerous descriptors is the most important practical feature for constructing MLIPs with high accuracy. An accurate MLIP can be constructed using only pairwise descriptors for most non-transition metals, whereas it is very important to consider angular-dependent descriptors when expressing interatomic interactions of transition metals.

リンク情報
DOI
https://doi.org/10.1063/1.5027283
ID情報
  • DOI : 10.1063/1.5027283
  • ISSN : 0021-9606
  • SCOPUS ID : 85049101493

エクスポート
BibTeX RIS