中国物理B ›› 2025, Vol. 34 ›› Issue (9): 96104-096104.doi: 10.1088/1674-1056/ae039a

• • 上一篇    下一篇

Sensitivity of short-range order prediction to machine learning potential formalisms: A case study on NbMoTaW high-entropy alloy

Dingyi Jin(金定毅)1, Guo Wei(魏国)2,†, and Haidong Wang(王海东)3,‡   

  1. 1 School of Intelligent Manufacturing, Hunan First Normal University, Changsha 410082, China;
    2 Department of Physics and Helsinki Institute of Physics, University of Helsinki, P. O. Box 43, Helsinki FI-00014, Finland;
    3 School of Advanced Interdisciplinary Studies, Hunan University of Technology and Business, Changsha 410082, China
  • 收稿日期:2025-07-10 修回日期:2025-09-02 接受日期:2025-09-05 出版日期:2025-08-21 发布日期:2025-09-09
  • 通讯作者: Guo Wei, Haidong Wang E-mail:weig0307@outlook.com;whd@hutb.edu.cn
  • 基金资助:
    multi-principal element alloys|short-range order|machine-learning potential

Sensitivity of short-range order prediction to machine learning potential formalisms: A case study on NbMoTaW high-entropy alloy

Dingyi Jin(金定毅)1, Guo Wei(魏国)2,†, and Haidong Wang(王海东)3,‡   

  1. 1 School of Intelligent Manufacturing, Hunan First Normal University, Changsha 410082, China;
    2 Department of Physics and Helsinki Institute of Physics, University of Helsinki, P. O. Box 43, Helsinki FI-00014, Finland;
    3 School of Advanced Interdisciplinary Studies, Hunan University of Technology and Business, Changsha 410082, China
  • Received:2025-07-10 Revised:2025-09-02 Accepted:2025-09-05 Online:2025-08-21 Published:2025-09-09
  • Contact: Guo Wei, Haidong Wang E-mail:weig0307@outlook.com;whd@hutb.edu.cn
  • Supported by:
    Project supported by the Hunan Provincial Natural Science Foundation (Grant Nos. 2024JJ6190 and 2024JK2007- 1).

RichHTML

0

PDF (PC)

34

赞

摘要： Chemical short-range order (SRO), a phenomenon at the atomic scale resulting from inhomogeneities in the local chemical environment, is usually studied using machine learning force field-based molecular dynamics simulations due to the limitations of experimental methods. To promote the reliable application of machine potentials in high-entropy alloy simulations, first, this work uses NEP models trained on two different datasets to predict the SRO coefficients of NbMoTaW. The results show that within the same machine learning framework, there are significant differences in the prediction of SRO coefficients for the Nb-Nb atomic pair. Subsequently, this work predicts the SRO coefficients of NbMoTaW using the NEP model and the SNAP model, both of which are trained on the same dataset. The results reveal significant discrepancies in SRO predictions for like-element pairs (e.g., Nb-Nb and W-W) between the two potentials, despite the identical training data. The findings of this study indicate that discrepancies in the prediction results of SRO coefficients can arise from either the same machine learning framework trained on different datasets or different learning frameworks trained on the same dataset. This reflects possible incompleteness in the current training set's coverage of local chemical environments at the atomic scale. Future research should establish unified evaluation standards to assess the capability of training sets to accurately describe complex atomic-scale behaviors such as SRO.

关键词: multi-principal element alloys, short-range order, machine-learning potential

Abstract: Chemical short-range order (SRO), a phenomenon at the atomic scale resulting from inhomogeneities in the local chemical environment, is usually studied using machine learning force field-based molecular dynamics simulations due to the limitations of experimental methods. To promote the reliable application of machine potentials in high-entropy alloy simulations, first, this work uses NEP models trained on two different datasets to predict the SRO coefficients of NbMoTaW. The results show that within the same machine learning framework, there are significant differences in the prediction of SRO coefficients for the Nb-Nb atomic pair. Subsequently, this work predicts the SRO coefficients of NbMoTaW using the NEP model and the SNAP model, both of which are trained on the same dataset. The results reveal significant discrepancies in SRO predictions for like-element pairs (e.g., Nb-Nb and W-W) between the two potentials, despite the identical training data. The findings of this study indicate that discrepancies in the prediction results of SRO coefficients can arise from either the same machine learning framework trained on different datasets or different learning frameworks trained on the same dataset. This reflects possible incompleteness in the current training set's coverage of local chemical environments at the atomic scale. Future research should establish unified evaluation standards to assess the capability of training sets to accurately describe complex atomic-scale behaviors such as SRO.

Key words: multi-principal element alloys, short-range order, machine-learning potential

中图分类号:  (Metals and alloys)

  • 61.82.Bg
75.40.-s (Critical-point effects, specific heats, short-range order) 34.20.Cf (Interatomic potentials and forces)