| CONDENSED MATTER: STRUCTURAL, MECHANICAL, AND THERMAL PROPERTIES |
Prev
Next
|
|
|
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 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 |
|
|
|
|
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.
|
Received: 10 July 2025
Revised: 02 September 2025
Accepted manuscript online: 05 September 2025
|
|
PACS:
|
61.82.Bg
|
(Metals and alloys)
|
| |
75.40.-s
|
(Critical-point effects, specific heats, short-range order)
|
| |
34.20.Cf
|
(Interatomic potentials and forces)
|
|
| Fund: Project supported by the Hunan Provincial Natural Science Foundation (Grant Nos. 2024JJ6190 and 2024JK2007- 1). |
Corresponding Authors:
Guo Wei, Haidong Wang
E-mail: weig0307@outlook.com;whd@hutb.edu.cn
|
Cite this article:
Dingyi Jin(金定毅), Guo Wei(魏国), and Haidong Wang(王海东) Sensitivity of short-range order prediction to machine learning potential formalisms: A case study on NbMoTaW high-entropy alloy 2025 Chin. Phys. B 34 096104
|
[1] Ritchie R O and Zheng X R 2022 Nat. Mater. 21 968
[2] Ritchie R O 2011 Nat. Mater. 10 817
[3] Belcher C H, MacDonald B E, Apelian D and Lavernia E J 2023 Prog. Mater. Sci. 137 101140
[4] Miracle D B and Senkov O N 2017 Acta Mater. 122 448
[5] George E P, Raabe D and Ritchie R O 2019 Nat. Rev. Mater. 4 515
[6] Senkov O N,Wilks G B, Scott JMand Miracle D B 2011 Intermetallics 19 698
[7] Kumar P, Kim S J, Yu Q, Ell J, Zhang M, Yang Y, Kim J Y, Park H K, Minor A M, Park E S and Ritchie R O 2023 Acta Mater. 245 118620
[8] Senkov O N, Miracle D B, Chaput K J and Couzinie J P 2018 J. Mater. Res. 33 3092
[9] George E P, Curtin W A and Tasan C C 2020 Acta Mater. 188 435
[10] Trivedi P B, Asay J R, Gupta Y M and Field D P 2007 J. Appl. Phys. 102 83513
[11] Yang X, Zeng X, Wang J, Wang J, Wang F and Ding J 2019 Mech. Mater. 135 98
[12] Zhu Y, Hu J, Wei Q, Zhang J, Sun Y, Luo G and Shen Q 2023 Mech. Mater. 186 104809
[13] LiW, Chen S, Aitken Z and Zhang Y W 2023 Int. J. Plast. 168 103691
[14] Li W, Xiang M, Aitken Z H, Chen S, Xu Y, Yang X, Pei Q, Wang J, Li X, Vastola G, Gao H and Zhang Y W 2024 Int. J. Plast. 178 104010
[15] Wang C, Peng Peng and Lai W S Chin. Phys. B 34 18101
[16] Frank J T, Unke O T, Müller K R and Chmiela S 2024 Nat. Commun. 15 6539
[17] Li X G, Chen C, Zheng H, Zuo Y and Ong S P 2020 npj Comput. Mater. 6 70
[18] Gong X, Louie S G, Duan W and Xu Y 2024 Nat. Comput. Sci. 4 752
[19] Musaelian A, Batzner S, Johansson A, Sun L, Owen C J, Kornbluth M and Kozinsky B 2023 Nat. Commun. 14 579
[20] Bertin N, Carson R, Bulatov V V, Lind J and Nelms M 2023 Acta Mater. 260 119336
[21] Fan Z, Zeng Z, Zhang C, Wang Y, Song K, Dong H, Chen Y and Ala- Nissila T 2021 Phys. Rev. B 104 104309
[22] Song K, Zhao R, Liu J, Wang Y, Lindgren E, Wang Y, Chen S, Xu K, Liang T, Ying P, Xu N, Zhao Z, Shi J, Wang J, Lyu S, Zeng Z, Liang S, Dong H, Sun L, Chen Y, Zhang Z, Guo W, Qian P, Sun J, Erhart P, Ala-Nissila T, Su Y and Fan Z 2024 Nat. Commun. 15 10208
[23] Fisher J C 1954 Acta Metall. 2 9
[24] Santos-Florez P A, Dai S C, Yao Y, Yanxon H, Li L, Wang Y J, Zhu Q and Yu X X 2023 Acta Mater. 255 11904
[25] Shi J, Liang Z,Wang J, Pan S, Ding C,Wang Y,Wang H T, Xing D and Sun J 2023 Phys. Rev. Lett. 131 146101
[26] Chen S, Aitken Z H, Pattamatta S, Wu Z, Yu Z G, Srolovitz D J, Liaw P K and Zhang Y W 2021 Nat. Commun. 12 4953
[27] Han Y, Chen H, Sun Y, Liu J, Wei S, Xie B, Zhang Z, Zhu Y, Li M, Yang J, Chen W, Cao P and Yang Y 2024 Nat. Commun. 15 6486
[28] Li L, Du J P, Ogata S and Inui H 2024 Acta Mater. 269 119775
[29] Ying P, Qian C, Zhao R, Wang Y, Xu K, Ding F, Chen S and Fan Z 2025 Chem. Phys. Rev. 6 11310
[30] Thompson A P, Swiler L P, Trott C R, Foiles S M and Tucker G J 2015 J. Comput. Phys. 285 316
[31] Fan Z,Wang Y, Ying P, Song K,Wang J,Wang Y, Zeng Z, Xu K, Lindgren E, Rahm J M, Gabourie A J, Liu J, Dong H, Wu J, Chen Y, Zhong Z, Sun J, Erhart P, Su Y and Ala-Nissila T 2022 J. Chem. Phys. 157 114801
[32] Song K, Liu J, Chen S, Fan Z, Su Y and Qian P 2024 arXiv:2404.13694 [cond-mat.mtrl-sci]
[33] Xu K, Bu H, Pan S, et al. 2025 Mater. Genome Eng. Adv. 3 e70028
[34] Liu J, Byggmästar J, Fan Z, Bai B, Qian P and Su Y 2025 J. Nucl. Mater. 616 156004
[35] Pei Z, Zhang X, Eisenbach M and Liaw P K 2025 Acta Mater. 286 120713 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
