Exploration for the physical origin and impact of chemical short-range order in high-entropy alloys: Machine learning-assisted study

Atomic-level chemical short-range order (CSRO) in high-entropy alloys (HEAs) has ever garnered increasing attention. However, the mechanisms underlying the effects of CSRO remain poorly understood. Material informatics, through a machine learning (ML) algorithm, can fit the high-dimensional correlat...

Full description

Saved in:
Bibliographic Details
Main Authors: Panhua Shi, Zhen Xie, Jiaxuan Si, Jianqiao Yu, Xiaoyong Wu, Yaojun Li, Qiu Xu, Yuexia Wang
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Materials & Design
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0264127525003120
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850182820911120384
author Panhua Shi
Zhen Xie
Jiaxuan Si
Jianqiao Yu
Xiaoyong Wu
Yaojun Li
Qiu Xu
Yuexia Wang
author_facet Panhua Shi
Zhen Xie
Jiaxuan Si
Jianqiao Yu
Xiaoyong Wu
Yaojun Li
Qiu Xu
Yuexia Wang
author_sort Panhua Shi
collection DOAJ
description Atomic-level chemical short-range order (CSRO) in high-entropy alloys (HEAs) has ever garnered increasing attention. However, the mechanisms underlying the effects of CSRO remain poorly understood. Material informatics, through a machine learning (ML) algorithm, can fit the high-dimensional correlation between features well and provide an approach for elucidating complex mechanisms. In this study, we introduced a set of interpretable ML workflows and determined the best algorithm (kernel ridge regression (KRR)) for predicting the atomic stress in HEAs, which can deepen the understanding of the formation mechanism of CSRO. Based on first-principles calculations and Monte Carlo methods, we obtained information on each atom at the atomic and electronic levels to establish the ML features. By systematically studying these features, we found that Shapley additive algorithm indicated that t2g orbitals are fundamental factors that dominate atomic stress, which is critical in the CSRO landscape. Additionally, we discovered that the elemental t2g-eg orbital relationship in FeCoNiTi system greatly influences the characteristics of atomic coordination. Moreover, the closely packed configuration efficiently promotes the ideal strength of the short-range order (SRO) HEA compared to its fully random counterpart. We posit that this endeavor provides a theoretical bedrock for grappling with experimental quandaries and theoretical conundrums.
format Article
id doaj-art-cd804c2abdb54982b185965e146530ee
institution OA Journals
issn 0264-1275
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series Materials & Design
spelling doaj-art-cd804c2abdb54982b185965e146530ee2025-08-20T02:17:33ZengElsevierMaterials & Design0264-12752025-05-0125311389210.1016/j.matdes.2025.113892Exploration for the physical origin and impact of chemical short-range order in high-entropy alloys: Machine learning-assisted studyPanhua Shi0Zhen Xie1Jiaxuan Si2Jianqiao Yu3Xiaoyong Wu4Yaojun Li5Qiu Xu6Yuexia Wang7Key Laboratory of Nuclear Physics and Ion-beam Application (MOE), Institute of Modern Physics, Fudan University, Shanghai 200433, ChinaKey Laboratory of Nuclear Physics and Ion-beam Application (MOE), Institute of Modern Physics, Fudan University, Shanghai 200433, ChinaKey Laboratory of Nuclear Physics and Ion-beam Application (MOE), Institute of Modern Physics, Fudan University, Shanghai 200433, China; The First Sub-Institute, Nuclear Power Institute of China, Chengdu 610005, ChinaKey Laboratory of Nuclear Physics and Ion-beam Application (MOE), Institute of Modern Physics, Fudan University, Shanghai 200433, ChinaThe Fourth Sub-Institute, Nuclear Power Institute of China, Chengdu 610005, ChinaSino-French Institute of Nuclear Engineering and Technology, Sun Yat-sen University, Zhuhai 519082 Guangdong, ChinaInstitute for Integrated Radiation and Nuclear Science, Kyoto University, Osaka 590-0494, JapanKey Laboratory of Nuclear Physics and Ion-beam Application (MOE), Institute of Modern Physics, Fudan University, Shanghai 200433, China; Corresponding author.Atomic-level chemical short-range order (CSRO) in high-entropy alloys (HEAs) has ever garnered increasing attention. However, the mechanisms underlying the effects of CSRO remain poorly understood. Material informatics, through a machine learning (ML) algorithm, can fit the high-dimensional correlation between features well and provide an approach for elucidating complex mechanisms. In this study, we introduced a set of interpretable ML workflows and determined the best algorithm (kernel ridge regression (KRR)) for predicting the atomic stress in HEAs, which can deepen the understanding of the formation mechanism of CSRO. Based on first-principles calculations and Monte Carlo methods, we obtained information on each atom at the atomic and electronic levels to establish the ML features. By systematically studying these features, we found that Shapley additive algorithm indicated that t2g orbitals are fundamental factors that dominate atomic stress, which is critical in the CSRO landscape. Additionally, we discovered that the elemental t2g-eg orbital relationship in FeCoNiTi system greatly influences the characteristics of atomic coordination. Moreover, the closely packed configuration efficiently promotes the ideal strength of the short-range order (SRO) HEA compared to its fully random counterpart. We posit that this endeavor provides a theoretical bedrock for grappling with experimental quandaries and theoretical conundrums.http://www.sciencedirect.com/science/article/pii/S0264127525003120High entropy alloyShort range orderFirst principles calculationsMonte Carlo methodMachine learning
spellingShingle Panhua Shi
Zhen Xie
Jiaxuan Si
Jianqiao Yu
Xiaoyong Wu
Yaojun Li
Qiu Xu
Yuexia Wang
Exploration for the physical origin and impact of chemical short-range order in high-entropy alloys: Machine learning-assisted study
Materials & Design
High entropy alloy
Short range order
First principles calculations
Monte Carlo method
Machine learning
title Exploration for the physical origin and impact of chemical short-range order in high-entropy alloys: Machine learning-assisted study
title_full Exploration for the physical origin and impact of chemical short-range order in high-entropy alloys: Machine learning-assisted study
title_fullStr Exploration for the physical origin and impact of chemical short-range order in high-entropy alloys: Machine learning-assisted study
title_full_unstemmed Exploration for the physical origin and impact of chemical short-range order in high-entropy alloys: Machine learning-assisted study
title_short Exploration for the physical origin and impact of chemical short-range order in high-entropy alloys: Machine learning-assisted study
title_sort exploration for the physical origin and impact of chemical short range order in high entropy alloys machine learning assisted study
topic High entropy alloy
Short range order
First principles calculations
Monte Carlo method
Machine learning
url http://www.sciencedirect.com/science/article/pii/S0264127525003120
work_keys_str_mv AT panhuashi explorationforthephysicaloriginandimpactofchemicalshortrangeorderinhighentropyalloysmachinelearningassistedstudy
AT zhenxie explorationforthephysicaloriginandimpactofchemicalshortrangeorderinhighentropyalloysmachinelearningassistedstudy
AT jiaxuansi explorationforthephysicaloriginandimpactofchemicalshortrangeorderinhighentropyalloysmachinelearningassistedstudy
AT jianqiaoyu explorationforthephysicaloriginandimpactofchemicalshortrangeorderinhighentropyalloysmachinelearningassistedstudy
AT xiaoyongwu explorationforthephysicaloriginandimpactofchemicalshortrangeorderinhighentropyalloysmachinelearningassistedstudy
AT yaojunli explorationforthephysicaloriginandimpactofchemicalshortrangeorderinhighentropyalloysmachinelearningassistedstudy
AT qiuxu explorationforthephysicaloriginandimpactofchemicalshortrangeorderinhighentropyalloysmachinelearningassistedstudy
AT yuexiawang explorationforthephysicaloriginandimpactofchemicalshortrangeorderinhighentropyalloysmachinelearningassistedstudy