Improved machine learning framework for prediction of phases and crystal structures of high entropy alloys

High-entropy alloys (HEAs) are gaining popularity because of their remarkable properties controlled by phases and crystal structures. In addition to that, in the field of material informatics, machine learning (ML) techniques have gained considerable attention in predicting phases and crystal struct...

Full description

Saved in:
Bibliographic Details
Main Authors: Debsundar Dey, Suchandan Das, Anik Pal, Santanu Dey, Chandan Kumar Raul, Pritam Mandal, Arghya Chatterjee, Soumya Chatterjee, Manojit Ghosh
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Journal of Alloys and Metallurgical Systems
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949917824000932
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850041345196949504
author Debsundar Dey
Suchandan Das
Anik Pal
Santanu Dey
Chandan Kumar Raul
Pritam Mandal
Arghya Chatterjee
Soumya Chatterjee
Manojit Ghosh
author_facet Debsundar Dey
Suchandan Das
Anik Pal
Santanu Dey
Chandan Kumar Raul
Pritam Mandal
Arghya Chatterjee
Soumya Chatterjee
Manojit Ghosh
author_sort Debsundar Dey
collection DOAJ
description High-entropy alloys (HEAs) are gaining popularity because of their remarkable properties controlled by phases and crystal structures. In addition to that, in the field of material informatics, machine learning (ML) techniques have gained considerable attention in predicting phases and crystal structures of HEAs. In this study, a novel ML-based methodology has been proposed to predict different phase stages and crystal structures. To this end, 1345 data samples were used to train the ML model to predict the phases of HEAs. Within the dataset, 705 data were utilized to predict the crystal structures with the help of thermodynamics and electronic configuration as input features. The important features were selected using the Pearson correlation coefficient matrix, followed by using of five distinct boosting algorithms to predict phases and crystal structures. Among all these algorithms, XGBoost recorded the highest detection accuracy of 94.05 % for phases and LightGBM yielded the highest detection accuracy of 90.07 % for crystal structure. Various hyperparameter tuning was conducted to find the optimum performance of the boosting classifiers. A comprehensive comparison was performed between the ML models and some from published papers in reputed journals. From the comparison, it was evident that the proposed methodology showed its superiority in terms of phase and crystal structure detection of HEAs.
format Article
id doaj-art-3f9cdc0b6bb14150af9be145132afaba
institution DOAJ
issn 2949-9178
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Journal of Alloys and Metallurgical Systems
spelling doaj-art-3f9cdc0b6bb14150af9be145132afaba2025-08-20T02:55:48ZengElsevierJournal of Alloys and Metallurgical Systems2949-91782025-03-01910014410.1016/j.jalmes.2024.100144Improved machine learning framework for prediction of phases and crystal structures of high entropy alloysDebsundar Dey0Suchandan Das1Anik Pal2Santanu Dey3Chandan Kumar Raul4Pritam Mandal5Arghya Chatterjee6Soumya Chatterjee7Manojit Ghosh8Department of Materials Engineering, Indian Institute of Science, Bengaluru 560012, IndiaDepartment of Electrical Engineering, National Institute of Technology, Silchar 788010, IndiaSchool of Physics, University of Hyderabad, Hyderabad 500046, IndiaDepartment of Physics, National Institute of Technology, Durgapur 713209, IndiaDepartment of Physics, National Institute of Technology, Durgapur 713209, IndiaIndian Institute of Engineering Science and Technology, Shibpur, Howrah 711103, IndiaDepartment of Physics, National Institute of Technology, Durgapur 713209, IndiaElectrical Engineering Department, National Institute of Technology, Durgapur 713209, IndiaIndian Institute of Engineering Science and Technology, Shibpur, Howrah 711103, India; Corresponding author.High-entropy alloys (HEAs) are gaining popularity because of their remarkable properties controlled by phases and crystal structures. In addition to that, in the field of material informatics, machine learning (ML) techniques have gained considerable attention in predicting phases and crystal structures of HEAs. In this study, a novel ML-based methodology has been proposed to predict different phase stages and crystal structures. To this end, 1345 data samples were used to train the ML model to predict the phases of HEAs. Within the dataset, 705 data were utilized to predict the crystal structures with the help of thermodynamics and electronic configuration as input features. The important features were selected using the Pearson correlation coefficient matrix, followed by using of five distinct boosting algorithms to predict phases and crystal structures. Among all these algorithms, XGBoost recorded the highest detection accuracy of 94.05 % for phases and LightGBM yielded the highest detection accuracy of 90.07 % for crystal structure. Various hyperparameter tuning was conducted to find the optimum performance of the boosting classifiers. A comprehensive comparison was performed between the ML models and some from published papers in reputed journals. From the comparison, it was evident that the proposed methodology showed its superiority in terms of phase and crystal structure detection of HEAs.http://www.sciencedirect.com/science/article/pii/S2949917824000932Crystal structure predictionFeature selectionHigh entropy alloyMachine learningPhase prediction
spellingShingle Debsundar Dey
Suchandan Das
Anik Pal
Santanu Dey
Chandan Kumar Raul
Pritam Mandal
Arghya Chatterjee
Soumya Chatterjee
Manojit Ghosh
Improved machine learning framework for prediction of phases and crystal structures of high entropy alloys
Journal of Alloys and Metallurgical Systems
Crystal structure prediction
Feature selection
High entropy alloy
Machine learning
Phase prediction
title Improved machine learning framework for prediction of phases and crystal structures of high entropy alloys
title_full Improved machine learning framework for prediction of phases and crystal structures of high entropy alloys
title_fullStr Improved machine learning framework for prediction of phases and crystal structures of high entropy alloys
title_full_unstemmed Improved machine learning framework for prediction of phases and crystal structures of high entropy alloys
title_short Improved machine learning framework for prediction of phases and crystal structures of high entropy alloys
title_sort improved machine learning framework for prediction of phases and crystal structures of high entropy alloys
topic Crystal structure prediction
Feature selection
High entropy alloy
Machine learning
Phase prediction
url http://www.sciencedirect.com/science/article/pii/S2949917824000932
work_keys_str_mv AT debsundardey improvedmachinelearningframeworkforpredictionofphasesandcrystalstructuresofhighentropyalloys
AT suchandandas improvedmachinelearningframeworkforpredictionofphasesandcrystalstructuresofhighentropyalloys
AT anikpal improvedmachinelearningframeworkforpredictionofphasesandcrystalstructuresofhighentropyalloys
AT santanudey improvedmachinelearningframeworkforpredictionofphasesandcrystalstructuresofhighentropyalloys
AT chandankumarraul improvedmachinelearningframeworkforpredictionofphasesandcrystalstructuresofhighentropyalloys
AT pritammandal improvedmachinelearningframeworkforpredictionofphasesandcrystalstructuresofhighentropyalloys
AT arghyachatterjee improvedmachinelearningframeworkforpredictionofphasesandcrystalstructuresofhighentropyalloys
AT soumyachatterjee improvedmachinelearningframeworkforpredictionofphasesandcrystalstructuresofhighentropyalloys
AT manojitghosh improvedmachinelearningframeworkforpredictionofphasesandcrystalstructuresofhighentropyalloys