A fast composition-stability machine learning model for screening MAX phases and guiding discovery of Ti2SnN

To explore the MAX phase with experimental value over a wider range, a data-driven machine learning (ML) model was trained to rapidly predict the stability of MAX phases via a random forest classifier (RFC), support vector machine (SVM), and gradient boosting tree (GBT), where the deemed significant...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiyao Lu, Yun Fan, Zhaoxu Sun, Xiaodong He, Chuchu Yang, Hang Yin, Jinze Zhang, Guangping Song, Yongting Zheng, Yuelei Bai
Format: Article
Language:English
Published: Tsinghua University Press 2025-04-01
Series:Journal of Advanced Ceramics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/JAC.2025.9221050
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849697681322016768
author Zhiyao Lu
Yun Fan
Zhaoxu Sun
Xiaodong He
Chuchu Yang
Hang Yin
Jinze Zhang
Guangping Song
Yongting Zheng
Yuelei Bai
author_facet Zhiyao Lu
Yun Fan
Zhaoxu Sun
Xiaodong He
Chuchu Yang
Hang Yin
Jinze Zhang
Guangping Song
Yongting Zheng
Yuelei Bai
author_sort Zhiyao Lu
collection DOAJ
description To explore the MAX phase with experimental value over a wider range, a data-driven machine learning (ML) model was trained to rapidly predict the stability of MAX phases via a random forest classifier (RFC), support vector machine (SVM), and gradient boosting tree (GBT), where the deemed significant descriptors were compiled from the literature and the stability of 1804 combinations of MAX phases was collected. Using this well-trained model, 190 new MAX phases were screened from 4347 MAX phases, 150 of which met the criteria for thermodynamic and intrinsic stability on the basis of first-principles calculations. Additionally, with the help of the ML model, the mean number of valence electrons and the valence electron deviation are the two most critical factors influencing stability. Additionally, one of these predicted MAX phases, Ti₂SnN, was experimentally synthesized through Lewis acid substitution reactions at 750 °C, with interesting A-site deintercalation and self-extrusion. First-principles calculations revealed that Ti₂SnN has lower elastic properties, higher damage tolerance and fracture toughness, and a higher coefficient of thermal expansion (CTE).
format Article
id doaj-art-35ad22ebdf494a35afdf86c3dfa4fc2a
institution DOAJ
issn 2226-4108
2227-8508
language English
publishDate 2025-04-01
publisher Tsinghua University Press
record_format Article
series Journal of Advanced Ceramics
spelling doaj-art-35ad22ebdf494a35afdf86c3dfa4fc2a2025-08-20T03:19:08ZengTsinghua University PressJournal of Advanced Ceramics2226-41082227-85082025-04-01144922105010.26599/JAC.2025.9221050A fast composition-stability machine learning model for screening MAX phases and guiding discovery of Ti2SnNZhiyao Lu0Yun Fan1Zhaoxu Sun2Xiaodong He3Chuchu Yang4Hang Yin5Jinze Zhang6Guangping Song7Yongting Zheng8Yuelei Bai9National Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, ChinaNational Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, ChinaNational Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, ChinaNational Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, ChinaNational Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, ChinaNational Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, ChinaNational Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, ChinaNational Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, ChinaNational Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, ChinaNational Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, ChinaTo explore the MAX phase with experimental value over a wider range, a data-driven machine learning (ML) model was trained to rapidly predict the stability of MAX phases via a random forest classifier (RFC), support vector machine (SVM), and gradient boosting tree (GBT), where the deemed significant descriptors were compiled from the literature and the stability of 1804 combinations of MAX phases was collected. Using this well-trained model, 190 new MAX phases were screened from 4347 MAX phases, 150 of which met the criteria for thermodynamic and intrinsic stability on the basis of first-principles calculations. Additionally, with the help of the ML model, the mean number of valence electrons and the valence electron deviation are the two most critical factors influencing stability. Additionally, one of these predicted MAX phases, Ti₂SnN, was experimentally synthesized through Lewis acid substitution reactions at 750 °C, with interesting A-site deintercalation and self-extrusion. First-principles calculations revealed that Ti₂SnN has lower elastic properties, higher damage tolerance and fracture toughness, and a higher coefficient of thermal expansion (CTE).https://www.sciopen.com/article/10.26599/JAC.2025.9221050max phasesmachine learning (ml)ti2snnfirst principlesself-extrusion
spellingShingle Zhiyao Lu
Yun Fan
Zhaoxu Sun
Xiaodong He
Chuchu Yang
Hang Yin
Jinze Zhang
Guangping Song
Yongting Zheng
Yuelei Bai
A fast composition-stability machine learning model for screening MAX phases and guiding discovery of Ti2SnN
Journal of Advanced Ceramics
max phases
machine learning (ml)
ti2snn
first principles
self-extrusion
title A fast composition-stability machine learning model for screening MAX phases and guiding discovery of Ti2SnN
title_full A fast composition-stability machine learning model for screening MAX phases and guiding discovery of Ti2SnN
title_fullStr A fast composition-stability machine learning model for screening MAX phases and guiding discovery of Ti2SnN
title_full_unstemmed A fast composition-stability machine learning model for screening MAX phases and guiding discovery of Ti2SnN
title_short A fast composition-stability machine learning model for screening MAX phases and guiding discovery of Ti2SnN
title_sort fast composition stability machine learning model for screening max phases and guiding discovery of ti2snn
topic max phases
machine learning (ml)
ti2snn
first principles
self-extrusion
url https://www.sciopen.com/article/10.26599/JAC.2025.9221050
work_keys_str_mv AT zhiyaolu afastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT yunfan afastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT zhaoxusun afastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT xiaodonghe afastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT chuchuyang afastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT hangyin afastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT jinzezhang afastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT guangpingsong afastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT yongtingzheng afastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT yueleibai afastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT zhiyaolu fastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT yunfan fastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT zhaoxusun fastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT xiaodonghe fastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT chuchuyang fastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT hangyin fastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT jinzezhang fastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT guangpingsong fastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT yongtingzheng fastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn
AT yueleibai fastcompositionstabilitymachinelearningmodelforscreeningmaxphasesandguidingdiscoveryofti2snn