Structural mechanism of glass transition uncovered by unsupervised machine learning

doi:10.1016/j.actamat.2024.120410

IMECH-IR > 非线性力学国家重点实验室

	Structural mechanism of glass transition uncovered by unsupervised machine learning
	Yang ZY(杨增宇)1 ; Miao, Qing 2,3; Dan, JiaKun 1; Liu, MingTao 1; Wang YJ(王云江)4,5
通讯作者	Yang, Zeng-Yu([email protected]) ; Miao, Qing([email protected]) ; Wang, Yun-Jiang([email protected])
发表期刊	ACTA MATERIALIA
	2024-12-01
卷号	281 页码:11
ISSN	1359-6454
摘要	Uncovering the structural origins of the ubiquitous dynamic arrest phenomenon at the glass transition has long been a challenge due to the difficulty in identifying a rational structural representation from a disordered medium. To address this challenge, we propose a novel approach based on unsupervised learning to define a set of structural fingerprints. In this approach, complex local atomic environments, ranging from short to medium range, are captured by the discretized radial distribution function and projected onto a simple two-dimensional space using a neural network-based autoencoder. This two-dimensional space is characterized by two static structural indicators, P-1 and P-2, providing a comprehensive and user-friendly representation of the mysterious "glassy structure". By employing Gaussian mixture modeling, the structural space is autonomously divided into three sections, each representing a unique cluster with similar environments. These indicators not only elucidate the glass transition but also allow for the quantitative prediction of activation barriers for local structural excitations. Furthermore, the unsupervised clustering technique can distinguish between the structural features of "hard zones" and "soft zones", as well as recently proposed superfast "liquid-like" atoms in glass. This unsupervised machine learning approach demonstrates the utility of seemingly agnostic local structure in amorphous materials, offering insights into the long-sought structural origins of the glass transition.
关键词	Glass transition Unsupervised machine learning Structural origin Superfast atoms
DOI	10.1016/j.actamat.2024.120410
收录类别	SCI ; EI
语种	英语
WOS记录号	WOS:001321869700001
关键词[WOS]	MEDIUM-RANGE ORDER ; BULK METALLIC-GLASS ; RELAXATION ; DYNAMICS ; DEFORMATION ; TEMPERATURE ; DUCTILE ; LIQUIDS ; MIXTURE
WOS研究方向	Materials Science ; Metallurgy & Metallurgical Engineering
WOS类目	Materials Science, Multidisciplinary ; Metallurgy & Metallurgical Engineering
资助项目	Strategic Priority Research Program of Chinese Academy of Sciences[XDB0620103] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDB0510301] ; Youth Innovation Promotion Association of the Chinese Academy of Sciences ; National Natural Science Foundation of China[12072332] ; National Natural Science Foundation of China[12472112] ; National Natural Science Foundation of China[11932018] ; National Natural Science Foundation of China[12402469] ; National Natural Science Foundation of China[12402326] ; China Academy of Engineering Physics (CAEP)[YZJJZL2024003]
项目资助者	Strategic Priority Research Program of Chinese Academy of Sciences ; Youth Innovation Promotion Association of the Chinese Academy of Sciences ; National Natural Science Foundation of China ; China Academy of Engineering Physics (CAEP)
论文分区	一类
力学所作者排名	1
RpAuthor	Yang, Zeng-Yu ; Miao, Qing ; Wang, Yun-Jiang
引用统计
文献类型	期刊论文
条目标识符	http://dspace.imech.ac.cn/handle/311007/96878
专题	非线性力学国家重点实验室
作者单位	1.China Acad Engn Phys, Inst Fluid Phys, Mianyang 621999, Sichuan, Peoples R China; 2.China Aerodynam Res & Dev Ctr, Hyperveloc Aerodynam Inst, Mianyang 621000, Sichuan, Peoples R China; 3.Natl Key Lab Aerosp Phys Fluids, Mianyang 621000, Sichuan, Peoples R China; 4.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China; 5.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Yang ZY,Miao, Qing,Dan, JiaKun,et al. Structural mechanism of glass transition uncovered by unsupervised machine learning[J]. ACTA MATERIALIA,2024,281:11.Rp_Au:Yang, Zeng-Yu, Miao, Qing, Wang, Yun-Jiang
APA	杨增宇,Miao, Qing,Dan, JiaKun,Liu, MingTao,&王云江.(2024).Structural mechanism of glass transition uncovered by unsupervised machine learning.ACTA MATERIALIA,281,11.
MLA	杨增宇,et al."Structural mechanism of glass transition uncovered by unsupervised machine learning".ACTA MATERIALIA 281(2024):11.