Thermal conductivity modeling using machine learning potentials: application to crystalline and amorphous silicon

doi:10.1016/j.mtphys.2019.100140

IMECH-IR > 非线性力学国家重点实验室

	Thermal conductivity modeling using machine learning potentials: application to crystalline and amorphous silicon
	Qian X.; 彭神佑.; Li X.; Wei YJ(魏宇杰); Yang R.
发表期刊	MATERIALS TODAY PHYSICS
	2019-08
卷号	10 页码:UNSP 100140
ISSN	2542-5293
摘要	First principles-based modeling on phonon dynamics and transport using density functional theory and the Boltzmann transport equation has proven powerful in predicting thermal conductivity of crystalline materials, but it remains unfeasible for modeling complex crystals and disordered solids due to the prohibitive computational cost to capture the disordered structure, especially when the quasiparticle 'phonon' model breaks down. Recently, machine learning regression algorithms show great promises for building high-accuracy potential fields for atomistic modeling with length scales and timescales far beyond those achievable by first principles calculations. In this work, using both crystalline and amorphous silicon as examples, we develop machine learning-based potential fields for predicting thermal conductivity. The machine learning-based interatomic potential is derived from density functional theory calculations by stochastically sampling the potential energy surface in the configurational space. The thermal conductivities of both amorphous and crystalline silicon are then calculated using equilibrium molecular dynamics, which agree well with experimental measurements. This work documents the procedure for training the machine learning-based potentials for modeling thermal conductivity and demonstrates that machine learning-based potential can be a promising tool for modeling thermal conductivity of both crystalline and amorphous materials with strong disorder. (C) 2019 Elsevier Ltd. All rights reserved.
关键词	Thermal conductivity Machine learning Molecular dynamics Phonons
DOI	10.1016/j.mtphys.2019.100140
收录类别	SCI
语种	英语
WOS记录号	WOS:000511431800008
关键词[WOS]	APPROXIMATION
WOS研究方向	Materials Science, Multidisciplinary ; Physics, Applied
WOS类目	Materials Science ; Physics
项目资助者	NSFNational Science Foundation (NSF) [ACI-1532235, ACI-1532236, 1512776] ; University of Colorado Boulder ; Colorado State University ; Supercomputing Center of Chinese Academy of Sciences
力学所作者排名	2
RpAuthor	Yang, R
引用统计	被引频次：57[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://dspace.imech.ac.cn/handle/311007/81442
专题	非线性力学国家重点实验室
推荐引用方式 GB/T 7714	Qian X.,彭神佑.,Li X.,et al. Thermal conductivity modeling using machine learning potentials: application to crystalline and amorphous silicon[J]. MATERIALS TODAY PHYSICS,2019,10:UNSP 100140.
APA	Qian X.,彭神佑.,Li X.,魏宇杰,&Yang R..(2019).Thermal conductivity modeling using machine learning potentials: application to crystalline and amorphous silicon.MATERIALS TODAY PHYSICS,10,UNSP 100140.
MLA	Qian X.,et al."Thermal conductivity modeling using machine learning potentials: application to crystalline and amorphous silicon".MATERIALS TODAY PHYSICS 10(2019):UNSP 100140.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Jp2019533.pdf（1356KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载