Prediction of lattice thermal conductivity with two-stage interpretable machine learning

Hu, Jinlong1; Zuo, Yuting1; Hao, Yuzhou1; Shu, Guoyu1; Wang, Yang1; Feng, Minxuan1; Li, Xuejie1; Wang, Xiaoying1; Sun, Jun1; Ding, Xiangdong1; Gao, Zhibin1; Zhu, Guimei2; Li, Baowen3,4,5

2023-03-01

10.1088/1674-1056/acbaf4

CHINESE PHYSICS B   Impact Factor & Quartile

1674-1056

2058-3834

Thermoelectric and thermal materials are essential in achieving carbon neutrality. However, the high cost of lattice thermal conductivity calculations and the limited applicability of classical physical models have led to the inefficient development of thermoelectric materials. In this study, we proposed a two-stage machine learning framework with physical interpretability incorporating domain knowledge to calculate high/low thermal conductivity rapidly. Specifically, crystal graph convolutional neural network (CGCNN) is constructed to predict the fundamental physical parameters related to lattice thermal conductivity. Based on the above physical parameters, an interpretable machine learning model-sure independence screening and sparsifying operator (SISSO), is trained to predict the lattice thermal conductivity. We have predicted the lattice thermal conductivity of all available materials in the open quantum materials database (OQMD) (). The proposed approach guides the next step of searching for materials with ultra-high or ultra-low lattice thermal conductivity and promotes the development of new thermal insulation materials and thermoelectric materials.

low lattice thermal conductivity interpretable machine learning thermoelectric materials physical domain knowledge

SCI

English

Corresponding

National Natural Science Foundation of China["12104356","52250191"] ; China Postdoctoral Science Foundation[2022M712552]

Physics

Physics, Multidisciplinary

WOS:000961371600001

IOP Publishing Ltd

Web of Science

1.Xi An Jiao Tong Univ, State Key Lab Mech Behav Mat, Xian 710049, Peoples R China
2.Southern Univ Sci & Technol, Sch Microelect, Shenzhen 518055, Peoples R China
3.Southern Univ Sci & Technol, Dept Mat Sci & Engn, Shenzhen 518055, Peoples R China
4.Southern Univ Sci & Technol, Dept Phys, Shenzhen 518055, Peoples R China
5.Univ Colorado, Paul M Rady Dept Mech Engn, Dept Phys, Boulder, CO 80305 USA

Hu, Jinlong,Zuo, Yuting,Hao, Yuzhou,et al. Prediction of lattice thermal conductivity with two-stage interpretable machine learning[J]. CHINESE PHYSICS B,2023,32(4).

Hu, Jinlong.,Zuo, Yuting.,Hao, Yuzhou.,Shu, Guoyu.,Wang, Yang.,...&Li, Baowen.(2023).Prediction of lattice thermal conductivity with two-stage interpretable machine learning.CHINESE PHYSICS B,32(4).

Hu, Jinlong,et al."Prediction of lattice thermal conductivity with two-stage interpretable machine learning".CHINESE PHYSICS B 32.4(2023).