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

作　　者：胡锦龙 左钰婷 郝昱州 舒国钰 王洋 冯敏轩 李雪洁 王晓莹 孙军 丁向东 高志斌 朱桂妹 李保文 Jinlong Hu;Yuting Zuo;Yuzhou Hao;Guoyu Shu;Yang Wang;Minxuan Feng;Xuejie Li;Xiaoying Wang;Jun Sun;Xiangdong Ding;Zhibin Gao;Guimei Zhu;Baowen Li(State Key Laboratory for Mechanical Behavior of Materials,Xi’an Jiaotong University,Xi’an 710049,China;School of Microelectronics,Southern University of Science and Technology,Shenzhen 518055,China;Department of Materials Science and Engineering,Southern University of Science and Technology,Shenzhen 518055,China;Department of Physics,Southern University of Science and Technology,Shenzhen 518055,China;Paul M.Rady Department of Mechanical Engineering and Department of Physics,University of Colorado,Boulder,Colorado 80305-0427,USA)

机构地区：[1]State Key Laboratory for Mechanical Behavior of Materials,Xi’an Jiaotong University,Xi’an 710049,China [2]School of Microelectronics,Southern University of Science and Technology,Shenzhen 518055,China [3]Department of Materials Science and Engineering,Southern University of Science and Technology,Shenzhen 518055,China [4]Department of Physics,Southern University of Science and Technology,Shenzhen 518055,China [5]Paul M.Rady Department of Mechanical Engineering and Department of Physics,University of Colorado,Boulder,Colorado 80305-0427,USA

出　　处：《Chinese Physics B》2023年第4期11-18,共8页中国物理B（英文版）

基　　金：support of the National Natural Science Foundation of China(Grant Nos.12104356 and52250191);China Postdoctoral Science Foundation(Grant No.2022M712552);the Opening Project of Shanghai Key Laboratory of Special Artificial Microstructure Materials and Technology(Grant No.Ammt2022B-1);the Fundamental Research Funds for the Central Universities;support by HPC Platform,Xi’an Jiaotong University。

摘　　要：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)(https://www.oqmd.org/). The proposed approach guides the next step of searching for materials with ultra-high or ultralow lattice thermal conductivity and promotes the development of new thermal insulation materials and thermoelectric materials.

关 键 词：low lattice thermal conductivity interpretable machine learning thermoelectric materials physical domain knowledge 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TB34[自动化与计算机技术—控制科学与工程]