Accuracy of Machine Learning Potential for Predictions of Multiple-Target Physical Properties

作     者：Yulou Ouyang Zhongwei Zhang Cuiqian Yu Jia He Gang Yan Jie Chen 欧阳宇楼;张忠卫;俞崔前;何佳;严钢;陈杰

作者机构：Center for Phononics and Thermal Energy ScienceChina–EU Joint Lab for NanophononicsSchool of Physics Science and EngineeringTongji UniversityShanghai 200092China Shanghai Institute of Intelligent Science and TechnologyTongji UniversityShanghai 200092China 

出 版 物：《Chinese Physics Letters》 (中国物理快报（英文版）)

年 卷 期：2020年第37卷第12期

页      面：53-61页

核心收录：

学科分类：12[管理学] 081702[工学-化学工艺] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0817[工学-化学工程与技术] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the National Natural Science Foundation of China(Grant Nos.12075168 and 11890703) the Science and Technology Commission of Shanghai Municipality(Grant Nos.19ZR1478600,18ZR1442000 and 18JC1410900) the Fundamental Research Funds for the Central Universities(Grant No.22120200069) the Open Fund of Hunan Provincial Key Laboratory of Advanced Materials for New Energy Storage and Conversion(Grant No.2018TP1037_201901) 

主　　题：materials. thermal potential 

摘      要：The accurate and rapid prediction of materials’physical properties,such as thermal transport and mechanical properties,are of particular importance for potential applications of featuring novel *** demonstrate,using graphene as an example,how machine learning potential,combined with the Boltzmann transport equation and molecular dynamics simulations,can simultaneously provide an accurate prediction of multiple-target physical properties,with an accuracy comparable to that of density functional theory calculation and/or experimental *** quantities include the Grüneisen parameter,the thermal expansion coefficient,Young’s modulus,Poisson’s ratio,and thermal ***,the transferability of commonly used empirical potential in predicting multiple-target physical properties is also *** study suggests that atomic simulation,in conjunction with machine learning potential,represents a promising method of exploring the various physical properties of novel materials.