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(Center for Phononics and Thermal Energy Science,China–EU Joint Lab for Nanophononics,School of Physics Science and Engineering,Tongji University,Shanghai 200092,China;Shanghai Institute of Intelligent Science and Technology,Tongji University,Shanghai 200092,China)

机构地区：[1]Center for Phononics and Thermal Energy Science,China–EU Joint Lab for Nanophononics,School of Physics Science and Engineering,Tongji University,Shanghai 200092,China [2]Shanghai Institute of Intelligent Science and Technology,Tongji University,Shanghai 200092,China

出　　处：《Chinese Physics Letters》2020年第12期53-61,共9页中国物理快报（英文版）

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)。

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 materials.We 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 measurements.Benchmarked quantities include the Grüneisen parameter,the thermal expansion coefficient,Young’s modulus,Poisson’s ratio,and thermal conductivity.Moreover,the transferability of commonly used empirical potential in predicting multiple-target physical properties is also examined.Our study suggests that atomic simulation,in conjunction with machine learning potential,represents a promising method of exploring the various physical properties of novel materials.

关 键 词：materials. THERMAL POTENTIAL 

分 类 号：TQ127.11[化学工程—无机化工] TP18[自动化与计算机技术—控制理论与控制工程]