Structure and Dynamics of Energy Materials from Machine Learning Simulations:A Topical Review

作     者：Shu-Hui Guan Cheng Shang Zhi-Pan Liu Shu-Hui Guan;Cheng Shang;Zhi-Pan Liu

作者机构：Shanghai Academy of Agricultural SciencesShanghai201403 China Collaborative Innovation Center of Chemistry for Energy MaterialShanghai Key Laboratory of molecular Catalysis and Innovative MaterialsKey Laboratory of Computational Physical ScienceDepartment of ChemistryFudan UniversityShanghai200438 China 

出 版 物：《Chinese Journal of Chemistry》 (中国化学（英文版）)

年 卷 期：2021年第39卷第11期

页      面：3144-3154页

核心收录：

学科分类：12[管理学] 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] 0805[工学-材料科学与工程（可授工学、理学学位）] 080502[工学-材料学] 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：This work was supported by Shanghai Sailing Program(19YF1442800) the National Key Research and Development Program of China(2018YFA0208600) the National Natural Science Foundation of China(22003040,22033003,91945301,91745201 and 21533001) 

主　　题：Machine learning Materials science Atomic simulation Thermodynamics Kinetics 

摘      要：Energy materials featuring the capability to store and release chemical energy reversibly involve generally complex geometrical structures with multiple *** has been a great challenge to establish the quantitative relationship between the structure of materials and their dynamic physicochemical *** recent years,machine learning(ML)technique has demonstrated its great power in accelerating the research on energy *** topical review introduces the key ingredients and typical applications of ML to energy *** mainly focus on the ML based atomic simulation via ML potentials in different architectures/implementations,including high dimensional neural networks(HDNN),Gaussian approximation potential(GAP),moment tensor potentials(MTP)and stochastic surface walking global optimization with global neural network potential(SSW-NN)*** cases studies,namely,Si,LiC and LiTiO systems,are presented to demonstrate the ability of ML simulation in assessing the thermodynamics and kinetics of complex material *** highlight that the SSW-NN method provides an automated solution for global potential energy surface data collection,ML potential construction and ML simulation,which boosts the current ability for large-scale atomic simulation and thus holds the great promise for fast property evaluation and material discovery.