Application of topology-based structure features for machine learning in materials science

作     者：Shisheng Zheng Haowen Ding Shunning Li Dong Chen Feng Pan Shisheng Zheng;Haowen Ding;Shunning Li;Dong Chen;Feng Pan

作者机构：School of Advanced MaterialsPeking University Shenzhen Graduate SchoolShenzhenGuangdong518055PR China Department of MathematicsMichigan State UniversityEast Lansing MIUSA 

出 版 物：《Chinese Journal of Structural Chemistry》 (结构化学（英文）)

年 卷 期：2023年第42卷第7期

页      面：47-53页

核心收录：

学科分类：0808[工学-电气工程] 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] 

基　　金：support from the Guangdong Basic and Applied Basic Research Foundation(2020A1515110843),Young S&T Talent Training Program of Guangdong Provincial Association for S&T(SKXRC202211) Chemistry and Chemical Engineering Guangdong Laboratory(1922018) Soft Science Research Project of Guangdong Province(2017B030301013) National Natural Science Foundation of China(22109003) Natural Science Foundation of Shenzhen(JCYJ20190813110605381) the Major Science and Technology Infrastructure Project of Material Genome Big-science Facilities Platform supported by Municipal Development and Reform Commission of Shenzhen 

主　　题：Machine learning Structure feature Structure graph Algebraic topology 

摘      要：Structure features play an important role in machine learning models for the materials ***,two topology-based features for the representation of material structure,specifically structure graph and algebraic topology,are *** present the fundamental mathematical concepts underlying these techniques and how they encode material ***,we discuss the practical applications and enhancements of these features made in specific material predicting *** review may provide suggestions on the selection of suitable structural features and inspire creativity in developing robust descriptors for diverse applications.