Accurate machine learning models based on small dataset of energetic materials through spatial matrix featurization methods

作     者：Chao Chen Danyang Liu Siyan Deng Lixiang Zhong Serene Hay Yee Chan Shuzhou Li Huey Hoon Hng Chao Chen;Danyang Liu;Siyan Deng;Lixiang Zhong;Serene Hay Yee Chan;Shuzhou Li;Huey Hoon Hng

作者机构：School of Materials Science and EngineeringNanyang Technological University50 Nanyang AvenueSingapore 639798Singapore 

出 版 物：《Journal of Energy Chemistry》 (能源化学（英文版）)

年 卷 期：2021年第30卷第12期

页      面：364-375,I0009页

核心收录：

学科分类：12[管理学] 082604[工学-军事化学与烟火技术] 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] 0826[工学-兵器科学与技术] 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：support from the Ministry of Education(MOE) Singapore Tier 1 (RG8/20) 

主　　题：Small database machine learning Energetic materials screening Spatial matrix featurization method Crystal density Formation enthalpy n-Body interactions 

摘      要：A large database is desired for machine learning(ML) technology to make accurate predictions of materials physicochemical properties based on their molecular *** a large database is not available,the development of proper featurization method based on physicochemical nature of target proprieties can improve the predictive power of ML models with a smaller *** this work,we show that two new featurization methods,volume occupation spatial matrix and heat contribution spatial matrix,can improve the accuracy in predicting energetic materials crystal density(ρ_(crystal)) and solid phase enthalpy of formation(H_(f,solid)) using a database containing 451 energetic *** mean absolute errors are reduced from 0.048 g/cm~3 and 24.67 kcal/mol to 0.035 g/cm~3 and 9.66 kcal/mol,*** leave-one-out-cross-validation,the newly developed ML models can be used to determine the performance of most kinds of energetic materials except *** ML models are applied to predict ρ_(crystal) and H_(f,solid) of CHON-based molecules of the 150 million sized PubChem database,and screened out 56 candidates with competitive detonation performance and reasonable chemical *** further improvement in future,spatial matrices have the potential of becoming multifunctional ML simulation tools that could provide even better predictions in wider fields of materials science.