Convolutional network learning of self-consistent electron density via grid-projected atomic fingerprints  

作　　者：Ryong-Gyu Lee Yong-Hoon Kim 

机构地区：[1]School of Electrical Engineering,Korea Advanced Institute of Science and Technology(KAIST),291 Daehak-ro,Yuseong-gu,Daejeon,34141,Korea

出　　处：《npj Computational Materials》2024年第1期598-605,共8页计算材料学(英文)

基　　金：supported by the National Research Foundation of Korea(2023R1A2C2003816 and RS-2023-00253716);Computational resources were provided by KISTI Supercomputing Center(KSC-2023-CRE-0476).

摘　　要：The self-consistent field(SCF)generation of the three-dimensional(3D)electron density distribution(ρ)represents a fundamental aspect of density functional theory(DFT)and related first-principles calculations,and how one can shorten or bypass the SCF loop represents a critical question in electronic structure theory from both practical and fundamental standpoints.Herein,a machine learning strategy,DeepSCF,is presented in which the map between the SCFρand the initial guess density(ρ_(0))constructed by the summation of neutral atomic densities is learned using 3D convolutional neural networks(CNNs).

关 键 词：learning THEORY NEUTRAL 

分 类 号：H31[语言文字—英语]