Completing density functional theory by machine learning hidden messages from molecules
作者机构:Department of PhysicsThe University of TokyoHongoBunkyo-KuTokyo 113-0033Japan Institute for Solid State PhysicsThe University of TokyoKashiwaChiba 277-8581Japan
出 版 物:《npj Computational Materials》 (计算材料学(英文))
年 卷 期:2020年第6卷第1期
页 面:1306-1313页
核心收录:
学科分类:07[理学] 0701[理学-数学] 070101[理学-基础数学]
基 金:Japan Society for the Promotion of Science JSPS (20J20845)
主 题:technique functional theory
摘 要:Kohn–Sham density functional theory(DFT)is the basis of modern computational approaches to electronic *** accuracy heavily relies on the exchange-correlation energy functional,which encapsulates electron–electron interaction beyond the classical *** its universal form remains undiscovered,approximated functionals constructed with heuristic approaches are used for practical ***,there are problems in their accuracy and transferability,while any systematic approach to improve them is yet *** this study,we demonstrate that the functional can be systematically constructed using accurate density distributions and energies in reference molecules via machine ***,a trial functional machine learned from only a few molecules is already applicable to hundreds of molecules comprising various first-and second-row elements with the same accuracy as the standard *** is achieved by relating density and energy using a flexible feed-forward neural network,which allows us to take a functional derivative via the back-propagation *** addition,simply by introducing a nonlocal density descriptor,the nonlocal effect is included to improve accuracy,which has hitherto been *** approach thus will help enrich the DFT framework by utilizing the rapidly advancing machine-learning technique.