Inclusion of Machine Learning Kernel Ridge Regression Potential Energy Surfaces in On-the-Fly Nonadiabatic Molecular Dynamics Simulation

doi:10.1021/acs.jpclett.8b00684

	Inclusion of Machine Learning Kernel Ridge Regression Potential Energy Surfaces in On-the-Fly Nonadiabatic Molecular Dynamics Simulation
	Hu, Deping 1,2; Xie, Yu 1; Li, Xusong 1,2; Li, Lingyue 2; Lan, Zhenggang 1,2
刊名	JOURNAL OF PHYSICAL CHEMISTRY LETTERS
	2018-06-07
卷号	9 期号:11 页码:2725-2732
ISSN号	1948-7185
DOI	10.1021/acs.jpclett.8b00684
文献子类	Article
英文摘要	We discuss a theoretical approach that employs machine learning potential energy surfaces (ML-PESs) in the nonadiabatic dynamics simulation of polyatomic systems by taking 6-aminopyrimidine as a typical example. The Zhu-Nakamura theory is employed in the surface hopping dynamics, which does not require the calculation of the nonadiabatic coupling vectors. The kernel ridge regression is used in the construction of the adiabatic PESs. In the nonadiabatic dynamics simulation, we use ML-PESs for most geometries and switch back to the electronic structure calculations for a few geometries either near the S-1/S-0 conical intersections or in the out-of-confidence regions. The dynamics results based on ML-PESs are consistent with those based on CASSCF PESs. The ML-PESs are further used to achieve the highly efficient massive dynamics simulations with a large number of trajectories. This work displays the powerful role of ML methods in the nonadiabatic dynamics simulation of polyatomic systems.
WOS关键词	NEURAL-NETWORK POTENTIALS ; QUANTUM MECHANICS/MOLECULAR MECHANICS ; CURVE CROSSING PROBLEMS ; EXCITED-STATE DYNAMICS ; CONICAL INTERSECTIONS ; CLASSICAL DYNAMICS ; CHEMICAL SPACE ; PHOTODYNAMICS ; REPRESENTATION ; TRANSITION
WOS研究方向	Chemistry ; Science & Technology - Other Topics ; Materials Science ; Physics
语种	英语
出版者	AMER CHEMICAL SOC
WOS记录号	WOS:000435026100002
资助机构	NSFC(21673266 ; Natural Science Foundation of Shandong Province for Distinguished Young Scholars(JQ201504) ; 21503248)
内容类型	期刊论文
源URL	[http://ir.qibebt.ac.cn/handle/337004/11385]
专题	中国科学院青岛生物能源与过程研究所
通讯作者	Lan, Zhenggang
作者单位	1.Chinese Acad Sci, Qingdao Inst Bioenergy & Bioproc Technol, CAS Key Lab Biobased Mat, Qingdao 266101, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Hu, Deping,Xie, Yu,Li, Xusong,et al. Inclusion of Machine Learning Kernel Ridge Regression Potential Energy Surfaces in On-the-Fly Nonadiabatic Molecular Dynamics Simulation[J]. JOURNAL OF PHYSICAL CHEMISTRY LETTERS,2018,9(11):2725-2732.
APA	Hu, Deping,Xie, Yu,Li, Xusong,Li, Lingyue,&Lan, Zhenggang.(2018).Inclusion of Machine Learning Kernel Ridge Regression Potential Energy Surfaces in On-the-Fly Nonadiabatic Molecular Dynamics Simulation.JOURNAL OF PHYSICAL CHEMISTRY LETTERS,9(11),2725-2732.
MLA	Hu, Deping,et al."Inclusion of Machine Learning Kernel Ridge Regression Potential Energy Surfaces in On-the-Fly Nonadiabatic Molecular Dynamics Simulation".JOURNAL OF PHYSICAL CHEMISTRY LETTERS 9.11(2018):2725-2732.