Neural network based quasi-diabatic Hamiltonians with symmetry adaptation and a correct description of conical intersections
Abstract
In a previous paper, we have demonstrated that artificial neural networks (NNs) can be used to generate quasidiabatic Hamiltonians (Hd) that are capable of representing adiabatic energies, energy gradients, and derivative couplings. In this work, two additional issues are addressed. First, symmetry-adapted functions such as permutation invariant polynomials are introduced to account for complete nuclear permutation inversion symmetry. Second, a partially diagonalized representation is introduced to facilitate a better description of near degeneracy points. The diabatization of 1, 21A states of NH3 is used as an example. The NN fitting results are compared to that of a previous fitting with symmetry adapted polynomials.
- Authors:
-
- Johns Hopkins Univ., Baltimore, MD (United States)
- Univ. of New Mexico, Albuquerque, NM (United States)
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Univ. of New Mexico, Albuquerque, NM (United States); Johns Hopkins Univ., Baltimore, MD (United States)
- Sponsoring Org.:
- USDOE Office of Science Education and Technical Information (ET); USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities Division
- OSTI Identifier:
- 1577596
- Alternate Identifier(s):
- OSTI ID: 1524125; OSTI ID: 1595109
- Grant/Contract Number:
- SC0015997
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Chemical Physics
- Additional Journal Information:
- Journal Volume: 150; Journal Issue: 21; Journal ID: ISSN 0021-9606
- Publisher:
- American Institute of Physics (AIP)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; 74 ATOMIC AND MOLECULAR PHYSICS; neural networks; conical intersections
Citation Formats
Guan, Yafu, Guo, Hua, and Yarkony, David R. Neural network based quasi-diabatic Hamiltonians with symmetry adaptation and a correct description of conical intersections. United States: N. p., 2019.
Web. doi:10.1063/1.5099106.
Guan, Yafu, Guo, Hua, & Yarkony, David R. Neural network based quasi-diabatic Hamiltonians with symmetry adaptation and a correct description of conical intersections. United States. https://doi.org/10.1063/1.5099106
Guan, Yafu, Guo, Hua, and Yarkony, David R. Mon .
"Neural network based quasi-diabatic Hamiltonians with symmetry adaptation and a correct description of conical intersections". United States. https://doi.org/10.1063/1.5099106. https://www.osti.gov/servlets/purl/1577596.
@article{osti_1577596,
title = {Neural network based quasi-diabatic Hamiltonians with symmetry adaptation and a correct description of conical intersections},
author = {Guan, Yafu and Guo, Hua and Yarkony, David R.},
abstractNote = {In a previous paper, we have demonstrated that artificial neural networks (NNs) can be used to generate quasidiabatic Hamiltonians (Hd) that are capable of representing adiabatic energies, energy gradients, and derivative couplings. In this work, two additional issues are addressed. First, symmetry-adapted functions such as permutation invariant polynomials are introduced to account for complete nuclear permutation inversion symmetry. Second, a partially diagonalized representation is introduced to facilitate a better description of near degeneracy points. The diabatization of 1, 21A states of NH3 is used as an example. The NN fitting results are compared to that of a previous fitting with symmetry adapted polynomials.},
doi = {10.1063/1.5099106},
journal = {Journal of Chemical Physics},
number = 21,
volume = 150,
place = {United States},
year = {Mon Jun 03 00:00:00 EDT 2019},
month = {Mon Jun 03 00:00:00 EDT 2019}
}
Web of Science
Works referenced in this record:
High-Dimensional Atomistic Neural Network Potentials for Molecule–Surface Interactions: HCl Scattering from Au(111)
journal, January 2017
- Kolb, Brian; Luo, Xuan; Zhou, Xueyao
- The Journal of Physical Chemistry Letters, Vol. 8, Issue 3
Interpolation of diabatic potential energy surfaces
journal, January 2004
- Evenhuis, Christian R.; Collins, Michael A.
- The Journal of Chemical Physics, Vol. 121, Issue 6
A seven-dimensional quantum dynamics study of the dissociative chemisorption of H 2 O on Cu(111): effects of azimuthal angles and azimuthal angle-averaging
journal, January 2016
- Liu, Tianhui; Zhang, Zhaojun; Fu, Bina
- Chemical Science, Vol. 7, Issue 3
Nuclear dynamics near conical intersections in the adiabatic representation: I. The effects of local topography on interstate transitions
journal, February 2001
- Yarkony, David R.
- The Journal of Chemical Physics, Vol. 114, Issue 6
Accurate Neural Network Description of Surface Phonons in Reactive Gas–Surface Dynamics: N 2 + Ru(0001)
journal, April 2017
- Shakouri, Khosrow; Behler, Jörg; Meyer, Jörg
- The Journal of Physical Chemistry Letters, Vol. 8, Issue 10
Neural network models of potential energy surfaces
journal, September 1995
- Blank, Thomas B.; Brown, Steven D.; Calhoun, August W.
- The Journal of Chemical Physics, Vol. 103, Issue 10
Permutationally invariant potential energy surfaces in high dimensionality
journal, October 2009
- Braams, Bastiaan J.; Bowman, Joel M.
- International Reviews in Physical Chemistry, Vol. 28, Issue 4
Potential Energy Surfaces Fitted by Artificial Neural Networks
journal, March 2010
- Handley, Chris M.; Popelier, Paul L. A.
- The Journal of Physical Chemistry A, Vol. 114, Issue 10
Fitting coupled potential energy surfaces for large systems: Method and construction of a 3-state representation for phenol photodissociation in the full 33 internal degrees of freedom using multireference configuration interaction determined data
journal, January 2014
- Zhu, Xiaolei; Yarkony, David R.
- The Journal of Chemical Physics, Vol. 140, Issue 2
A scheme to interpolate potential energy surfaces and derivative coupling vectors without performing a global diabatization
journal, December 2011
- Evenhuis, Christian; Martínez, Todd J.
- The Journal of Chemical Physics, Vol. 135, Issue 22
High-dimensional ab initio potential energy surfaces for reaction dynamics calculations
journal, January 2011
- Bowman, Joel M.; Czakó, Gábor; Fu, Bina
- Physical Chemistry Chemical Physics, Vol. 13, Issue 18
On the adiabatic to diabatic states transformation near intersections of conical intersections
journal, February 2000
- Yarkony, David R.
- The Journal of Chemical Physics, Vol. 112, Issue 5
Permutation invariant polynomial neural network approach to fitting potential energy surfaces. III. Molecule-surface interactions
journal, July 2014
- Jiang, Bin; Guo, Hua
- The Journal of Chemical Physics, Vol. 141, Issue 3
An optimal adiabatic-to-diabatic transformation of the 1 2A′ and 2 2A′ states of H3
journal, January 2002
- Abrol, Ravinder; Kuppermann, Aron
- The Journal of Chemical Physics, Vol. 116, Issue 3
Interpolation of multidimensional diabatic potential energy matrices
journal, September 2006
- Godsi, Oded; Evenhuis, Christian R.; Collins, Michael A.
- The Journal of Chemical Physics, Vol. 125, Issue 10
Neural network-based approaches for building high dimensional and quantum dynamics-friendly potential energy surfaces
journal, October 2014
- Manzhos, Sergei; Dawes, Richard; Carrington, Tucker
- International Journal of Quantum Chemistry, Vol. 115, Issue 16
Potential energy surfaces near intersections
journal, August 1991
- Atchity, Gregory J.; Xantheas, Sotirios S.; Ruedenberg, Klaus
- The Journal of Chemical Physics, Vol. 95, Issue 3
Permutationally Invariant Polynomial Basis for Molecular Energy Surface Fitting via Monomial Symmetrization
journal, November 2009
- Xie, Zhen; Bowman, Joel M.
- Journal of Chemical Theory and Computation, Vol. 6, Issue 1
An implementation of the Levenberg–Marquardt algorithm for simultaneous-energy-gradient fitting using two-layer feed-forward neural networks
journal, June 2015
- Nguyen-Truong, Hieu T.; Le, Hung M.
- Chemical Physics Letters, Vol. 629
Conditions for the definition of a strictly diabatic electronic basis for molecular systems
journal, December 1982
- Mead, C. Alden; Truhlar, Donald G.
- The Journal of Chemical Physics, Vol. 77, Issue 12
Communication: An accurate global potential energy surface for the OH + CO → H + CO 2 reaction using neural networks
journal, June 2013
- Chen, Jun; Xu, Xin; Xu, Xin
- The Journal of Chemical Physics, Vol. 138, Issue 22
Introduction to the theory of electronic non-adiabatic coupling terms in molecular systems
journal, February 2002
- Baer, Michael
- Physics Reports, Vol. 358, Issue 2
Combining ab initio computations, neural networks, and diffusion Monte Carlo: An efficient method to treat weakly bound molecules
journal, November 1996
- Brown, David F. R.; Gibbs, Mark N.; Clary, David C.
- The Journal of Chemical Physics, Vol. 105, Issue 17
Direct diabatization of electronic states by the fourfold way. II. Dynamical correlation and rearrangement processes
journal, September 2002
- Nakamura, Hisao; Truhlar, Donald G.
- The Journal of Chemical Physics, Vol. 117, Issue 12
Neural network diabatization: A new ansatz for accurate high-dimensional coupled potential energy surfaces
journal, November 2018
- Williams, David M. G.; Eisfeld, Wolfgang
- The Journal of Chemical Physics, Vol. 149, Issue 20
Permutation invariant polynomial neural network approach to fitting potential energy surfaces. IV. Coupled diabatic potential energy matrices
journal, October 2018
- Xie, Changjian; Zhu, Xiaolei; Yarkony, David R.
- The Journal of Chemical Physics, Vol. 149, Issue 14
On the adiabatic to diabatic states transformation in the presence of a conical intersection: A most diabatic basis from the solution to a Poisson’s equation. I
journal, July 1998
- Sadygov, Rovshan G.; Yarkony, David R.
- The Journal of Chemical Physics, Vol. 109, Issue 1
Communication: Fitting potential energy surfaces with fundamental invariant neural network
journal, August 2016
- Shao, Kejie; Chen, Jun; Zhao, Zhiqiang
- The Journal of Chemical Physics, Vol. 145, Issue 7
Training feedforward networks with the Marquardt algorithm
journal, January 1994
- Hagan, M. T.; Menhaj, M. B.
- IEEE Transactions on Neural Networks, Vol. 5, Issue 6
Quasi-diabatic representations of adiabatic potential energy surfaces coupled by conical intersections including bond breaking: A more general construction procedure and an analysis of the diabatic representation
journal, December 2012
- Zhu, Xiaolei; Yarkony, David R.
- The Journal of Chemical Physics, Vol. 137, Issue 22
Permutation invariant polynomial neural network approach to fitting potential energy surfaces
journal, August 2013
- Jiang, Bin; Guo, Hua
- The Journal of Chemical Physics, Vol. 139, Issue 5
Simultaneous fitting of a potential-energy surface and its corresponding force fields using feedforward neural networks
journal, April 2009
- Pukrittayakamee, A.; Malshe, M.; Hagan, M.
- The Journal of Chemical Physics, Vol. 130, Issue 13
Methane dissociation on Ni(111): A fifteen-dimensional potential energy surface using neural network method
journal, October 2015
- Shen, Xiangjian; Chen, Jun; Zhang, Zhaojun
- The Journal of Chemical Physics, Vol. 143, Issue 14
Multilayer feedforward networks are universal approximators
journal, January 1989
- Hornik, Kurt; Stinchcombe, Maxwell; White, Halbert
- Neural Networks, Vol. 2, Issue 5
Full-Dimensional Quantum Dynamics of Vibrationally Mediated Photodissociation of NH 3 and ND 3 on Coupled Ab Initio Potential Energy Surfaces: Absorption Spectra and NH 2 (Ã 2 A 1 )/NH 2 (X̃ 2 B 1 ) Branching Ratios
journal, July 2014
- Ma, Jianyi; Xie, Changjian; Zhu, Xiaolei
- The Journal of Physical Chemistry A, Vol. 118, Issue 51
Constructing diabatic states from adiabatic states: Extending generalized Mulliken–Hush to multiple charge centers with Boys localization
journal, December 2008
- Subotnik, Joseph E.; Yeganeh, Sina; Cave, Robert J.
- The Journal of Chemical Physics, Vol. 129, Issue 24
Full-Dimensional Quantum State-to-State Nonadiabatic Dynamics for Photodissociation of Ammonia in its A -Band
journal, March 2014
- Xie, Changjian; Ma, Jianyi; Zhu, Xiaolei
- The Journal of Physical Chemistry Letters, Vol. 5, Issue 7
The DQ and DQΦ electronic structure diabatization methods: Validation for general applications
journal, May 2016
- Hoyer, Chad E.; Parker, Kelsey; Gagliardi, Laura
- The Journal of Chemical Physics, Vol. 144, Issue 19
Permutation invariant polynomial neural network approach to fitting potential energy surfaces. II. Four-atom systems
journal, November 2013
- Li, Jun; Jiang, Bin; Guo, Hua
- The Journal of Chemical Physics, Vol. 139, Issue 20
Extension of the fourfold way for calculation of global diabatic potential energy surfaces of complex, multiarrangement, non-Born–Oppenheimer systems: Application to HNCO(S0,S1)
journal, April 2003
- Nakamura, Hisao; Truhlar, Donald G.
- The Journal of Chemical Physics, Vol. 118, Issue 15
Toward eliminating the electronic structure bottleneck in nonadiabatic dynamics on the fly: An algorithm to fit nonlocal, quasidiabatic, coupled electronic state Hamiltonians based on ab initio electronic structure data
journal, March 2010
- Zhu, Xiaolei; Yarkony, David R.
- The Journal of Chemical Physics, Vol. 132, Issue 10
Adiabatic and diabatic representations for atom-diatom collisions: Treatment of the three-dimensional case
journal, June 1976
- Baer, Michael
- Chemical Physics, Vol. 15, Issue 1
Neural network based coupled diabatic potential energy surfaces for reactive scattering
journal, August 2017
- Lenzen, Tim; Manthe, Uwe
- The Journal of Chemical Physics, Vol. 147, Issue 8
Dynamics of Water Dissociative Chemisorption on Ni(111): Effects of Impact Sites and Incident Angles
journal, April 2015
- Jiang, Bin; Guo, Hua
- Physical Review Letters, Vol. 114, Issue 16
Observation of the geometric phase effect in the H + HD → H 2 + D reaction
journal, December 2018
- Yuan, Daofu; Guan, Yafu; Chen, Wentao
- Science, Vol. 362, Issue 6420
First principles determination of the NH 2 /ND 2 (Ã,X̃) branching ratios for photodissociation of NH 3 /ND 3 via full-dimensional quantum dynamics based on a new quasi-diabatic representation of coupled ab initio potential energy surfaces
journal, December 2012
- Ma, Jianyi; Zhu, Xiaolei; Guo, Hua
- The Journal of Chemical Physics, Vol. 137, Issue 22
Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations
journal, January 2011
- Behler, Jörg
- Physical Chemistry Chemical Physics, Vol. 13, Issue 40
Construction of diabatic energy surfaces for LiFH with artificial neural networks
journal, December 2017
- Guan, Yafu; Fu, Bina; Zhang, Dong H.
- The Journal of Chemical Physics, Vol. 147, Issue 22
Communication: On the competition between adiabatic and nonadiabatic dynamics in vibrationally mediated ammonia photodissociation in its A band
journal, March 2015
- Xie, Changjian; Zhu, Xiaolei; Ma, Jianyi
- The Journal of Chemical Physics, Vol. 142, Issue 9
On the representation of coupled adiabatic potential energy surfaces using quasi-diabatic Hamiltonians: A distributed origins expansion approach
journal, May 2012
- Zhu, Xiaolei; Yarkony, David R.
- The Journal of Chemical Physics, Vol. 136, Issue 17
Representation of coupled adiabatic potential energy surfaces using neural network based quasi-diabatic Hamiltonians: 1,2 2 A′ states of LiFH
journal, January 2019
- Guan, Yafu; Zhang, Dong H.; Guo, Hua
- Physical Chemistry Chemical Physics, Vol. 21, Issue 26
Molecular Quantum Dynamics
text, January 2017
- Hagedorn, George A.; Lasser, Caroline
- Mathematisches Forschungsinstitut Oberwolfach
Works referencing / citing this record:
Statistical distributions of the tuning and coupling collective modes at a conical intersection using the hierarchical equations of motion
journal, December 2019
- Mangaud, Etienne; Lasorne, Benjamin; Atabek, Osman
- The Journal of Chemical Physics, Vol. 151, Issue 24
Combining SchNet and SHARC: The SchNarc Machine Learning Approach for Excited-State Dynamics
journal, April 2020
- Westermayr, Julia; Gastegger, Michael; Marquetand, Philipp
- The Journal of Physical Chemistry Letters, Vol. 11, Issue 10
Machine learning and excited-state molecular dynamics
journal, September 2020
- Westermayr, Julia; Marquetand, Philipp
- Machine Learning: Science and Technology, Vol. 1, Issue 4