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

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 S1/S0 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.

[1]  Yajun Liu,et al.  Benchmark Performance of Global Switching versus Local Switching for Trajectory Surface Hopping Molecular Dynamics Simulation: Cis↔Trans Azobenzene Photoisomerization. , 2017, Chemphyschem : a European journal of chemical physics and physical chemistry.

[2]  K. Müller,et al.  Fast and accurate modeling of molecular atomization energies with machine learning. , 2011, Physical review letters.

[3]  Matthias Rupp,et al.  Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach. , 2015, Journal of chemical theory and computation.

[4]  Hung M. Le,et al.  An implementation of the Levenberg–Marquardt algorithm for simultaneous-energy-gradient fitting using two-layer feed-forward neural networks , 2015 .

[5]  Joel M. Bowman,et al.  Permutationally invariant potential energy surfaces in high dimensionality , 2009 .

[6]  M. Rupp,et al.  Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties , 2013, 1307.2918.

[7]  E. Weinan,et al.  Deep Potential: a general representation of a many-body potential energy surface , 2017, 1707.01478.

[8]  Satish T. S. Bukkapatnam,et al.  Neural Networks in Chemical Reaction Dynamics , 2012 .

[9]  A. Pukrittayakamee,et al.  Simultaneous fitting of a potential-energy surface and its corresponding force fields using feedforward neural networks. , 2009, The Journal of chemical physics.

[10]  Le Yu,et al.  Trajectory-based nonadiabatic molecular dynamics without calculating nonadiabatic coupling in the avoided crossing case: trans↔cis photoisomerization in azobenzene. , 2014, Physical chemistry chemical physics : PCCP.

[11]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[12]  Abhinav Vishnu,et al.  Deep learning for computational chemistry , 2017, J. Comput. Chem..

[13]  Markus Meuwly,et al.  Toolkit for the Construction of Reproducing Kernel-Based Representations of Data: Application to Multidimensional Potential Energy Surfaces , 2017, J. Chem. Inf. Model..

[14]  Jörg Behler,et al.  Constructing high‐dimensional neural network potentials: A tutorial review , 2015 .

[15]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[16]  Matthias Rupp,et al.  Machine learning for quantum mechanics in a nutshell , 2015 .

[17]  Alán Aspuru-Guzik,et al.  Machine learning exciton dynamics , 2015, Chemical science.

[18]  Hiroki Nakamura,et al.  New implementation of the trajectory surface hopping method with use of the Zhu-Nakamura theory , 2001 .

[19]  D. Hu,et al.  Nonadiabatic dynamics simulation of keto isocytosine: a comparison of dynamical performance of different electronic-structure methods. , 2017, Physical chemistry chemical physics : PCCP.

[20]  J. Behler,et al.  Machine learning molecular dynamics for the simulation of infrared spectra , 2017, Chemical science.

[21]  Atsuto Seko,et al.  Representation of compounds for machine-learning prediction of physical properties , 2016, 1611.08645.

[22]  Michael Gastegger,et al.  Machine learning molecular dynamics for the simulation of infrared spectra† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc02267k , 2017, Chemical science.

[23]  E Weinan,et al.  Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics , 2017, Physical review letters.

[24]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.

[25]  Joel M. Bowman,et al.  High-dimensional ab initio potential energy surfaces for reaction dynamics calculations. , 2011, Physical chemistry chemical physics : PCCP.

[26]  K. Müller,et al.  Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space , 2015, The journal of physical chemistry letters.