Nonadiabatic Excited-State Dynamics with Machine Learning

Pavlo O Dral , Mario Barbatti (1) , Walter Thiel (2)

1 ICR - Institut de Chimie Radicalaire
2 Max-Planck-Institut für Kohlenforschung (Coal Research)

We show that machine learning (ML) can be used to accurately reproduce nonadiabatic excited-state dynamics with decoherence-corrected fewest switches surface hopping in a one-dimensional model system. We propose to use ML to significantly reduce the simulation time of realistic, high-dimensional systems with good reproduction of observables obtained from reference simulations. Our approach is based on creating approximate ML potentials for each adiabatic state using a small number of training points. We investigate the feasibility of this approach by using adiabatic spin-boson Hamiltonian models of various dimensions as reference methods.

Keywords: Machine learning; Adiabatic; Hamiltonian; Spin-boson model

Domains: Chemical Sciences; Chemical Sciences; Theoretical and/or physical chemistry

Pavlo O Dral, Mario Barbatti, Walter Thiel. Nonadiabatic Excited-State Dynamics with Machine Learning. Journal of Physical Chemistry Letters, 2018, 9 (19), pp.5660-5663. ⟨hal-01965451⟩