Fewest-Switches Surface Hopping with Combined Deep Learning Potential and Long Short-Term Memory Network Propagator for Simulating Realistic Photochemical Processes.

Fewest-switches surface hopping (FSSH) is the most popular method for simulating photochemical processes of molecular systems. Recently, we have constructed long short-term memory (LSTM) networks as a propagator for electronic subsystems in FSSH dynamics simulations. The collective results on Tully's three models have been reproduced satisfactorily. In the present work, we developed an extended LSTM-FSSH framework to simulate realistic photochemical reactions. The input features of LSTM as well as the training procedure are redesigned to represent high-dimensional nuclear degrees of freedom in an effective manner. Equivariant neural networks are integrated with LSTM to build adiabatic potential energy surfaces in ground and excited states. Photoisomerizations of CH2NH and azobenzene are simulated, showing that our newly proposed LSTM-FSSH method can produce excited-state lifetimes and product yields accurately in comparison with conventional FSSH simulations as a reference. Only 10 reference trajectories are required for training LSTM networks, and then a trajectory ensemble can be generated with very efficient LSTM-FSSH dynamic simulations to obtain collective results.