Fewest-Switches Surface Hopping with Long Short-Term Memory Networks

TL;DR

This paper introduces a novel approach using LSTM networks to accelerate nonadiabatic quantum dynamics simulations, specifically within the surface hopping framework, enabling efficient trajectory generation and analysis.

Contribution

The study demonstrates that LSTM networks can effectively replace parts of the FSSH simulation process, providing a faster and qualitatively accurate method for nonadiabatic dynamics.

Findings

LSTM networks successfully reproduce qualitative results of FSSH simulations.

The approach accelerates trajectory generation in nonadiabatic dynamics.

LSTM-based FSSH maintains key features of the original method.

Abstract

The mixed quantum-classical dynamical simulation is essential to study nonadiabatic phenomena in photophysics and photochemistry. In recent years, many machine learning models have been developed to accelerate the time evolution of the nuclear subsystem. Herein, we implement long short-term memory (LSTM) networks as a propagator to accelerate the time evolution of the electronic subsystem during the fewest-switches surface hopping (FSSH) simulations. A small number of reference trajectories are generated using the original FSSH method, and then the LSTM networks can be built, accompanied by careful examination of typical LSTM-FSSH trajectories that employ the same initial condition and random numbers as the corresponding reference. The constructed network is applied to FSSH to further produce a trajectory ensemble to reveal the mechanism of nonadiabatic processes. Taking Tully's three models as test systems, the collective results can be reproduced qualitatively. This work demonstrates that LSTM is applicable to the most popular surface hopping simulations.