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

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.

arXiv comment32 pages, 7 figures in Article; 28 pages, 20 figures, 5 tables in SI

References in corpus (12)

• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine learning for electronically excited states of molecules
• Machine learning enables long time scale molecular photodynamics simulations
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Inclusion of machine learning kernel ridge regression potential energy surfaces in on-the-fly nonadiabatic molecular dynamics simulation
• The quest to simulate excited-state dynamics of transition metal complexes
• A Perspective on Deep Learning for Molecular Modeling and Simulations
• Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks

Cited by in corpus (5)

• MLQD: A package for machine learning-based quantum dissipative dynamics
• QD3SET-1: A Database with Quantum Dissipative Dynamics Data Sets
• A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
• Machine learning meets $\mathfrak{su}(n)$ Lie algebra: Enhancing quantum dynamics learning with exact trace conservation
• Toward Quantum-Aware Machine Learning: Improved Prediction of Quantum Dissipative Dynamics via Complex Valued Neural Networks