Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
This work addresses the problem of computationally expensive photodynamics simulations for quantum chemists, offering a more efficient method, though it appears incremental as it combines existing techniques.
The authors tackled the challenge of simulating excited-state dynamics in photochemistry by developing SchNarc, a deep learning approach that learns multiple properties including energies, forces, and couplings, and tested it on model and realistic systems to enable efficient simulations of complex systems.
In recent years, deep learning has become a part of our everyday life and is revolutionizing quantum chemistry as well. In this work, we show how deep learning can be used to advance the research field of photochemistry by learning all important properties for photodynamics simulations. The properties are multiple energies, forces, nonadiabatic couplings and spin-orbit couplings. The nonadiabatic couplings are learned in a phase-free manner as derivatives of a virtually constructed property by the deep learning model, which guarantees rotational covariance. Additionally, an approximation for nonadiabatic couplings is introduced, based on the potentials, their gradients and Hessians. As deep-learning method, we employ SchNet extended for multiple electronic states. In combination with the molecular dynamics program SHARC, our approach termed SchNarc is tested on a model system and two realistic polyatomic molecules and paves the way towards efficient photodynamics simulations of complex systems.