Inclusion of machine learning kernel ridge regression potential energy surfaces in on-the-fly nonadiabatic molecular dynamics simulation

TL;DR

This paper demonstrates how machine learning kernel ridge regression potential energy surfaces can be integrated into nonadiabatic molecular dynamics simulations, enabling efficient and accurate modeling of polyatomic systems like 6-aminopyrimidine.

Contribution

It introduces a novel approach combining ML-PESs with Zhu-Nakamura surface hopping for nonadiabatic dynamics, reducing reliance on extensive electronic structure calculations.

Findings

ML-PESs produce results consistent with CASSCF PESs.

The method enables highly efficient large-scale dynamics simulations.

ML-PESs effectively identify regions near conical intersections.

Abstract

We discuss a theoretical approach that employs machine learning potential energy surfaces (ML-PESs) in the nonadiabatic dynamics simulation of polyatomic systems by taking 6-aminopyrimidine as a typical example. The Zhu-Nakamura theory is employed in the surface hopping dynamics, which does not require the calculation of the nonadiabatic coupling vectors. The kernel ridge regression is used in the construction of the adiabatic PESs. In the nonadiabatic dynamics simulation, we use ML-PESs for most geometries and switch back to the electronic structure calculations for a few geometries either near the S1/S0 conical intersections or in the out-of-confidence regions. The dynamics results based on ML-PESs are consistent with those based on CASSCF PESs. The ML-PESs are further used to achieve the highly efficient massive dynamics simulations with a large number of trajectories. This work displays the powerful role of ML methods in the nonadiabatic dynamics simulation of polyatomic systems.