A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
This work addresses the problem of accelerating photochemical simulations for researchers in computational chemistry by providing a novel method to accurately learn NACs, though it is incremental as it builds on existing ML and FSSH approaches.
The authors tackled the challenge of machine learning nonadiabatic coupling vectors (NACs), which are difficult due to their vectorial nature and singularities, by designing NAC-specific descriptors and a phase-correction procedure, achieving an accuracy of R^2 exceeding 0.99 and enabling efficient ML-driven simulations with reduced error bars.
Nonadiabatic couplings (NACs) play a crucial role in modeling photochemical and photophysical processes with methods such as the widely used fewest-switches surface hopping (FSSH). There is therefore a strong incentive to machine learn NACs for accelerating simulations. However, this is challenging due to NACs' vectorial, double-valued character and the singularity near a conical intersection seam. For the first time, we design NAC-specific descriptors based on our domain expertise and show that they allow learning NACs with never-before-reported accuracy of $R^2$ exceeding 0.99. The key to success is also our new ML phase-correction procedure. We demonstrate the efficiency and robustness of our approach on a prototypical example of fully ML-driven FSSH simulations of fulvene targeting the SA-2-CASSCF(6,6) electronic structure level. This ML-FSSH dynamics leads to an accurate description of $S_1$ decay while reducing error bars by allowing the execution of a large ensemble of trajectories. Our implementations are available in open-source MLatom.