Article Dans Une Revue Journal of Physical Chemistry Letters Année : 2025

A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors

Jakub Martinka
Lina Zhang
Yi-Fan Hou
Mikołaj Martyka
Jiří Pittner
Pavlo Dral

Résumé

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, doublevalued 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 R2 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 S1 decay while reducing error bars by allowing the execution of a large ensemble of trajectories. Our approach is generalizable to more states as we demonstrate for a three-state MLFSSH simulation of methylenimmonium cation. Our implementations are available in open-source MLatom.

Fichier principal
Vignette du fichier
martinka_accepted_2025.pdf (7.02 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05345520 , version 1 (04-11-2025)

Licence

Identifiants

Citer

Jakub Martinka, Lina Zhang, Yi-Fan Hou, Mikołaj Martyka, Jiří Pittner, et al.. A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors. Journal of Physical Chemistry Letters, 2025, 16, pp.11732-11744. ⟨10.1021/acs.jpclett.5c02810⟩. ⟨hal-05345520⟩
121 Consultations
1 Téléchargements

Altmetric

Partager

  • More