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

Abstract

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.

References in corpus (23)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• 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
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Landau-Zener type surface hopping algorithms
• A mapping approach to surface hopping
• Excited state, non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows
• Neural networks and kernel ridge regression for excited states dynamics of CH${}_2$NH${}_2^{+}$: From single-state to multi-state representations and multi-property machine learning models
• H5MD: a structured, efficient, and portable file format for molecular data
• Nonadiabatic Field on Quantum Phase Space: A Century after Ehrenfest
• MLatom software ecosystem for surface hopping dynamics in Python with quantum mechanical and machine learning methods
• Fewest-Switches Surface Hopping with Long Short-Term Memory Networks
• Nonadiabatic Field with Triangle Window Functions on Quantum Phase Space
• Nonadiabatic Field: A Conceptually Novel Approach for Nonadiabatic Quantum Molecular Dynamics
• Tell machine learning potentials what they are needed for: Simulation-oriented training exemplified for glycine
• Exciting DeePMD: Learning excited state energies, forces, and non-adiabatic couplings
• Machine Learning Framework for Modeling Exciton-Polaritons in Molecular Materials
• Thawed Gaussian wavepacket dynamics with $\Delta$-machine learned potentials
• A simple approach to rotationally invariant machine learning of avector quantity

Cited by in corpus (1)

• The Photochemical Birth of the Hydrated Electron in Liquid Water