Symmetry-Adapted High Dimensional Neural Network Representation of Electronic Friction Tensor of Adsorbates on Metals

Abstract

Nonadiabatic effects in chemical reaction at metal surfaces, due to excitation of electron-hole pairs, stand at the frontier of the studies of gas-surface reaction dynamics. However, the first principles description of electronic excitation remains challenging. In an efficient molecular dynamics with electronic friction (MDEF) method, the nonadiabatic couplings are effectively included in a so-called electronic friction tensor (EFT), which can be computed from first-order time-dependent perturbation theory (TDPT) in terms of density functional theory (DFT) orbitals. This second-rank tensor depends on adsorbate position and features a complicated transformation with regard to the intrinsic symmetry operations of the system. In this work, we develop a new symmetry-adapted neural network representation of EFT, based on our recently proposed embedded atom neural network (EANN) framework. Inspired by the derivation of the nonadiabatic coupling matrix, we represent the tensorial friction by the first and second derivatives of multiple outputs of NNs with respect to atomic Cartesian coordinates. This rigorously preserves the positive semidefiniteness, directional property, and correct symmetry-equivariance of EFT. Unlike previous methods, our new approach can readily include both molecular and surface degrees of freedom, regardless of the type of surface. Tests on the H2+Ag(111) system show that this approach yields an accurate, efficient, and continuous representation of EFT, making it possible to perform large scale TDPT-based MDEF simulations to study both adiabatic and nonadiabatic energy dissipation in a unified framework.

arXiv commentThe paper have been published on the journal of physical chemistry C

References in corpus (14)

• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• Machine learning enables long time scale molecular photodynamics simulations
• Operators in Machine Learning: Response Properties in Chemical Space
• Ab-initio tensorial electronic friction for molecules on metal surfaces: nonadiabatic vibrational relaxation
• Competition between electron and phonon excitations in the scattering of nitrogen atoms and molecules off tungsten and silver surfaces
• Signatures of nonadiabatic O2 dissociation at Al(111): First-principles fewest-switches study
• Mode specific electronic friction in dissociative chemisorption on metal surfaces: H${}_2$ on Ag(111)
• Electronic friction-based vibrational lifetimes of molecular adsorbates: Beyond the independent atom approximation
• Strong Vibrational Relaxation of NO Scattered from Au(111): Importance of an Accurate Adiabatic Potential Energy Surface
• Femtosecond laser driven molecular dynamics on surfaces: Photodesorption of molecular oxygen from Ag(110)
• Hydrogen abstraction from metal surfaces: When electron-hole pair excitations strongly affect hot-atom recombination
• Ready, set and no action: A static perspective on potential energy surfaces commonly used in gas-surface dynamics

Cited by in corpus (16)

• Machine learning for electronically excited states of molecules
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Perspective on integrating machine learning into computational chemistry and materials science
• A practical guide to machine learning interatomic potentials -- Status and future
• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
• Universal Machine Learning for the Response of Atomistic Systems to External Fields
• Machine learning and excited-state molecular dynamics
• Accelerating Atomistic Simulations with Piecewise Machine Learned Ab Initio Potentials at Classical Force Field-like Cost
• Mechanical Vibrational Relaxation of NO Scattering from Metal and Insulator Surfaces: When and Why Are They Different?
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Quantum Dynamics with Electronic Friction
• Electronic friction coefficients from the atom-in-jellium model for $Z=1-92$
• Reaction dynamics for the Cl(${}^2$P) + XCl $\to$ XCl + Cl(${}^2$P) (X = H, D, Mu) reaction on a high-fidelity ground state potential energy surface
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• NQCDynamics.jl: A Julia Package for Nonadiabatic Quantum Classical Molecular Dynamics in the Condensed Phase