Symmetry Adapted Residual Neural Network Diabatization: Conical Intersections in Aniline Photodissociation

TL;DR

This paper introduces a symmetry adapted residual neural network (SAResNet) method for constructing diabatic Hamiltonians, accurately modeling potential energy surfaces and nonadiabatic couplings in photodissociation processes, demonstrated on aniline.

Contribution

The paper develops a novel symmetry adapted residual neural network approach for diabatization, combining neural networks with symmetry adaptation for accurate potential energy surfaces.

Findings

Achieved 190 cm-1 RMS deviation in energy for aniline diabatization.

Discovered a higher excited state influencing photodissociation via geometric phase.

Constructed 36-dimensional coupled diabatic potential energy surfaces with 2,269 data points.

Abstract

We present a symmetry adapted residual neural network (SAResNet) diabatization method to construct quasi-diabatic Hamiltonians that accurately represent ab initio adiabatic energies, energy gradients, and nonadiabatic couplings for moderate sized systems. Our symmetry adapted neural network inherits from the pioneering symmetry adapted polynomial and fundamental invariant neural network diabatization methods to exploit the power of neural network along with the transparent symmetry adaptation of polynomial for both symmetric and asymmetric irreducible representations. In addition, our symmetry adaptation provides a unified framework for symmetry adapted polynomial and symmetry adapted neural network, enabling the adoption of the residual neural network architecture, which is a powerful descendant of the pioneering feedforward neural network. Our SAResNet is applied to construct the full 36-dimensional coupled diabatic potential energy surfaces for aniline N-H bond photodissociation, with 2,269 data points and 32,640 trainable parameters and 190 cm-1 root mean square deviation in energy. In addition to the experimentally observed {\pi}{\pi}* and {\pi}Rydberg/{\pi}{\sigma}* states, a higher state (HOMO - 1 {\pi} to Rydberg/{\sigma}* excitation) is found to introduce an induced geometric phase effect thus indirectly participate in the photodissociation process.