Physically inspired deep learning of molecular excitations and photoemission spectra

TL;DR

This paper introduces a physics-inspired deep learning model capable of accurately predicting molecular excited-state properties and photoemission spectra for large, complex organic molecules, surpassing the limitations of traditional computational methods.

Contribution

A novel deep neural network leveraging physical principles to predict quasiparticle excitations and spectra of large molecules, enabling efficient high-throughput screening.

Findings

Accurately predicts charged quasiparticle excitations across diverse molecules.

Replicates GW-level photoemission spectra for unseen conjugated molecules.

Handles complex chemical and configurational diversity effectively.

Abstract

Modern functional materials consist of large molecular building blocks with significant chemical complexity which limits spectroscopic property prediction with accurate first-principles methods. Consequently, a targeted design of materials with tailored optoelectronic properties by high-throughput screening is bound to fail without efficient methods to predict molecular excited-state properties across chemical space. In this work, we present a deep neural network that predicts charged quasiparticle excitations for large and complex organic molecules with a rich elemental diversity and a size well out of reach of accurate many body perturbation theory calculations. The model exploits the fundamental underlying physics of molecular resonances as eigenvalues of a latent Hamiltonian matrix and is thus able to accurately describe multiple resonances simultaneously. The performance of this model is demonstrated for a range of organic molecules across chemical composition space and configuration space. We further showcase the model capabilities by predicting photoemission spectra at the level of the GW approximation for previously unseen conjugated molecules.