Graph neural networks to predict atomic transition charges and exciton couplings in organic semiconductors

13 March 2025, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Exciton couplings between molecules in organic semiconductors are important parameters for simulating exciton diffusion, however they are time-consuming to compute from first-principles. Previous works have developed machine-learned models to predict exciton couplings, however these models have mostly been restricted to specific molecule and cannot generalize over databases of organic materials. In this paper, we present a graph neural network (GNN) that can predict exciton couplings between organic molecules by using atomic transition charges as an intermediary. Our GNN is shown to predict exciton coupling between important fused-ring electron acceptors (FREAs), as well as many other molecules found in the Cambridge Crystallographic Data Centre crystal database. We also show that these predicted couplings can be used for accurate simulations of exciton diffusion. This work therefore overcomes the key limitation of previous machine-learned models for exciton couplings, thereby bringing us closer to the possibility of performing high-throughput virtual screening of organic materials for photovoltaic applications.

Keywords

graph neural network
atomic transition charge
exciton coupling
organic semiconductor

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.