Exciton diffusion in amorphous organic semiconductors: reducing simulation overheads with machine learning

TL;DR

This paper introduces a new machine learning architecture that significantly reduces training time for predicting exciton coupling parameters, enabling efficient and accurate simulations of exciton diffusion in amorphous organic semiconductors.

Contribution

The authors develop a novel machine learning model that decreases training time compared to traditional methods, improving the efficiency of exciton diffusion simulations in complex materials.

Findings

The new model achieves excellent accuracy in predicting exciton diffusion properties.

Simulation results closely match those using density functional theory parameters.

Training time is substantially reduced compared to Gaussian process and kernel ridge regression.

Abstract

Simulations of exciton and charge hopping in amorphous organic materials involve numerous physical parameters. Each of these parameters must be computed from costly ab initio calculations before the simulation can commence, resulting in a significant computational overhead for studying exciton diffusion, especially in large and complex material datasets. While the idea of using machine learning to quickly predict these parameters has been explored previously, typical machine learning models require long training times which ultimately contribute to simulation overheads. In this paper, we present a new machine learning architecture for building predictive models for intermolecular exciton coupling parameters. Our architecture is designed in such a way that the total training time is reduced compared to ordinary Gaussian process regression or kernel ridge regression models. Based on this architecture, we build a predictive model and use it to estimate the coupling parameters which enter into an exciton hopping simulation in amorphous pentacene. We show that this hopping simulation is able to achieve excellent predictions for exciton diffusion tensor elements and other properties as compared to a simulation using coupling parameters computed entirely from density functional theory. This result, along with the short training times afforded by our architecture, therefore shows how machine learning can be used to reduce the high computational overheads associated with exciton and charge diffusion simulations in amorphous organic materials.