ePrints

A deep learning framework for predictions of excited state properties of light emissive molecules

Lookup NU author(s): Professor Thomas Penfold

Downloads

• Accepted version [.pdf]

Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

Abstract

We have implemented a deep learning protocol to forecast the excited state properties for thermally activated delayed fluorescence (TADF) molecules with satisfactory accuracies being achieved. In particular, for the oscillator strengths, predictive precisions have been significantly improved when the torsional profile of the dataset is enriched.

Publication metadata

Author(s): Tan Z, Li Y, Zhang Z, Penfold T, Shi W, Yang S, Zhang W

Publication type: Article

Publication status: Published

Journal: New Journal of Chemistry

Year: 2023

Volume: 47

Issue: 20

Pages: 9550-9554

Print publication date: 10/05/2023

Online publication date: 09/05/2023

Acceptance date: 29/04/2023

Date deposited: 10/05/2023

ISSN (print): 1144-0546

ISSN (electronic): 1369-9261

Publisher: Royal Society of Chemistry

URL: https://doi.org/10.1039/D3NJ01174G

DOI: 10.1039/D3NJ01174G

ePrints DOI: 10.57711/3ty9-m315

Altmetrics

Funding

Share