Photoactive iridium complexes are of broad interest due to their applications ranging from lighting to photocatalysis. However, the excited state property prediction of these complexes challenges <i>ab initio </i>methods such as time-dependent density functional theory (TDDFT) both from an accuracy and a computational cost perspective, complicating high throughput virtual screening (HTVS). In this talk, I will describe how we leverage low-cost machine learning (ML) models to predict the excited state properties of photoactive iridium complexes. I will detail our use of experimental data of 1,380 iridium complexes to train and evaluate the ML models, and show how we identified the best-performing and most transferable models to be those trained on electronic structure features from low-cost density functional theory tight binding calculations. I will show how we use these models to predict the three excited state properties considered, mean emission energy of phosphorescence, excited state lifetime, and emission spectral integral, with accuracy competitive with or superseding TDDFT. I will present the feature importance analysis conducted to identify which iridium complex attributes govern excited state properties and illustrate these trends with explicit examples. I will end by presenting how our ML models can be used for HTVS and the acceleration of chemical discovery, with an example of the curation of novel hypothetical iridium complexes and the identification of promising ligands from these complexes for the design of new phosphors.

Low-cost machine learning approach to the prediction of transition metal phosphor excited state properties

Where thousands of chemistry professionals meet to share ideas and advance scientific and technical knowledge. Spring 2023 abstracts, posters, and presentations will launch at the end of March.

ACS Spring 2023

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.