Transition metal complexes display a rich array of photophysical properties where substituted ligands can be used both for the tuning of excited states and as conduits for electron- and energy-transfer. In this study, the combination of experimental, computational, cheminformatics and machine learning methods are applied to reveal the factors responsible for near-IR (NIR) emission properties. In particular, the development of new predictive machine learning model for organometallic complexes with nonlinear NIR emission properties is discussed. The applied methodology involves a new approach to encode organometallic materials and the developed framework could offer an efficient and cost-effective design of optical materials for various applications. The study lies at the interface of organic, inorganic, materials chemistry, theoretical quantum chemistry, cheminformatics and machine learning approaches.

Development of predictive machine learning model for organometallic materials with near-IR emission properties

Fall 2022 abstracts, posters, and presentations will launch in mid-September.

ACS Fall 2022

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