Computer-aided design of new and improved materials is vastly accelerated by combining atomistic modeling methods with machine learning in a cloud-deployable, easily scalable platform. By combining powerful quantum chemistry methods from SCM with modern active learning techniques from Kebotix, researchers can screen millions of compounds and optimize many properties simultaneously. We will demonstrate the new platform for screening new thermally activated delayed fluorescence (TADF) emitters for OLEDs. Millions of candidates are screened for their key properties for novel TADF emitters (S1/T1 gap, spin-orbit coupling, emission profile, and radiative lifetime). Researchers can also screen other relevant properties for organic electronics such as degradation and charge mobility. The future roadmap for the accelerated materials innovation platform will be discussed with applications to optimize materials and processes for battery, catalysis, and semiconductors.

Accelerated materials innovation through machine-learning assisted atomistic modeling

ACS Spring 2022

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