Join us to hear from Chad Risko, the John C. Hubbard Professor of Chemistry from the University of Kentucky!

Abstract: Organic semiconductors (OS) derived from π-conjugated molecules and polymers are of broad interest across a range of electronic and optical technologies. How molecular design and material processing merge to result in OS with optimal properties to function in a given device application, however, remains largely a mixture of art and science. To enable machine-driven OS design and discovery, we seek to develop and implement artificial intelligence (AI) / machine learning (ML) approaches to enhance and expedite the search for new materials. Here, we will discuss the development of ML models to rapidly predict properties of molecular building blocks and the final OS. Further, we will discuss the development of software and tools to enable automated, robotic experimentation.