Title: Data-Driven Approaches to Transition-Metal Catalysis
Abstract: The application of machine learning to homogeneous catalysis is transforming the field, with computational methods addressing key challenges in catalyst design, mechanistic understanding, and reaction optimization. In this talk, I will present recent work on how the combination of data-driven approaches and quantum chemistry can improve the modelling and discovery of transition-metal (TM) catalysts. I will first outline the current landscape of AI in homogeneous catalysis, focusing on recent advances in chemical representations and computational workflows. I will then present our recent developments in TM descriptors, highlighting their transferability across different chemical motifs. Finally, I will showcase the application of these methods to the discovery of bifunctional catalysts for CO₂ hydrogenation to methanol. By combining high-throughput virtual screening with machine learning surrogate models, we explore large chemical spaces to identify and prioritize candidates for experimental validation.
Date: May 12, 2026