(106a) Molecular Design Blueprints: Catalysts and Principles from New Simulation and Machine Learning Tools

Many highly selective catalysts have been discovered that are defined by well-isolated sites with tailored metal-organic bonding. The rational design of such sites in de novo transition metal complexes, metal-organic frameworks (MOFs), or single atom catalysts, however, remains challenging. First-principles (i.e., with density functional theory, or DFT) high-throughput screening is a promising approach but is hampered by high computational cost, particularly in the brute force screening of large numbers of materials. In this talk, I will outline our efforts over the past few years to accelerate the design of single-site catalysts. I will describe our software and machine learning (ML) models that both simplify and accelerate the screening of new materials. These tools have enabled us to uncover new design rules and exceptions in both molecular and periodic materials (e.g., MOFs). We have paired ML models with multiobjective optimization strategies, robust uncertainty quantification, and highly parallel accelerated computing to discover optimal materials in weeks instead of decades. Time permitting, I will describe our recent efforts in autonomous computational chemistry by developing ML models as decision engines capable of predicting when calculations will fail and when methods beyond DFT are needed.