Colloquium: Zachary Ulissi

Title: Workflows, Datasets and Models for Active Discovery in Catalysis

Abstract: Machine learning accelerated catalyst discovery efforts has seen much progress in the last few years. Datasets of computational calculations have improved, models to connect surface structure with electronic structure or adsorption energies have gotten more sophisticated, and active learning exploration strategies are becoming routine in discovery efforts. However, there are several large challenges that remain: to date, models have had trouble generalizing to new materials or reaction intermediates and applying these methods requires significant training. I will review and discuss methods in my lab for high-throughput catalyst screening and on-line discovery of interesting materials, resulting in an optimized Cu-Al catalyst for CO2-to-ethylene conversion. I will then introduce the Open Catalyst Project and the Open Catalyst 2020 dataset, a collaborative project to span surface composition, structure, and chemistry and enable a new generation of deep machine learning models for catalysis, with initial results for state-of-the-art deep graph convolutional models. Finally, I will discuss on-going work to develop small ML models to accelerate routine calculations without requiring expert intervention.