Samuel Young is a Ph.D. candidate in the Department of Chemical Engineering and a member of the Goldsmith Computational Materials Laboratory studying under the supervision of Prof. Bryan R. Goldsmith. His research focuses on using first-principles computational catalysis approaches and machine learning to discover active, stable, and selective electrocatalysts for industrially and environmentally important chemical reactions. His previous work identified transition metal alloy and metal sulfide catalysts for the aqueous nitrate reduction reaction. Currently, he is focusing on (1) exploring computer vision machine learning (ML) models and featurization schemes to improve the accuracy of catalyst property predictions and (2) building a community-driven database of synthesis recipes for metal alloy catalysts along with new ML models that incorporate data on synthesis conditions to predict empirically measured activity and selectivity. Together, these aims will complementarily address the larger problem of improving the fidelity of ML models to first-principles theory and to experimental observations. High-fidelity catalysis ML models will help enable the cheap, accurate screening of potentially millions of catalyst materials for a certain reaction.