Learning Chemical Trends in Heterogeneous Catalysis

Despite tremendous advances in the understanding of catalysis in the past few decades, the discovery of improved materials for energy transformation processes has been guided by physical intuition and trial-and-error approaches. Even though computational simulations have provided a more rational approach, even the most systematic studies involving the most well-described systems require a large number of costly and repetitive calculations. We attempt to mitigate this problem by proposing a learning model for directly obtaining energetic parameters relevant to catalysis using widely accessible bulk chemical data. Among the methods surveyed, our tree-based models achieved a cross-validation error of about 0.45 eV, which approaches the error obtained from simulations (about 0.2 eV).