Unveiling Hidden Catalysts for the Oxidative Coupling of Methane based on Combining Machine Learning with Literature Data

Abstract

Catalysts for oxidative coupling of methane (OCM) are explored using data science and 1868 OCM catalysts from literature data. Machine learning reveals the descriptors responsible for determining the C2 yield produced during the OCM reaction. Trained machine predicts 56 undiscovered catalysts with corresponding conditions for OCM reactions achieving a C2 yield over 30 %. First principle calculations are implemented to evaluate the predicted catalysts where the activation of CH4, CH3, and O2 are confirmed with the predicted catalysts for the OCM reaction. Thus, machine learning is proven to be an effective approach for discovering hidden catalysts and should accelerate the catalyst design process in general.