A Route Map of Machine Learning Approaches in Heterogeneous CO<sub>2</sub> Reduction Reaction
Diptendu Roy, A. Das, Souvik Manna, Biswarup Pathak
Abstract
Machine learning (ML) with its indigenous predicting ability has been influential in the current scientific world and has enabled a paradigm shift in the field of CO 2 reduction reaction (CO 2 RR). In this perspective, current research progress of ML approaches in heterogeneous electrocatalytic CO 2 RR has been demonstrated. The important findings related to the ML systems comprising features, output descriptors, and ML models have been summarized. Further, the opportunities and challenges in using the state-of-the-art ML methodologies along with the ways of circumventing those challenges are discussed. Finally, the interpretation of black box ML models and extensive usages of interpretable glass box and gray box models for CO 2 RR are encouraged for obtaining proper physical interpretations. The future directions on utilizing several such evolving ML methods to predict catalytic activity descriptors can help in a broader way to explore novel and efficient heterogeneous CO 2 RR and other similar catalytic reactions.