A Heuristic Approach to Linking Experimental Descriptors with Product Selectivity in Electrochemical CO2 Reduction.

Abstract

An important challenge in electrochemical CO2 reduction (ECR) is relating experimental conditions to their consequences, particularly in terms of product selectivity. The problem lies in the lack of descriptors which adequately describe the experimental protocols and their associated results. In this study, a machine learning approach is applied to correlate the molar composition of 21 single metals and 23 bimetallic particles, as well as operating parameters, from a large collection of synthetic records compiled from the literature with product selectivity. The decision tree obtained shows the conditions that lead to high desired product selectivity and provides a heuristic insight into its electrochemistry. As such, the data does not provide details. However, machine learning algorithms are capable of identifying hidden patterns in the data, providing a deeper insight into the chemistry involved in product formation in the ECR.