Iterative machine learning method for screening high-performance catalysts for H2O2 production

Electrochemical H2O2 production through a selective two-electron oxygen reduction reaction represents a promising alternative to the traditional anthraquinone oxidation process (AOP). However, it remains an unavoidable challenge to screen high-performance catalysts for the H2O2 production such as ambiguous activation mechanisms. Herein, we propose an iterative machine learning (iML) method that drastically reduces the required training set size. By introducing the feature of spatial coordinate information, we can rapidly screen out the optimal catalytic activity from hundreds of single-atom catalysts. It can be found that RhO2N2(A) is an ideal catalyst for H2O2 production with an ultra-low overpotential of 0.013 V. The work sheds light on the path to accelerate the data-driven design and discovery of high-performance catalysts.(c) 2022 Elsevier Ltd. All rights reserved.

Automated summary

Electrochemical H2O2 production through selective two-electron oxygen reduction reaction is a promising alternative to the traditional anthraquinone oxidation process. However, it remains challenging to screen high-performance catalysts for H2O2 production due to ambiguous activation mechanisms. In this study, an iterative machine learning (iML) method is proposed to drastically reduce the required training set size. By incorporating spatial coordinate information, the optimal catalytic activity among hundreds of single-atom catalysts can be rapidly screened out. It is found that RhO2N2(A) exhibits an ultra-low overpotential of 0.013 V, making it an ideal catalyst for H2O2 production. This work sheds light on accelerating the data-driven design and discovery of high-performance catalysts.