Recent advances and applications of machine learning in electrocatalysis

Abstract

Electrocatalysis plays an important role in the production of clean energy and pollution control. Researchers have made great efforts to explore efficient, stable, and inexpensive electrocatalysts. However, traditional trial and error experiments and theoretical calculations require a significant amount of time and resources, which limits the development speed of electrocatalysts. Fortunately, the rapid development of machine learning (ML) has brought new solutions to scientific problems and new paradigms to the development of electrocatalysts. The combination of ML with experimental and theoretical calculations has propelled significant advancements in electrocatalysis research, particularly in the areas of materials screening, performance prediction, and catalysis theory development. In this review, we present a comprehensive overview of the workflow and cutting-edge techniques of ML in the field of electrocatalysis. In addition, we discuss the diverse applications of ML in predicting performance, guiding synthesis, and exploring the theory of catalysis. Finally, we conclude the review with the challenges of ML in electrocatalysis.