Deeper learning in electrocatalysis: realizing opportunities and addressing challenges

• Published in: Current opinion in chemical engineering Vol. 36; p. 100824
• Main Authors: Keith, John A, McKone, James R, Snyder, Joshua D, Tang, Maureen H
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.06.2022
• ISSN: 2211-3398; 2211-3398
• DOI: 10.1016/j.coche.2022.100824

Emerging techniques in deep learning have created exciting opportunities for next-generation electrochemical technologies. While deep learning has been revolutionizing many research fields, strategies for its implementation for electrocatalysis remain nascent. This Opinion calls on the electrocatalysis community to join together and introduce a paradigm shift by establishing standards for reporting and sharing data from electrocatalysis investigations. We speculate on a possible future where crowd-sourced and standardized data from experimental and computational researchers can be analyzed collectively to better understand fundamental electrochemistry, yielding unprecedented insights for the development of new electrocatalysts. We identify key barriers to realizing this opportunity and how they might be overcome.