Treffer: Machine learning aided synthesis and screening of HER catalyst: Present developments and prospects.

There have been significant advancements in catalysis today, especially with the aid of artificial intelligence (AI). Understanding the relationship between the descriptors and catalytic performance and underlying principles is crucial for hydrogen evolution reaction (HER) catalysis. As of today, the usage and application of machine learning (ML) are soaring and there has been a phenomenal demand owing to its immense pattern recognition capability and optimization potential. Its applications in computational quantum mechanical modeling have inspired promising development in HER catalyst scrutiny and screening. The present communication reviews the general scheme of ML, data sources, and computational tools for HER catalyst screening and therefore provides a strong basis for its application. Furthermore, the analysis elucidates how ML algorithms are used for the prediction of a) adsorption energies, b) reaction descriptors, c) structure–property relationships, d) catalyst discovery, and e) synthesis conditions and reaction design of HER catalysts. Lastly, key constraints and the need for an integrative platform have been highlighted. Based on literature surveys, recent trends, material advancements, systems understanding, and key challenges in deploying ML tools, future directions with a road map have been provided for an evolved design and development in the case of HER catalysis. [ABSTRACT FROM AUTHOR]

Copyright of Catalysis Reviews: Science & Engineering is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)