Data‐Driven Machine Learning for Understanding Surface Structures of Heterogeneous Catalysts

• Published in: Angewandte Chemie International Edition Vol. 62; no. 9; pp. e202216383 - n/a
• Main Authors: Li, Haobo, Jiao, Yan, Davey, Kenneth, Qiao, Shi‐Zhang
• Format: Journal Article
• Language: English
• Published: Germany Wiley Subscription Services, Inc 20.02.2023
• Edition: International ed. in English
• Subjects: Adsorption; Catalysts; Heterogeneous Catalysts; In-Situ Characterization; Learning algorithms; Machine learning; Machine Learning (ML); Operando Computation; Optimization; Surface chemistry; Surface Structures; Operando Computation; Surface Structures; Heterogeneous Catalysts; Machine Learning (ML); In-Situ Characterization
• ISSN: 1433-7851; 1521-3773; 1521-3773
• DOI: 10.1002/anie.202216383

The design of heterogeneous catalysts is necessarily surface‐focused, generally achieved via optimization of adsorption energy and microkinetic modelling. A prerequisite is to ensure the adsorption energy is physically meaningful is the stable existence of the conceived active‐site structure on the surface. The development of improved understanding of the catalyst surface, however, is challenging practically because of the complex nature of dynamic surface formation and evolution under in‐situ reactions. We propose therefore data‐driven machine‐learning (ML) approaches as a solution. In this Minireview we summarize recent progress in using machine‐learning to search and predict (meta)stable structures, assist operando simulation under reaction conditions and micro‐environments, and critically analyze experimental characterization data. We conclude that ML will become the new norm to lower costs associated with discovery and design of optimal heterogeneous catalysts. Heterogeneous catalytic reactions occur at the surface of catalysts. The catalyst surface structure is highly complex and changes with reaction conditions and surrounding micro‐environment. This Minireviewsummarizes recent progress in using state‐of‐the‐art data‐driven machine‐learning (ML) to accelerate the research in heterogeneous catalyst surface by assisting catalysis experiments, in‐situ characterizations, and operando computational simulations.