Knowledge extraction in catalysis utilizing design of experiments and machine learning

Leave No Photon Behind: Artificial Intelligence in Multiscale Physics of Photocatalyst and Photoreactor Design

Although solar fuels photocatalysis offers the promise of converting carbon dioxide directly with sunlight as commercially scalable solutions have remained elusive over the past few decades, despite significant advancements in photocatalysis band-gap engineering and atomic site activity. The primary challenge lies not in the discovery of new catalyst materials, which are abundant, but in overcoming the bottlenecks related to material-photoreactor synergy. These factors include achieving photogeneration and charge-carrier recombination at reactive sites, utilizing high mass transfer efficiency supports, maximizing solar collection, and achieving uniform light distribution within a reactor. Addressing this multi-dimensional problem necessitates harnessing machine learning techniques to analyze real-world data from photoreactors and material properties. In this perspective, the challenges are outlined associated with each bottleneck factor, review relevant data analysis studies, and assess the requirements for developing a comprehensive solution that can unlock the full potential of solar fuels photocatalysis technology. Physics-informed machine learning (or Physics Neural Networks) may be the key to advancing this important area from disparate data towards optimal reactor solutions.

DoE-Assisted Development of a 2H-MoS2 -Catalyzed Approach for the Production of Indole Derivatives

2H-MoS2 is an appealing semiconductor because of its Earth-abundant nature, cheapness, and low toxicity. This material has shown promising catalytic activity for various energy-related processes, but its use in catalysis for C-C bond forming reactions towards useful organic compounds is still largely unexplored. The lack of examples in organic synthesis is mainly due to the intrinsic difficulties of using bulk 2H-MoS2 (e. g., low surface area), which implies the reliance on high catalytic loadings for obtaining acceptable yields. This makes the optimization process more expensive and tedious. Here, we report the development of a 2H-MoS2 -mediated synthesis of valuable bis(indolyl)methane derivatives, using indoles and benzaldehydes as starting materials. Exploiting the Design of Experiments (DoE) method, we identified the critical parameters affecting the catalytic performance of commercial 2H-MoS2 powder and optimized the reaction conditions. Lastly, we demonstrated that the catalytic system has versatility and good tolerance towards functional group variations of the reagents.