Despite the widespread applications of homogeneous catalysis with organo-transition metal complexes in fine/specialty chemical syntheses, catalyst and ligand discovery are still based on Edisonian techniques. Existing catalyst/ligand discovery strategies using resource-intensive batch reactors and one-at-a-time experimentation strategies fail to comprehensively explore the experimental space of homogeneous catalytic reactions due to the exponential growth of potential experiments over high dimensional spaces. Therefore, resulting in a slow and expensive catalyst/ligand discovery and development timeframe. Recent advances in flow chemistry and machine learning (ML)-assisted modeling/decision-making strategies provide an exciting opportunity to reshape the catalyst/ligand discovery for transition metal-catalyzed reactions. In this talk, I will present an end-to-end ‘self-driving catalysis lab’ for autonomous ligand structure-yield-selectivity relationship mapping of transition metal-catalyzed reactions enabled by the integration of flow chemistry, robotics, and online characterization with ML. I will discuss how modularization of different stages of homogeneous catalysis in tandem with an ensemble neural network modeling and decision-making under uncertainty can enable resource-efficient navigation through a high-dimensional experimental design space of organo-transition metal complexes. An application of the self-driving catalysis lab for homogeneous hydroformylation of olefins will be presented.

Self-driving catalysis lab: Research acceleration in homogeneous catalysis

Where thousands of chemistry professionals meet to share ideas and advance scientific and technical knowledge. Spring 2023 abstracts, posters, and presentations will launch at the end of March.

ACS Spring 2023

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.