Application of an Electrochemical Microflow Reactor for Cyanosilylation: Machine Learning-Assisted Exploration of Suitable Reaction Conditions for Semi-Large-Scale Synthesis

Abstract

Cyanosilylation of carbonyl compounds provides protected cyanohydrins, which can be converted into many kinds of compounds such as amino alcohols, amides, esters, and carboxylic acids. In particular, the use of trimethylsilyl cyanide as the sole carbon source can avoid the need for more toxic inorganic cyanides. In this paper, we describe an electrochemically initiated cyanosilylation of carbonyl compounds and its application to a microflow reactor. Furthermore, to identify suitable reaction conditions, which reflect considerations beyond simply a high yield, we demonstrate machine learning-assisted optimization. Machine learning can be used to adjust the current and flow rate at the same time and identify the conditions needed to achieve the best productivity.

Investigation of Parameter Control for Electrocatalytic Semihydrogenation in a Proton-Exchange Membrane Reactor Utilizing Bayesian Optimization

“…Naturally, optimizing a reaction with multiple parameters requires considerable energy, time, and chemical and human resources. Thus, to minimize resource requirements, we decided to utilize Bayesian optimization for reaction optimization (Ahneman et al, 2018;Kondo et al, 2020;Sato et al, 2021;Shields et al, 2021;Sugisawa et al, 2021).…”

Interfacing single-atom catalysis with continuous-flow organic electrosynthesis

“…On top of that, and given the modularity of these systems, large-scale reactions are also within reach, as numbering-approaches allow to increase the scale in a cheap, robust, safe, and sustainable fashion. In addition to that, computational fluid dynamic 293 and machine learning-assisted models 294 are also being applied to further understand the different physical processes occurring in the electrochemical cells, such as hydrodynamics, mass transport, heat transfer and current distribution, in an effort to streamline the choice of suitable reaction conditions. DFT and computational modelling can be utilised to predict the overpotential requirements of SAC-based electrosynthetic transformations, providing a mechanistic understanding and facilitating the deduction of structure–function correlations, from which more efficient and optimal single-atom electrocatalysts can be rationally designed and fabricated.…”

Working at the interfaces of data science and synthetic electrochemistry

“…The application of DOE in flow electrochemistry has also been demonstrated [ 27 – 29 ]. Wirth and coworkers disclosed the decarboxylative alkoxylation of chiral N -aryloyl amino acids to generate enantiomerically enriched N,O -acetals in flow ( Fig.…”