Electrochemical Carbon-Ferrier Rearrangement Using a Microflow Reactor and Machine Learning-Assisted Exploration of Suitable Conditions

The use of a flow reactor in electrolysis enables efficient and scalable synthesis, which is normally difficult to accomplish by batch reactors. We achieved electrochemical carbon-Ferrier rearrangement which proceeded with catalytic anodic oxidation, and this transformation could be performed using an electrochemical flow reactor. Additional numeric parameters derived from the flow reactor could be adjusted using Gaussian process regression (GPR), which is a machine learning method. GPR enables the construction of two models to estimate yields and productivity, and the reaction condition can be selected rationally.

Automated summary

The use of a flow reactor in electrolysis allows for efficient and scalable synthesis, which is typically challenging with batch reactors. We successfully achieved electrochemical carbon-Ferrier rearrangement using catalytic anodic oxidation in an electrochemical flow reactor. Gaussian process regression (GPR), a machine learning method, enabled the adjustment of numerical parameters derived from the flow reactor. GPR also facilitated the construction of two models for estimating yields and productivity, allowing for rational selection of reaction conditions.