Virtual Reaction Condition Optimization based on Machine Learning for a Small Number of Experiments in High-dimensional Continuous and Discrete Variables

Mikito Fujinami, Junji Seino, Takumi Nukazawa, Shintaro Ishida, Takeaki Iwamoto, Hiromi Nakai

Chemistry Letters · 2019 · 10 citations · 20 references

DOIFull text

Open access

Concepts

Abstract

We examined a virtual simulation scheme for reaction condition optimization using machine learning for a small number of experiments with nine reaction conditions, consisting of five continuous and four discrete variables. Simulations were performed for predicting product yields in a synthetic reaction of tetrasilabicyclo[1.1.0]but-1(3)-ene (SiBBE). The performances in terms of accuracy and efficiency in the simulations and the chemical implications of the results were discussed. A virtual simulation of reaction condition optimization based on machine learning was performed for a reaction including nine experimental conditions. The simulation aimed to determine the best reaction condition with high product yield and large product mass through iterative prediction and learning of experimental results. The scheme performed reasonably to reduce the experimental attempts.

References

20