Dynamic flow experiments for Bayesian optimization of a single process objective
Name
d4re00543k.pdf
Description
Published version
Size
2.82 MB
Format
Adobe PDF
Checksum (MD5)
4ec076db2ad7a67619d0af106114c01f
Author(s)
Florit, Federico
Nandiwale, Kakasaheb Y
Armstrong, Cameron T
Grohowalski, Katharina
Diaz, Angel R
Mustakis, Jason
Guinness, Steven M
Jensen, Klavs F
Date Issued
December 11, 2024
Journal
Reaction Chemistry & Engineering
Publisher
Royal Society of Chemistry
Citation
Florit, Federico, Nandiwale, Kakasaheb Y, Armstrong, Cameron T, Grohowalski, Katharina, Diaz, Angel R et al. 2024. "Dynamic flow experiments for Bayesian optimization of a single process objective." Reaction Chemistry & Engineering, 10 (3).
Version
Final published version
Abstract
A new method, named dynamic experiment optimization (DynO), is developed for the current needs of chemical reaction optimization by leveraging for the first time both Bayesian optimization and data-rich dynamic experimentation in flow chemistry. DynO is readily implementable in automated systems and it is augmented with simple stopping criteria to guide non-expert users in fast and reagent-efficient optimization campaigns. The developed algorithms is compared in silico with the algorithm Dragonfly and an optimizer based on random selection, showing remarkable results in Euclidean design spaces superior to Dragonfly. Finally, DynO is validated with an ester hydrolysis reaction on an automated platform showcasing the simplicity of the method.
MIT Department
Massachusetts Institute of Technology. Department of Chemical Engineering
Terms of Use
Creative Commons Attribution-Noncommercial
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1039/d4re00543k
