Active Learning as a Tool for Optimizing "Plug-n-Play" Electrochemical Atom Transfer Radical Polymerization

Active Learning as a Tool for Optimizing "Plug-n-Play" Electrochemical Atom Transfer Radical Polymerization. Zhao, B., Cheng, J., Gao, J., Haddleton, D. M., & Wilson, P. MACROMOLECULAR CHEMISTRY AND PHYSICS, June, 2023.
doi abstract bibtex

A recently reported "plug-n-play" approach to simplified electrochemical atom transfer radical polymerization (seATRP) is investigated using machine learning. It is shown that Bayesian optimization via an active learning (AL) algorithm accelerates optimization of the polymerization of oligo(ethylene glycol methyl ether acrylate)(480) (OEGA(480)) in water. Molecular weight distribution (M-w/M-n; dispersity; D-m) is the output selected for optimization targeting poly(oligo[ethylene glycol methyl ether acrylate]) (POEGA(480)) with low dispersity (D-m \textless 1.30). Input variables included applied potential (E-app), [M] and [M]/[I], which led to a potential space of 275 possible reaction conditions. From a training data set of seven reactions, selected to yield uncontrolled POEGA(480) with higher dispersities (D-m \textgreater 1.5), ten iteration loops are performed. During each iteration the algorithm suggests the next reaction conditions. The reactions are then performed and the conversion, number average molecular weight (M-n) and D-m values are recorded and the D-m values fed back into the algorithm. Overall, 80% of the experiments yield POEGA with D-m \textless 1.30. Conversely, only 30% of experiments performed using reaction conditions selected at random from the possible reaction space yield POEGA with D-m \textless 1.30. This study suggests that adopting AL methods can improve the efficiency of optimizing a given seATRP reaction.

@article{zhao_active_2023,
	title = {Active {Learning} as a {Tool} for {Optimizing} "{Plug}-n-{Play}" {Electrochemical} {Atom} {Transfer} {Radical} {Polymerization}},
	volume = {224},
	issn = {1022-1352},
	doi = {10.1002/macp.202300039},
	abstract = {A recently reported "plug-n-play" approach to simplified electrochemical atom transfer radical polymerization (seATRP) is investigated using machine learning. It is shown that Bayesian optimization via an active learning (AL) algorithm accelerates optimization of the polymerization of oligo(ethylene glycol methyl ether acrylate)(480) (OEGA(480)) in water. Molecular weight distribution (M-w/M-n; dispersity; D-m) is the output selected for optimization targeting poly(oligo[ethylene glycol methyl ether acrylate]) (POEGA(480)) with low dispersity (D-m {\textless} 1.30). Input variables included applied potential (E-app), [M] and [M]/[I], which led to a potential space of 275 possible reaction conditions. From a training data set of seven reactions, selected to yield uncontrolled POEGA(480) with higher dispersities (D-m {\textgreater} 1.5), ten iteration loops are performed. During each iteration the algorithm suggests the next reaction conditions. The reactions are then performed and the conversion, number average molecular weight (M-n) and D-m values are recorded and the D-m values fed back into the algorithm. Overall, 80\% of the experiments yield POEGA with D-m {\textless} 1.30. Conversely, only 30\% of experiments performed using reaction conditions selected at random from the possible reaction space yield POEGA with D-m {\textless} 1.30. This study suggests that adopting AL methods can improve the efficiency of optimizing a given seATRP reaction.},
	number = {12},
	urldate = {2023-05-07},
	journal = {MACROMOLECULAR CHEMISTRY AND PHYSICS},
	author = {Zhao, Boyu and Cheng, Jiahao and Gao, Junlong and Haddleton, David. M. and Wilson, Paul},
	month = jun,
	year = {2023},
}

Downloads: 0

{"_id":"BGhRg2nM7y8JwKEuv","bibbaseid":"zhao-cheng-gao-haddleton-wilson-activelearningasatoolforoptimizingplugnplayelectrochemicalatomtransferradicalpolymerization-2023","author_short":["Zhao, B.","Cheng, J.","Gao, J.","Haddleton, D. M.","Wilson, P."],"bibdata":{"bibtype":"article","type":"article","title":"Active Learning as a Tool for Optimizing \"Plug-n-Play\" Electrochemical Atom Transfer Radical Polymerization","volume":"224","issn":"1022-1352","doi":"10.1002/macp.202300039","abstract":"A recently reported \"plug-n-play\" approach to simplified electrochemical atom transfer radical polymerization (seATRP) is investigated using machine learning. It is shown that Bayesian optimization via an active learning (AL) algorithm accelerates optimization of the polymerization of oligo(ethylene glycol methyl ether acrylate)(480) (OEGA(480)) in water. Molecular weight distribution (M-w/M-n; dispersity; D-m) is the output selected for optimization targeting poly(oligo[ethylene glycol methyl ether acrylate]) (POEGA(480)) with low dispersity (D-m \\textless 1.30). Input variables included applied potential (E-app), [M] and [M]/[I], which led to a potential space of 275 possible reaction conditions. From a training data set of seven reactions, selected to yield uncontrolled POEGA(480) with higher dispersities (D-m \\textgreater 1.5), ten iteration loops are performed. During each iteration the algorithm suggests the next reaction conditions. The reactions are then performed and the conversion, number average molecular weight (M-n) and D-m values are recorded and the D-m values fed back into the algorithm. Overall, 80% of the experiments yield POEGA with D-m \\textless 1.30. Conversely, only 30% of experiments performed using reaction conditions selected at random from the possible reaction space yield POEGA with D-m \\textless 1.30. This study suggests that adopting AL methods can improve the efficiency of optimizing a given seATRP reaction.","number":"12","urldate":"2023-05-07","journal":"MACROMOLECULAR CHEMISTRY AND PHYSICS","author":[{"propositions":[],"lastnames":["Zhao"],"firstnames":["Boyu"],"suffixes":[]},{"propositions":[],"lastnames":["Cheng"],"firstnames":["Jiahao"],"suffixes":[]},{"propositions":[],"lastnames":["Gao"],"firstnames":["Junlong"],"suffixes":[]},{"propositions":[],"lastnames":["Haddleton"],"firstnames":["David.","M."],"suffixes":[]},{"propositions":[],"lastnames":["Wilson"],"firstnames":["Paul"],"suffixes":[]}],"month":"June","year":"2023","bibtex":"@article{zhao_active_2023,\n\ttitle = {Active {Learning} as a {Tool} for {Optimizing} \"{Plug}-n-{Play}\" {Electrochemical} {Atom} {Transfer} {Radical} {Polymerization}},\n\tvolume = {224},\n\tissn = {1022-1352},\n\tdoi = {10.1002/macp.202300039},\n\tabstract = {A recently reported \"plug-n-play\" approach to simplified electrochemical atom transfer radical polymerization (seATRP) is investigated using machine learning. It is shown that Bayesian optimization via an active learning (AL) algorithm accelerates optimization of the polymerization of oligo(ethylene glycol methyl ether acrylate)(480) (OEGA(480)) in water. Molecular weight distribution (M-w/M-n; dispersity; D-m) is the output selected for optimization targeting poly(oligo[ethylene glycol methyl ether acrylate]) (POEGA(480)) with low dispersity (D-m {\\textless} 1.30). Input variables included applied potential (E-app), [M] and [M]/[I], which led to a potential space of 275 possible reaction conditions. From a training data set of seven reactions, selected to yield uncontrolled POEGA(480) with higher dispersities (D-m {\\textgreater} 1.5), ten iteration loops are performed. During each iteration the algorithm suggests the next reaction conditions. The reactions are then performed and the conversion, number average molecular weight (M-n) and D-m values are recorded and the D-m values fed back into the algorithm. Overall, 80\\% of the experiments yield POEGA with D-m {\\textless} 1.30. Conversely, only 30\\% of experiments performed using reaction conditions selected at random from the possible reaction space yield POEGA with D-m {\\textless} 1.30. This study suggests that adopting AL methods can improve the efficiency of optimizing a given seATRP reaction.},\n\tnumber = {12},\n\turldate = {2023-05-07},\n\tjournal = {MACROMOLECULAR CHEMISTRY AND PHYSICS},\n\tauthor = {Zhao, Boyu and Cheng, Jiahao and Gao, Junlong and Haddleton, David. M. and Wilson, Paul},\n\tmonth = jun,\n\tyear = {2023},\n}\n\n","author_short":["Zhao, B.","Cheng, J.","Gao, J.","Haddleton, D. M.","Wilson, P."],"key":"zhao_active_2023","id":"zhao_active_2023","bibbaseid":"zhao-cheng-gao-haddleton-wilson-activelearningasatoolforoptimizingplugnplayelectrochemicalatomtransferradicalpolymerization-2023","role":"author","urls":{},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://warwick.ac.uk/fac/cross_fac/wesic/research/wpg/research/WPGsep2024.bib","dataSources":["m4fxWT6XKrYfGbZFR","GBhqMC9hjyD5vqptk","6idaYK6okJY39mWgG"],"keywords":[],"search_terms":["active","learning","tool","optimizing","plug","play","electrochemical","atom","transfer","radical","polymerization","zhao","cheng","gao","haddleton","wilson"],"title":"Active Learning as a Tool for Optimizing \"Plug-n-Play\" Electrochemical Atom Transfer Radical Polymerization","year":2023}