Machine learning for yield prediction for chemical reactions using in situ sensors

Davies, Joseph C.; Pattison, David; Hirst, Jonathan D.

Abstract

Machine learning models were developed to predict product formation from time-series reaction data for ten Buchwald-Hartwig coupling reactions. The data was provided by DeepMatter and was collected in their DigitalGlassware cloud platform. The reaction probe has 12 sensors to measure properties of interest, including temperature, pressure, and colour. Colour was a good predictor of product formation for this reaction and machine learning models were able to learn which of the properties were important. Predictions for the current product formation (in terms of % yield) had a mean absolute error of 1.2%. For predicting 30, 60 and 120 min ahead the error rose to 3.4, 4.1 and 4.6%, respectively. The work here presents an example into the insight that can be obtained from applying machine learning methods to sensor data in synthetic chemistry.

Citation

Davies, J. C., Pattison, D., & Hirst, J. D. (2023). Machine learning for yield prediction for chemical reactions using in situ sensors. Journal of Molecular Graphics and Modelling, 118, Article 108356. https://doi.org/10.1016/j.jmgm.2022.108356

• Journal Article Type: Article
• Acceptance Date: Sep 30, 2022
• Online Publication Date: Oct 13, 2022
• Publication Date: Jan 1, 2023
• Deposit Date: Oct 15, 2022
• Publicly Available Date: Oct 20, 2022
• Journal: Journal of Molecular Graphics and Modelling
• Print ISSN: 1093-3263
• Electronic ISSN: 1873-4243
• Publisher: Elsevier BV
• Peer Reviewed: Peer Reviewed
• Volume: 118
• Article Number: 108356
• DOI: https://doi.org/10.1016/j.jmgm.2022.108356
• Keywords: Materials Chemistry, Computer Graphics and Computer-Aided Design, Physical and Theoretical Chemistry, Spectroscopy
• Public URL: https://nottingham-repository.worktribe.com/output/12329773
• Publisher URL: https://www.sciencedirect.com/science/article/pii/S1093326322002352?via%3Dihub