Self-optimization of chemical reactions

Autonomous reaction platforms combine automated experiments with machine learning to find optimal reaction conditions with few experiments. This foundational work dates from before the group was founded.

Background

This line of work originates from Artur M. Schweidtmann's research with Prof. Alexei Lapkin at the University of Cambridge and his PhD research at RWTH Aachen University. It is no longer an active research line of the group, but its methods, such as Bayesian and multi-objective optimization with machine learning models, are used in our current work on optimization with surrogate models.

Approach

Autonomous reaction platforms can find optimal reaction conditions for continuous variables, such as temperature, residence time, and concentrations, by using machine learning algorithms that decide which experiment to run next. Multi-objective algorithms identify the trade-off (Pareto front) between objectives such as yield and cost. Discrete decisions, such as solvent selection, can be included through continuous molecular descriptors.

Key publications

  • Schweidtmann, A. M., Clayton, A. D., Holmes, N., Bradford, E., Bourne, R. A., & Lapkin, A. A. (2018). Machine learning meets continuous flow chemistry: Automated optimization towards the Pareto front of multiple objectives. Chemical Engineering Journal, 352, 277–282. doi:10.1016/j.cej.2018.07.031 · Details
  • Amar, Y., Schweidtmann, A. M., Deutsch, P., Cao, L., & Lapkin, A. (2019). Machine learning and molecular descriptors enable rational solvent selection in asymmetric catalysis. Chemical Science, 10(27), 6697–6706. doi:10.1039/C9SC01844A · Details
  • Clayton, A. D., Schweidtmann, A. M., Clemens, G., Manson, J. A., Taylor, C. J., Niño, C. G., Chamberlain, T. W., Kapur, N., Blacker, A. J., Lapkin, A. A., & Bourne, R. A. (2020). Automated self-optimisation of multi-step reaction and separation processes using machine learning. Chemical Engineering Journal, 384, 123340. doi:10.1016/j.cej.2019.123340 · Details
  • Jose, N. A., Kovalev, M., Bradford, E., Schweidtmann, A. M., Zeng, H. C., & Lapkin, A. A. (2021). Pushing nanomaterials up to the kilogram scale – An accelerated approach for synthesizing antimicrobial ZnO with high shear reactors, machine learning and high-throughput analysis. Chemical Engineering Journal, 426, 131345. doi:10.1016/j.cej.2021.131345 · Details
← All projects