Chemical Engineering and Industrial Chemistry

AROPS: A Framework of Automated Reaction Optimization with Parallelized Scheduling



With the development of automated experimental platforms and optimization algorithms, chemists can easily optimize chemical reactions in an automated and high-throughput fashion. However, the modules in existing automated experimental platforms are operated in a predefined way without orchestrating with the optimization algorithm, thus leaving room for further efficiency improvement. Here, we introduced a framework of automated reaction optimization with parallelized scheduling (AROPS) to realize the integration of optimization algorithm and module scheduling. AROPS relies on a customized Bayesian optimizer to solve multi-reactor/analyzer reaction optimization problems with three different scheduling modes to arrange tasks for various experimental modules. In addition, a mechanism based on probability of improvement (PI) for discarding unpromising on-going experiments was developed to facilitate freeing-up valuable experimental resources in parallelized optimization. We tested the performance of AROPS using a hardware emulator on three typical benchmark reactions encountered in organic synthesis, illustrating that AROPS can trade off optimization time and cost according to the chemists’ preference.

Version notes

Correct author order.


Thumbnail image of manuscript_submitted.pdf

Supplementary material

Thumbnail image of SI.pdf
The supporting information of AROPS
The supporting description of AROPS and the benchmarks as well as the supporting figures of results section (PDF).