Chemically-informed data-driven optimization (ChIDDO): leveraging physical models and Bayesian learning to accelerate chemical research

• Published in: Reaction chemistry & engineering Vol. 7; no. 4; pp. 855 - 865
• Main Authors: Frey, Daniel, Shin, Ju Hee, Musco, Christopher, Modestino, Miguel A
• Format: Journal Article
• Language: English
• Published: Cambridge Royal Society of Chemistry 29.03.2022
• Subjects: Accuracy; Algorithms; Bayesian analysis; Chemical reactions; Machine learning; Optimization
• ISSN: 2058-9883; 2058-9883
• DOI: 10.1039/d2re00005a

Current methods of finding optimal experimental conditions, Edisonian systematic searches, often inefficiently evaluate suboptimal design points and require fine resolution to identify near optimal conditions. For expensive experimental campaigns or those with large design spaces, the shortcomings of the status quo approaches are more significant. Here, we extend Bayesian optimization (BO) and introduce a chemically-informed data-driven optimization (ChIDDO) approach. This approach uses inexpensive and low-fidelity information obtained from physical models of chemical processes and subsequently combines it with expensive and high-fidelity experimental data to optimize a common objective function. Using common optimization benchmark objective functions, we describe scenarios in which the ChIDDO algorithm outperforms the traditional BO approach, and then implement the algorithm on a simulated electrochemical engineering optimization problem. A method combining information from both experiments and physics-based models is used to improve experimental Bayesian optimization.