Production of functional molecules from renewable bio-feedstocks and bio-waste has the potential to significantly reduce the greenhouse gas emissions. However, the development of such processes commonly requires invention and scale-up of highly selective and robust chemistry for complex reaction networks in bio-waste mixtures. We demonstrate an approach to optimising a chemical route for multiple objectives starting from a mixture derived from bio-waste. We optimise the recently developed route from a mixture of waste terpenes to p-cymene. In the first reaction step it was not feasible to build a detailed kinetic model. A Bayesian multiple objectives optimisation algorithm TS-EMO was used to optimise the first two steps of reaction for maximum conversion and selectivity. The model suggests a set of very different conditions that result in simultaneous high values of the two outputs.

Rational solvent selection remains a significant challenge in process development. Here we describe a hybrid mechanistic-machine learning approach, geared towards automated process development workflow. A library of 459 solvents was used, for which 12 conventional molecular descriptors, two reaction-specific descriptors, and additional descriptors based on screening charge density, were calculated. Gaussian process surrogate models were trained on experimental data from a Rh(CO)₂(acac)/Josiphos catalysed asymmetric hydrogenation of a chiral α-β unsaturated γ-lactam. With two simultaneous objectives-high conversion and high diastereomeric excess-the multi-objective algorithm, trained on the initial dataset of 25 solvents, has identified solvents leading to better reaction outcomes. In addition to being a powerful design of experiments (DoE) methodology, the resulting Gaussian process surrogate model for conversion is, in statistical terms, predictive, with a cross-validation correlation coefficient of 0.84. After identifying promising solvents, the composition of solvent mixtures and optimal reaction temperature were found using a black-box Bayesian optimisation. We then demonstrated the application of a new genetic programming approach to select an appropriate machine learning model for a specific physical system, which should allow the transition of the overall process development workflow into the future robotic laboratories.