Meta-learning for sample-efficient Bayesian optimisation of fed-batch processes

TL;DR

This paper introduces SANODEP, a meta-learning model that enhances Bayesian Optimization for time-varying batch processes, enabling more efficient process optimization with fewer experiments.

Contribution

The work demonstrates that SANODEP outperforms Gaussian Process models in few-shot Bayesian Optimization for batch process applications, especially under limited data conditions.

Findings

SANODEP achieves better optimization objectives with fewer experimental runs.

It generalizes well across different batch distributions.

The approach accelerates initial process optimization steps.

Abstract

The optimisation of fed-batch (bio)chemical process recipes is subject to inherent, underlying, and unmeasurable fluctuations across batches, whose trajectories are difficult to model and costly to measure. Bayesian Optimisation (BayesOpt) is a powerful tool for sampling and optimisation of expensive-to-measure functions. Gaussian Processes (GPs), the surrogate models used in BayesOpt, are static, forecast poorly, and lack generalisation across experiments, limiting their applicability to time-varying batch processes with stochastic parameters, i.e., process fluctuations. This work investigates System-Aware Neural ODE Processes (SANODEP) as a meta-learning model to overcome the limitations of GPs and increase few-shot optimisation performance in BayesOpt. Using a penicillin batch production case study, we find that SANODEP outperforms GP-based BayesOpt in the low-data regime, resulting in improved objectives when few experimental runs are performed. These improvements are observed in both on- and off-distribution batches, highlighting the generalisation capabilities of SANODEP. Using this approach, batch process operators can accelerate the initial optimisation steps in BayesOpt by deploying meta-learning or optimise the process with fewer experiments when the experimental cost is high.