Work

Optimal Experiment Campaigns under Uncertainty Minimizing Bayes Risk

Year: 2025

Type: article

Abstract: Applying model-based design of experiments to compute maximally-informative campaigns with multiple parallel runs is challenging. Herein, we develop a systematic framework for recasting an experiment design problem for model parameter precision as one of discrimination between multiple rival models with different uncertain parameter realizations. We use an algebraic upper bound on the Bayes Risk as information criterion and apply a search procedure that iterates between an effort-based optimization step followed by a gradient-based refinement step. Through the case study of a fed-batch reactor, we show that a Bayes Risk discrimination strategy can provide highly-informative experimental campaigns to improve parameter precision, while being computationally advantageous compared to conventional FIM-based design strategies and capable of handling structurally unidentifiable problems.

Source: IFAC-PapersOnLine

DOI: 10.1016/j.ifacol.2025.07.196

Authors: Benoît Chachuat, Marco Sandrin, Constantinos C. Pantelides

Institution: Imperial College London

Language: English

Topic: Optimal Experimental Design Methods

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: diamond

Funders: Eli Lilly and Company, Horizon 2020 Framework Programme, Engineering and Physical Sciences Research Council, H2020 Marie Skłodowska-Curie Actions

Awards: Prosperity Partnership Call 3 Strategic Students-Eli Lilly and Imperial College London, A knowledge-based training network for digitalisation of photosynthetic bioprocesses