Hybrid Neural Network Models of Bioprocesses: A Comparative Study

Grosfils, Aline; Wouwer, Alain Vande; Bogaerts, Philippe

doi:10.3182/20050703-6-cz-1902.02230

Cited by 3 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…artificial neural networks (Chen et al, 2000), Gaussian process (GP) models (Del Rio-Chanona et al, 2019;Bradford et al, 2018). Black models have satisfactory modeling performance after careful training with the experimental data (Grosfils et al, 2005). However, they are totally data-driven approaches with little biological interpretations, even though some of them are hybrid (Von Stosch et al, 2014;Fiedler and Schuppert, 2008), e.g.…”

Section: Introductionmentioning

confidence: 99%

Identification of nonlinear kinetics of macroscopic bio-reactions using multilinear Gaussian processes

Wang

Risuleo

Jacobsen

et al. 2020

Computers & Chemical Engineering

View full text Add to dashboard Cite

In biological systems, nonlinear kinetic relationships between metabolites of interest are modeled for various purposes. Usually, little a priori knowledge is available in such models. Identifying the unknown kinetics is, therefore, a critical step which can be very challenging due to the problems of (i) model selection and (ii) nonlinear parameter estimation. In this paper, we aim to address these problems systematically in a framework based on multilinear Gaussian processes using a family of kernels tailored to typical behaviours of modulation effects such as activation and inhibition or combinations thereof. Using one such process as a model for each modulation effect leads to a much more flexible model than conventional parametric models, e.g., the Monod model. The resulting models of the modulation effects can also be used as a starting point for estimating parametric kinetic models. As each modulation effect is modeled separately, this task is greatly simplified compared to the conventional approach where the parameters in all modulation functions have to be estimated simultaneously. We also show how the type of modulation effect can be selected automatically by way of regularization, thus bypassing the model selection problem. The resulting parameter estimates can be used as initial estimates in the conventional approach where the full model is estimated. Numerical experiments, including fed-batch simulations, are conducted to demonstrate our methods.

show abstract