A bootstrap-aggregated hybrid semi-parametric modeling framework for bioprocess development
- 2 August 2019
- journal article
- research article
- Published by Springer Nature in Bioprocess and Biosystems Engineering
- Vol. 42 (11) , 1853-1865
Abstract
Hybrid semi-parametric modeling, combining mechanistic and machine-learning methods, has proven to be a powerful method for process development. This paper proposes bootstrap aggregation to increase the predictive power of hybrid semi-parametric models when the process data are obtained by statistical design of experiments. A fed-batch Escherichia coli optimization problem is addressed, in which three factors (biomass growth setpoint, temperature, and biomass concentration at induction) were designed statistically to identify optimal cell growth and recombinant protein expression conditions. Synthetic data sets were generated applying three distinct design methods, namely, Box–Behnken, central composite, and Doehlert design. Bootstrap-aggregated hybrid models were developed for the three designs and compared against the respective non-aggregated versions. It is shown that bootstrap aggregation significantly decreases the prediction mean squared error of new batch experiments for all three designs. The number of (best) models to aggregate is a key calibration parameter that needs to be fine-tuned in each problem. The Doehlert design was slightly better than the other designs in the identification of the process optimum. Finally, the availability of several predictions allowed computing error bounds for the different parts of the model, which provides an additional insight into the variation of predictions within the model components.Keywords
This publication has 27 references indexed in Scilit:
- Hybrid semi-parametric modeling in process systems engineering: Past, present and futureComputers & Chemical Engineering, 2014
- A novel identification method for hybrid (N)PLS dynamical systems with application to bioprocessesExpert Systems with Applications, 2011
- Modelling biochemical networks with intrinsic time delays: a hybrid semi-parametric approachBMC Systems Biology, 2010
- Hybrid modeling of penicillin fermentation process based on least square support vector machineChemical Engineering Research and Design, 2010
- Combining first principles modelling and artificial neural networks: a general framework2003
- An efficient model development strategy for bioprocesses based on neural networks in macroscopic balances: Part IIBiotechnology and Bioengineering, 1999
- How to increase the performance of models for process optimization and controlJournal of Biotechnology, 1997
- Modeling chemical processes using prior knowledge and neural networksAIChE Journal, 1994
- Bioprocess optimization and control: Application of hybrid modellingJournal of Biotechnology, 1994
- A hybrid neural network‐first principles approach to process modelingAIChE Journal, 1992