Dynamic modeling and optimization of sustainable algal production with uncertainty using multivariate Gaussian processes

Eric Bradford, Artur M. Schweidtmann, Dongda Zhang, Keju Jing, Ehecatl Antonio del Rio-Chanona*

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

27 Citations (Scopus)

Abstract

Dynamic modeling is an important tool to gain better understanding of complex bioprocesses and to determine optimal operating conditions for process control. Currently, two modeling methodologies have been applied to biosystems: kinetic modeling, which necessitates deep mechanistic knowledge, and artificial neural networks (ANN), which in most cases cannot incorporate process uncertainty. The goal of this study is to introduce an alternative modeling strategy, namely Gaussian processes (GP), which incorporates uncertainty but does not require complicated kinetic information. To test the performance of this strategy, GPs were applied to model microalgae growth and lutein production based on existing experimental datasets and compared against the results of previous ANNs. Furthermore, a dynamic optimization under uncertainty is performed, avoiding over-optimistic optimization outside of the model's validity. The results show that GPs possess comparable prediction capabilities to ANNs for long-term dynamic bioprocess modeling, while accounting for model uncertainty. This strongly suggests their potential applications in bioprocess systems engineering.

Original languageEnglish
Pages (from-to)143-158
JournalComputers and Chemical Engineering
Volume118
DOIs
Publication statusPublished - 2018
Externally publishedYes

Keywords

  • Artificial neural network
  • Dynamic bioprocess
  • Gaussian process
  • Machine learning
  • Optimization under uncertainty

Fingerprint

Dive into the research topics of 'Dynamic modeling and optimization of sustainable algal production with uncertainty using multivariate Gaussian processes'. Together they form a unique fingerprint.

Cite this