Improving Microalgae Growth Modeling of Outdoor Cultivation with Light History Data using Machine Learning Models: A Comparative Study

Research output: Contribution to journalResearch articleContributedpeer-review

Contributors

  • Yen-Cheng Yeh - , Fraunhofer Institute for Interfacial Engineering and Biotechnology (First author)
  • Tehreem Syed - , Chair of Process Control Systems (First author)
  • Gordon Brinitzer - , Fraunhofer Institute for Interfacial Engineering and Biotechnology (Author)
  • Konstantin Frick - , Fraunhofer Institute for Interfacial Engineering and Biotechnology (Author)
  • Ulrike Schmid-Staiger - , Fraunhofer Institute for Interfacial Engineering and Biotechnology (Author)
  • Bernard Haasdonk - , University of Stuttgart (Author)
  • Günter E.M. Tovar - , Fraunhofer Institute for Interfacial Engineering and Biotechnology (Author)
  • Felix Krujatz - , Chair of Bioprocess Engineering (Author)
  • Jonathan Mädler - , Process Systems Engineering Group (Author)
  • Leon Urbas - , Chair of Process Control Systems (Author)

Abstract

Accurate prediction of microalgae growth is crucial for understanding the impacts of light dynamics and optimizing production. Although various mathematical models have been proposed, only a few of them have been validated in outdoor cultivation. This study aims to investigate the use of machine learning algorithms in microalgae growth modeling. Outdoor cultivation data of Phaeodactylum tricornutum in flat-panel airlift photobioreactors for 50 days were used to compare the performance of Long Short-Term Memory (LSTM) and Support Vector Regression (SVR) with traditional models, namely Monod and Haldane. The results indicate that the machine learning models outperform the traditional models due to their ability to utilize light history as input. Moreover, the LSTM model shows an excellent ability to describe the light acclimation effect. Last, two potential applications of these models are demonstrated: 1) use as a biomass soft sensor and 2) development of an optimal harvest strategy for outdoor cultivation.

Details

Original languageEnglish
Article number129882
Pages (from-to)1-11
Number of pages11
JournalBioresource Technology
Volume2023
Issue number390
Publication statusE-pub ahead of print - 15 Oct 2023
Peer-reviewedYes

External IDs

Scopus 85175179591
ORCID /0000-0001-5165-4459/work/148145628
ORCID /0000-0001-7012-5966/work/148145988
Mendeley 48733afd-1787-3113-b344-2a4c70fc044f

Keywords

Research priority areas of TU Dresden

Subject groups, research areas, subject areas according to Destatis

Keywords

  • Growth modeling, Light acclimation, Long Short-Term Memory (LSTM), Microalgae, Time series

Library keywords