A1 Journal article (refereed)
Non-invasive monitoring of microalgae cultivations using hyperspectral imager (2024)
Pääkkönen, S., Pölönen, I., Raita-Hakola, A.-M., Carneiro, M., Cardoso, H., Mauricio, D., Rodrigues, A. M. C., & Salmi, P. (2024). Non-invasive monitoring of microalgae cultivations using hyperspectral imager. Journal of Applied Phycology, Early online. https://doi.org/10.1007/s10811-024-03256-4
JYU authors or editors
Publication details
All authors or editors: Pääkkönen, Salli; Pölönen, Ilkka; Raita-Hakola, Anna-Maria; Carneiro, Mariana; Cardoso, Helena; Mauricio, Dinis; Rodrigues, Alexandre Miguel Cavaco; Salmi, Pauliina
Journal or series: Journal of Applied Phycology
ISSN: 0921-8971
eISSN: 1573-5176
Publication year: 2024
Publication date: 09/05/2024
Volume: Early online
Publisher: Springer Nature
Publication country: Netherlands
Publication language: English
DOI: https://doi.org/10.1007/s10811-024-03256-4
Research data link: https://doi.org/10.23729/1e576402-1ccc-4974-a392-e014bd6cec38
Publication open access: Openly available
Publication channel open access: Partially open access channel
Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/94847
Abstract
High expectations are placed on microalgae as a sustainable source of valuable biomolecules. Robust methods to control microalgae cultivation processes are needed to enhance their efficiency and, thereafter, increase the profitability of microalgae-based products. To meet this need, a non-invasive monitoring method based on a hyperspectral imager was developed for laboratory scale and afterwards tested on industrial scale cultivations. In the laboratory experiments, reference data for microalgal biomass concentration was gathered to construct 1) a vegetation index-based linear regression model and 2) a one-dimensional convolutional neural network model to resolve microalgae biomass concentration from the spectral images. The two modelling approaches were compared. The mean absolute percentage error (MAPE) for the index-based model was 15–24%, with the standard deviation (SD) of 13-18 for the diferent species. MAPE for the convolutional neural network was 11–26% (SD = 10–22). Both models predicted the biomass well. The convolutional neural network could also classify the monocultures of green algae by species (accuracy of 97–99%). The index-based model was fast to construct and easy to interpret. The index-based monitoring was also tested in an industrial setup demonstrating a promising ability to retrieve microalgae-biomass-based signals in different cultivation systems.
Keywords: microalgae; biomolecules; monitoring; imaging; hyperspectral imaging; aquaculture; biotechnology; computational science
Free keywords: green microalgae; hyperspectral imaging; non-invasive monitoring; vegetation indices; convolutional neural network; model comparison
Contributing organizations
Related projects
- Robust Algae Systems
- Salmi, Pauliina
- Business Finland
Ministry reporting: Yes
Preliminary JUFO rating: 1
- Computational Science (Faculty of Information Technology IT) LASK
- Computing, Information Technology and Mathematics (Faculty of Information Technology IT) CITM
- Aquatic Sciences (Department of Biological and Environmental Science BIOENV) WET
- School of Resource Wisdom (University of Jyväskylä JYU) JYU.Wisdom