Resolving phytoplankton pigments from spectral images using convolutional neural networks

Salmi, Pauliina; Pölönen, Ilkka; Beckmann, Daniel Atton; Calderini, Marco L.; May, Linda ORCID: https://orcid.org/0000-0003-3385-9973; Olszewska, Justyna ORCID: https://orcid.org/0000-0002-4910-2206; Perozzi, Laura; Pääkkönen, Salli; Taipale, Sami; Hunter, Peter. 2024 Resolving phytoplankton pigments from spectral images using convolutional neural networks. Limnology and Oceanography: Methods, 22 (1). 1-13. https://doi.org/10.1002/lom3.10588

Before downloading, please read NORA policies.

Preview

Text N536375JA.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (2MB) | Preview

Abstract/Summary

Motivated by the need for rapid and robust monitoring of phytoplankton in inland waters, this article introduces a protocol based on a mobile spectral imager for assessing phytoplankton pigments from water samples. The protocol includes (1) sample concentrating; (2) spectral imaging; and (3) convolutional neural networks (CNNs) to resolve concentrations of chlorophyll a (Chl a), carotenoids, and phycocyanin. The protocol was demonstrated with samples from 20 lakes across Scotland, with special emphasis on Loch Leven where blooms of cyanobacteria are frequent. In parallel, samples were prepared for reference observations of Chl a and carotenoids by high-performance liquid chromatography and of phycocyanin by spectrophotometry. Robustness of the CNNs were investigated by excluding each lake from model trainings one at a time and using the excluded data as independent test data. For Loch Leven, median absolute percentage difference (MAPD) was 15% for Chl a and 36% for carotenoids. MAPD in estimated phycocyanin concentration was high (102%); however, the system was able to indicate the possibility of a cyanobacteria bloom. In the leave-one-out tests with the other lakes, MAPD was 26% for Chl a, 27% for carotenoids, and 75% for phycocyanin. The higher error for phycocyanin was likely due to variation in the data distribution and reference observations. It was concluded that this protocol could support phytoplankton monitoring by using Chl a and carotenoids as proxies for biomass. Greater focus on the distribution and volume of the training data would improve the phycocyanin estimates.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	https://doi.org/10.1002/lom3.10588
UKCEH and CEH Sections/Science Areas:	Water Resources (Science Area 2017-)
ISSN:	1541-5856
Additional Information. Not used in RCUK Gateway to Research.:	Open Access paper - full text available via Official URL link.
NORA Subject Terms:	Electronics, Engineering and Technology Hydrology
Related URLs:	Dataset Other Other
Date made live:	01 Dec 2023 12:24 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/536375

Actions (login required)

View Item

Document Downloads

More statistics for this item...