Näytä suppeat kuvailutiedot

dc.contributor.authorSalmi, Pauliina
dc.contributor.authorCalderini, Marco
dc.contributor.authorPääkkönen, Salli
dc.contributor.authorTaipale, Sami
dc.contributor.authorPölönen, Ilkka
dc.date.accessioned2022-04-28T07:57:19Z
dc.date.available2022-04-28T07:57:19Z
dc.date.issued2022
dc.identifier.citationSalmi, P., Calderini, M., Pääkkönen, S., Taipale, S., & Pölönen, I. (2022). Assessment of microalgae species, biomass, and distribution from spectral images using a convolution neural network. <i>Journal of Applied Phycology</i>, <i>34</i>(3), 1565-1575. <a href="https://doi.org/10.1007/s10811-022-02735-w" target="_blank">https://doi.org/10.1007/s10811-022-02735-w</a>
dc.identifier.otherCONVID_117816621
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/80780
dc.description.abstractEffective monitoring of microalgae growth is crucial for environmental observation, while the applications of this monitoring could also be expanded to commercial and research-focused microalgae cultivation. Currently, the distinctive optical properties of different microalgae groups are targeted for monitoring. Since different microalgae can grow together, their spectral signals are mixed with ambient properties, making estimations of species biomasses a challenging task. In this study, we cultured five different microalgae and monitored their growth with a mobile spectral imager in three separate experiments. We trained and validated a one-dimensional convolution neural network by introducing absorbance spectra of the cultured microalgae and simulated pairwise mixtures of them. We then tested the model with samples of microalgae (monocultures and their pairwise mixtures) that were not part of the training or validation data. The convolution neural network classified microalgae accurately in the monocultures (test accuracy = 95%, SD = 4) and in the pairwise mixtures (test accuracy = 100%, SD = 0). Median prediction errors for biomasses were 17% (mean = 22%, SD = 18) for the monocultures and 17% (mean 24%, SD = 28) for the pairwise mixtures. As the spectral camera produced spatial information of the imaged target, we also demonstrated here the spatial distribution of microalgae biomass by applying the model across 5 × 5 pixel areas of the spectral images. The results of this study encourage the application of a one-dimensional convolution neural network to solve classification, regression, and distribution problems related to microalgae observation, simultaneously.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherSpringer Science and Business Media LLC
dc.relation.ispartofseriesJournal of Applied Phycology
dc.rightsCC BY 4.0
dc.subject.othermicroalgae monitoring
dc.subject.otherhyperspectral imaging
dc.subject.othermachine learning
dc.titleAssessment of microalgae species, biomass, and distribution from spectral images using a convolution neural network
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-202204282447
dc.contributor.laitosBio- ja ympäristötieteiden laitosfi
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosDepartment of Biological and Environmental Scienceen
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineLaskennallinen tiedefi
dc.contributor.oppiaineComputing, Information Technology and Mathematicsfi
dc.contributor.oppiaineResurssiviisausyhteisöfi
dc.contributor.oppiaineAkvaattiset tieteetfi
dc.contributor.oppiaineComputational Scienceen
dc.contributor.oppiaineComputing, Information Technology and Mathematicsen
dc.contributor.oppiaineSchool of Resource Wisdomen
dc.contributor.oppiaineAquatic Sciencesen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.type.coarhttp://purl.org/coar/resource_type/c_2df8fbb1
dc.description.reviewstatuspeerReviewed
dc.format.pagerange1565-1575
dc.relation.issn0921-8971
dc.relation.numberinseries3
dc.relation.volume34
dc.type.versionpublishedVersion
dc.rights.copyright© The Author(s) 2022
dc.rights.accesslevelopenAccessfi
dc.relation.grantnumber321780
dc.subject.ysohyperspektrikuvantaminen
dc.subject.ysoneuroverkot
dc.subject.ysomikrolevät
dc.subject.ysobiomassa (ekologia)
dc.subject.ysoviljely
dc.subject.ysooptiset ominaisuudet
dc.subject.ysokoneoppiminen
dc.subject.ysoympäristötutkimus
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p39290
jyx.subject.urihttp://www.yso.fi/onto/yso/p7292
jyx.subject.urihttp://www.yso.fi/onto/yso/p26977
jyx.subject.urihttp://www.yso.fi/onto/yso/p39245
jyx.subject.urihttp://www.yso.fi/onto/yso/p5098
jyx.subject.urihttp://www.yso.fi/onto/yso/p25870
jyx.subject.urihttp://www.yso.fi/onto/yso/p21846
jyx.subject.urihttp://www.yso.fi/onto/yso/p10900
dc.rights.urlhttps://creativecommons.org/licenses/by/4.0/
dc.relation.datasethttps://doi.org/10.5281/zenodo.5061719
dc.relation.doi10.1007/s10811-022-02735-w
dc.relation.funderResearch Council of Finlanden
dc.relation.funderSuomen Akatemiafi
jyx.fundingprogramPostdoctoral Researcher, AoFen
jyx.fundingprogramTutkijatohtori, SAfi
jyx.fundinginformationOpen Access funding provided by University of Jyväskylä (JYU). This research was funded by the Academy of Finland, grant number 321780 for Pauliina Salmi.
datacite.isSupplementedBy.doi10.17011/jyx/dataset/78519
datacite.isSupplementedBySalmi, Pauliina; Calderini, Marco; Taipale, Sami; Pölönen, Ilkka; Pääkkönen, Salli. (2021). <i>Assessment of microalgae species, biomass and distribution from spectral images using a convolution neural network</i>. V. 2.9.2021. University of Jyväskylä. <a href="https://doi.org/10.17011/jyx/dataset/78519" target="_blank">https://doi.org/10.17011/jyx/dataset/78519</a>. <a href="http://urn.fi/URN:NBN:fi:jyu-202111085543">https://urn.fi/URN:NBN:fi:jyu-202111085543</a>
dc.type.okmA1


Aineistoon kuuluvat tiedostot

Thumbnail

Aineisto kuuluu seuraaviin kokoelmiin

Näytä suppeat kuvailutiedot

CC BY 4.0
Ellei muuten mainita, aineiston lisenssi on CC BY 4.0