Semi-supervised anomaly detection from Chlorella vulgaris cultivations using hyperspectral imaging
More evolved anomaly detection methods are needed to ensure efficient quality control of microalgae cultivations. This study aimed to determine whether non-invasively collected hyperspectral data can be used to indicate anomalies in Chlorella vulgaris cultivations. Three models of varying computatio...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525003545 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850120586526720000 |
|---|---|
| author | Salli Pääkkönen Ilkka Pölönen Pauliina Salmi |
| author_facet | Salli Pääkkönen Ilkka Pölönen Pauliina Salmi |
| author_sort | Salli Pääkkönen |
| collection | DOAJ |
| description | More evolved anomaly detection methods are needed to ensure efficient quality control of microalgae cultivations. This study aimed to determine whether non-invasively collected hyperspectral data can be used to indicate anomalies in Chlorella vulgaris cultivations. Three models of varying computational complexities were tested: isolation forest (iForest), one-class support vector machine (OC SVM), and neural network autoencoder. The models were trained in a semi-supervised way using 280 non-anomalous Chlorella spectra. test data included artificially contaminated cultures with Microcystis aeruginosa (4 spectra), nitrogen-depleted cultures (24 spectra) and non-anomalous Chlorella cultivations (43 spectra). The OC SVM was the most sensitive in detecting anomalies (AUC = 0.87 [0.79, 0.95], F1 = 0.91 CI [0.85, 0.98]), although the 95 % confidence intervals (CI) overlapped with the metrics of the other models. The model detected artificial contamination when the amount of Microcystis was around 1 % (biomass/ biomass) in the cultivation and nitrogen depletion after 3 days of nitrogen-free cultivation. The advantage of the semi-supervised training was that the models were able to learn about the normal Chlorella cultivations used as training data, and thus to classify unknown anomalies that deviated from the learned features. This may prove useful for detecting wider range of anomalies, but further testing is required to assess whether the other potential contaminants affect the spectra imaged in such a way that they differ from the normal. Non-invasive hyperspectral imaging together with the semi-supervised models provides a rapid indication method that could potentially give microalgae producers up-to-date information on cultivation quality. |
| format | Article |
| id | doaj-art-28b4c2b8ba004ed4a2816bd2ce99e890 |
| institution | OA Journals |
| issn | 2772-3755 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-28b4c2b8ba004ed4a2816bd2ce99e8902025-08-20T02:35:19ZengElsevierSmart Agricultural Technology2772-37552025-12-011210112110.1016/j.atech.2025.101121Semi-supervised anomaly detection from Chlorella vulgaris cultivations using hyperspectral imagingSalli Pääkkönen0Ilkka Pölönen1Pauliina Salmi2Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland; Corresponding author at: P.O. Box 35, Mattilanniemi 2, FI-40014, University of Jyväskylä, Jyväskylä, Finland.Faculty of Information Technology, University of Jyväskylä, Jyväskylä, FinlandDepartment of Biology, Norwegian University of Science and Technology, Trondheim, NorwayMore evolved anomaly detection methods are needed to ensure efficient quality control of microalgae cultivations. This study aimed to determine whether non-invasively collected hyperspectral data can be used to indicate anomalies in Chlorella vulgaris cultivations. Three models of varying computational complexities were tested: isolation forest (iForest), one-class support vector machine (OC SVM), and neural network autoencoder. The models were trained in a semi-supervised way using 280 non-anomalous Chlorella spectra. test data included artificially contaminated cultures with Microcystis aeruginosa (4 spectra), nitrogen-depleted cultures (24 spectra) and non-anomalous Chlorella cultivations (43 spectra). The OC SVM was the most sensitive in detecting anomalies (AUC = 0.87 [0.79, 0.95], F1 = 0.91 CI [0.85, 0.98]), although the 95 % confidence intervals (CI) overlapped with the metrics of the other models. The model detected artificial contamination when the amount of Microcystis was around 1 % (biomass/ biomass) in the cultivation and nitrogen depletion after 3 days of nitrogen-free cultivation. The advantage of the semi-supervised training was that the models were able to learn about the normal Chlorella cultivations used as training data, and thus to classify unknown anomalies that deviated from the learned features. This may prove useful for detecting wider range of anomalies, but further testing is required to assess whether the other potential contaminants affect the spectra imaged in such a way that they differ from the normal. Non-invasive hyperspectral imaging together with the semi-supervised models provides a rapid indication method that could potentially give microalgae producers up-to-date information on cultivation quality.http://www.sciencedirect.com/science/article/pii/S2772375525003545Microalgaecontaminationmicrocystis aeruginosamachine learningmodel comparison |
| spellingShingle | Salli Pääkkönen Ilkka Pölönen Pauliina Salmi Semi-supervised anomaly detection from Chlorella vulgaris cultivations using hyperspectral imaging Smart Agricultural Technology Microalgae contamination microcystis aeruginosa machine learning model comparison |
| title | Semi-supervised anomaly detection from Chlorella vulgaris cultivations using hyperspectral imaging |
| title_full | Semi-supervised anomaly detection from Chlorella vulgaris cultivations using hyperspectral imaging |
| title_fullStr | Semi-supervised anomaly detection from Chlorella vulgaris cultivations using hyperspectral imaging |
| title_full_unstemmed | Semi-supervised anomaly detection from Chlorella vulgaris cultivations using hyperspectral imaging |
| title_short | Semi-supervised anomaly detection from Chlorella vulgaris cultivations using hyperspectral imaging |
| title_sort | semi supervised anomaly detection from chlorella vulgaris cultivations using hyperspectral imaging |
| topic | Microalgae contamination microcystis aeruginosa machine learning model comparison |
| url | http://www.sciencedirect.com/science/article/pii/S2772375525003545 |
| work_keys_str_mv | AT sallipaakkonen semisupervisedanomalydetectionfromchlorellavulgariscultivationsusinghyperspectralimaging AT ilkkapolonen semisupervisedanomalydetectionfromchlorellavulgariscultivationsusinghyperspectralimaging AT pauliinasalmi semisupervisedanomalydetectionfromchlorellavulgariscultivationsusinghyperspectralimaging |