Towards operational phytoplankton recognition with automated high-throughput imaging, near-real-time data processing, and convolutional neural networks
Plankton communities form the basis of aquatic ecosystems and elucidating their role in increasingly important environmental issues is a persistent research question. Recent technological advances in automated microscopic imaging, together with cloud platforms for high-performance computing, have cr...
Uložené v:
| Vydané v: | Frontiers in Marine Science Ročník 9 |
|---|---|
| Hlavní autori: | , , , , , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Frontiers Media S.A
02.09.2022
|
| Predmet: | |
| ISSN: | 2296-7745, 2296-7745 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Plankton communities form the basis of aquatic ecosystems and elucidating their role in increasingly important environmental issues is a persistent research question. Recent technological advances in automated microscopic imaging, together with cloud platforms for high-performance computing, have created possibilities for collecting and processing detailed high-frequency data on planktonic communities, opening new horizons for testing core hypotheses in aquatic ecosystems. Analyzing continuous streams of big data calls for development and deployment of novel computer vision and machine learning systems. The implementation of these analysis systems is not always straightforward with regards to operationality, and issues regarding data flows, computing and data treatment need to be considered. We created a data pipeline for automated near-real-time classification of phytoplankton during remote deployment of imaging flow cytometer (Imaging FlowCytobot, IFCB). Convolutional neural network (CNN) is used to classify continuous imaging data with probability thresholds used to filter out images not belonging to our existing classes. The automated data flow and classification system were used to monitor dominating species of filamentous cyanobacteria on the coast of Finland during summer 2021. We demonstrate that good phytoplankton recognition can be achieved with transfer learning utilizing a relatively shallow, publicly available, pre-trained CNN model and fine-tuning it with community-specific phytoplankton images (overall F1-score of 0.95 for test set of our labeled image data complemented with a 50% unclassifiable image portion). This enables both fast training and low computing resource requirements for model deployment making it easy to modify and applicable in wide range of situations. The system performed well when used to classify a natural phytoplankton community over different seasons (overall F1-score 0.82 for our evaluation data set). Furthermore, we address the key challenges of image classification for varying planktonic communities and analyze the practical implications of confused classes. We published our labeled image data set of Baltic Sea phytoplankton community for the training of image recognition models (~63000 images in 50 classes) to accelerate implementation of imaging systems for other brackish and freshwater communities. Our evaluation data set, 59 fully annotated samples of natural communities throughout an annual cycle, is also available for model testing purposes (~150000 images). |
|---|---|
| AbstractList | Plankton communities form the basis of aquatic ecosystems and elucidating their role in increasingly important environmental issues is a persistent research question. Recent technological advances in automated microscopic imaging, together with cloud platforms for high-performance computing, have created possibilities for collecting and processing detailed high-frequency data on planktonic communities, opening new horizons for testing core hypotheses in aquatic ecosystems. Analyzing continuous streams of big data calls for development and deployment of novel computer vision and machine learning systems. The implementation of these analysis systems is not always straightforward with regards to operationality, and issues regarding data flows, computing and data treatment need to be considered. We created a data pipeline for automated near-real-time classification of phytoplankton during remote deployment of imaging flow cytometer (Imaging FlowCytobot, IFCB). Convolutional neural network (CNN) is used to classify continuous imaging data with probability thresholds used to filter out images not belonging to our existing classes. The automated data flow and classification system were used to monitor dominating species of filamentous cyanobacteria on the coast of Finland during summer 2021. We demonstrate that good phytoplankton recognition can be achieved with transfer learning utilizing a relatively shallow, publicly available, pre-trained CNN model and fine-tuning it with community-specific phytoplankton images (overall F1-score of 0.95 for test set of our labeled image data complemented with a 50% unclassifiable image portion). This enables both fast training and low computing resource requirements for model deployment making it easy to modify and applicable in wide range of situations. The system performed well when used to classify a natural phytoplankton community over different seasons (overall F1-score 0.82 for our evaluation data set). Furthermore, we address the key challenges of image classification for varying planktonic communities and analyze the practical implications of confused classes. We published our labeled image data set of Baltic Sea phytoplankton community for the training of image recognition models (~63000 images in 50 classes) to accelerate implementation of imaging systems for other brackish and freshwater communities. Our evaluation data set, 59 fully annotated samples of natural communities throughout an annual cycle, is also available for model testing purposes (~150000 images). |
| Author | Ylöstalo, Pasi Kälviäinen, Heikki Johansson, Milla Eerola, Tuomas Suikkanen, Sanna Haario, Heikki Velhonoja, Otso Lensu, Lasse Seppälä, Jukka Kielosto, Sami Kraft, Kaisa Tamminen, Timo Haraguchi, Lumi |
| Author_xml | – sequence: 1 givenname: Kaisa surname: Kraft fullname: Kraft, Kaisa – sequence: 2 givenname: Otso surname: Velhonoja fullname: Velhonoja, Otso – sequence: 3 givenname: Tuomas surname: Eerola fullname: Eerola, Tuomas – sequence: 4 givenname: Sanna surname: Suikkanen fullname: Suikkanen, Sanna – sequence: 5 givenname: Timo surname: Tamminen fullname: Tamminen, Timo – sequence: 6 givenname: Lumi surname: Haraguchi fullname: Haraguchi, Lumi – sequence: 7 givenname: Pasi surname: Ylöstalo fullname: Ylöstalo, Pasi – sequence: 8 givenname: Sami surname: Kielosto fullname: Kielosto, Sami – sequence: 9 givenname: Milla surname: Johansson fullname: Johansson, Milla – sequence: 10 givenname: Lasse surname: Lensu fullname: Lensu, Lasse – sequence: 11 givenname: Heikki surname: Kälviäinen fullname: Kälviäinen, Heikki – sequence: 12 givenname: Heikki surname: Haario fullname: Haario, Heikki – sequence: 13 givenname: Jukka surname: Seppälä fullname: Seppälä, Jukka |
| BookMark | eNp1Uctq3TAUFCWFpmk-oDt9QH0rW9bDyxL6CAS6SdfiWDq2lfhKRpJ7yZf0dxv7plAKXc3hDDPnMW_JRYgBCXlfswPnuvs4HCHlQ8Oa5qClkp14RS6bppOVUq24-Kt-Q65zfmCM1bxlou0uya_7eILkMo0LJig-BpjpMj2VuMwQHksMNKGNY_AbR0--TBTWEo9Q0NHJj1NVphTXcVrWQv0RRh_GDzQgpCohzFXxR6QOCtAlRYs57zwER20MP-O8vswMuKYdyimmx_yOvB5gznj9glfkx5fP9zffqrvvX29vPt1Vlou2VAprJ3ura22FcjUOHJBrxfvaQq8agAGha1wnkTlumVVCcuV6qzaCuY5fkduzr4vwYJb0fEF6MhG82RsxjQZS8XZGw7XmqKETDGXbsq4Xom00t3KQ1kG7eamzl00x54SDsb7sPy0J_GxqZra4zB6X2eIy57ielfU_yj-b_F_zG9Paofk |
| CitedBy_id | crossref_primary_10_1002_lom3_10659 crossref_primary_10_1016_j_ecoinf_2025_103272 crossref_primary_10_1016_j_ecoinf_2025_103372 crossref_primary_10_3897_aca_8_e151406 crossref_primary_10_1111_2041_210X_14281 crossref_primary_10_1088_2632_2153_ace417 crossref_primary_10_1002_lom3_10723 crossref_primary_10_1007_s00138_023_01450_x crossref_primary_10_5194_bg_21_4341_2024 crossref_primary_10_5194_essd_16_2971_2024 crossref_primary_10_1021_acs_est_5c06078 crossref_primary_10_3389_fmars_2022_1032287 crossref_primary_10_1002_lom3_10588 crossref_primary_10_3389_fmars_2023_1280510 crossref_primary_10_1002_lom3_10572 crossref_primary_10_1002_lol2_10438 crossref_primary_10_1016_j_hal_2025_102865 crossref_primary_10_1007_s10661_024_12861_2 crossref_primary_10_1016_j_scitotenv_2025_180245 crossref_primary_10_5194_acp_24_4717_2024 crossref_primary_10_1007_s10750_025_05802_8 crossref_primary_10_3389_fmars_2024_1513463 crossref_primary_10_1007_s10462_024_10745_y crossref_primary_10_1016_j_ocecoaman_2025_107542 |
| Cites_doi | 10.1016/j.aci.2019.11.004 10.1016/S0422-9894(03)80083-1 10.1038/sdata.2016.18 10.5194/bg-11-3619-2014 10.1016/j.hal.2019.101739 10.5194/os-14-617-2018 10.1146/annurev-marine-041921-013023 10.1086/703657 10.1109/IEEECONF38699.2020.9388998 10.1016/j.jmarsys.2014.10.001 10.4319/lom.2007.5.204 10.1007/BF00994018 10.3389/fmars.2018.00211 10.1007/s11356-021-12471-2 10.1016/j.dsr2.2014.03.012 10.1023/A:1010933404324 10.1111/j.1529-8817.2009.00791.x 10.3390/app7080753 10.1017/CBO9780511542145 10.1016/j.pocean.2019.02.001 10.1186/s12898-018-0209-5 10.1109/ACCESS.2020.3022242 10.4319/lom.2007.5.195 10.1126/sciadv.aau6253 10.4319/lom.2012.10.278 10.1038/nmicrobiol.2017.58 10.3389/fmars.2021.594144 10.1109/IJCNN.2010.5596486 10.3354/ame01842 10.1002/lom3.10151 10.1016/j.patcog.2011.06.019 10.1016/j.ecoinf.2019.02.007 10.1111/gcb.14108 10.1016/j.csr.2003.06.001 10.3389/fmars.2019.00529 10.1093/plankt/fbu070 10.1002/lom3.10402 10.3389/fmars.2019.00196 10.1007/978-3-030-68780-9_11 10.1002/lno.11443 10.1016/j.mio.2016.04.003 10.1016/j.hal.2019.101685 10.1007/s11356-012-1437-4 10.1186/s40537-019-0192-5 10.1038/nature14539 10.1007/978-3-319-54526-4_8 10.5121/ijdkp.2015.5201 10.1002/lom3.10285 10.1002/lno.10117 10.5194/os-17-1657-2021 |
| ContentType | Journal Article |
| DBID | AAYXX CITATION DOA |
| DOI | 10.3389/fmars.2022.867695 |
| DatabaseName | CrossRef DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Oceanography |
| EISSN | 2296-7745 |
| ExternalDocumentID | oai_doaj_org_article_3883e8a950e64409b554283c6f6cda49 10_3389_fmars_2022_867695 |
| GroupedDBID | 5VS 88I 8FE 8FH 9T4 AAFWJ AAYXX ABUWG ACGFS ADBBV AEUYN AFFHD AFKRA AFPKN ALMA_UNASSIGNED_HOLDINGS AZQEC BBNVY BCNDV BENPR BHPHI BKSAR BPHCQ CCPQU CITATION DWQXO FRP GNUQQ GROUPED_DOAJ HCIFZ KQ8 LK8 M2P M7P M~E OK1 PCBAR PHGZM PHGZT PIMPY PQGLB PQQKQ PROAC |
| ID | FETCH-LOGICAL-c354t-7e1d6bc818c57d1ef3ae3873b1cab72aafea92d96e0d3c0c75637dbc7afea0d93 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 28 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000855100200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2296-7745 |
| IngestDate | Fri Oct 03 12:43:55 EDT 2025 Tue Nov 18 22:38:17 EST 2025 Sat Nov 29 04:07:40 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c354t-7e1d6bc818c57d1ef3ae3873b1cab72aafea92d96e0d3c0c75637dbc7afea0d93 |
| OpenAccessLink | https://doaj.org/article/3883e8a950e64409b554283c6f6cda49 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_3883e8a950e64409b554283c6f6cda49 crossref_citationtrail_10_3389_fmars_2022_867695 crossref_primary_10_3389_fmars_2022_867695 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-09-02 |
| PublicationDateYYYYMMDD | 2022-09-02 |
| PublicationDate_xml | – month: 09 year: 2022 text: 2022-09-02 day: 02 |
| PublicationDecade | 2020 |
| PublicationTitle | Frontiers in Marine Science |
| PublicationYear | 2022 |
| Publisher | Frontiers Media S.A |
| Publisher_xml | – name: Frontiers Media S.A |
| References | Reynolds (B57) 2006 B22 Bueno (B4) 2017; 7 Lumini (B41) 2019; 51 Ruokanen (B59) 2003; 69 He (B24) 2016 Luo (B43) 2018; 16 Kaitala (B32) 2014; 140 (B66) 2021 Guo (B18) 2021 Olli (B49) 2019; 194 Lombard (B40) 2019; 6 Irisson (B28) 2022; 14 Henrichs (B23) 2021; 28 Moreno-Torres (B46) 2012; 45 Farcy (B15) 2019; 6 Kraft (B36) 2021; 8 Hossin (B26) 2015; 5 Campbell (B7) 2013; 20 B35 Righetti (B58) 2019; 5 Picheral (B54) 2017 Anglès (B1) 2015; 60 Bureš (B5) 2021 Campbell (B6) 2010; 46 Lumini (B42) 2020 Muller-Karger (B47) 2018; 5 Walker (B64) 2021 LeCun (B39) 2015; 521 Harred (B21) 2014; 36 Kahru (B31) 2020; 92 Breiman (B3) 2001; 45 González (B17) 2017; 15 Fischer (B16) 2020; 65 Kingma (B34) 2014 B8 Johnson (B29) 2019; 6 Teigen (B62) 2020 Honkanen (B25) 2021; 17 Deng (B12) 2009 Dunker (B13) 2018; 18 Miloslavich (B44) 2018; 24 Anglès (B2) 2019; 173 Laakso (B37) 2018; 14 Stal (B61) 2003; 23 Olson (B51) 2007; 5 Faillettaz (B14) 2016; 15 Cortes (B10) 1995; 20 Sosik (B60) 2007; 5 Correa (B9) 2017 Hutchins (B27) 2017; 2 Pu (B55) 2021 Moberg (B45) 2012; 10 Niemistö (B48) 1989; 17 Recht (B56) 2019 Haraguchi (B20) 2017; 80 Kahru (B30) 2014; 11 Orenstein (B52) 2017 Kerr (B33) 2020; 8 Olofsson (B50) 2020; 91 Dai (B11) 2017 Laney (B38) 2014; 105 Thai-Nghe (B63) 2010 Wilkinson (B65) 2016; 3 Paszke (B53) 2019 Hällfors (B19) 2004; 95 |
| References_xml | – year: 2020 ident: B42 article-title: Deep learning for plankton and coral classification publication-title: Appl. Comput. Inform. doi: 10.1016/j.aci.2019.11.004 – ident: B35 – volume: 69 start-page: 519 year: 2003 ident: B59 article-title: Alg@line–joint operational unattended phytoplankton monitoring in the Baltic Sea publication-title: Elsevier Oceanogr. Ser. doi: 10.1016/S0422-9894(03)80083-1 – volume: 3 start-page: 1 year: 2016 ident: B65 article-title: Comment: the FAIR guiding principles for scientific data management and stewardship publication-title: Sci. Data doi: 10.1038/sdata.2016.18 – volume: 11 start-page: 3619 year: 2014 ident: B30 article-title: Multidecadal time series of satellite-detected accumulations of cyanobacteria in the Baltic Sea publication-title: Biogeosciences doi: 10.5194/bg-11-3619-2014 – volume: 92 year: 2020 ident: B31 article-title: Cyanobacterial blooms in the Baltic Sea: Correlations with environmental factors publication-title: Harmful Algae doi: 10.1016/j.hal.2019.101739 – volume: 14 start-page: 617 year: 2018 ident: B37 article-title: 100 years of atmospheric and marine observations at the Finnish utö island in the Baltic Sea publication-title: Ocean Sci. doi: 10.5194/os-14-617-2018 – volume: 14 start-page: 277 year: 2022 ident: B28 article-title: Machine learning for the study of plankton and marine snow from images publication-title: Ann. Rev. Mar. Sci. doi: 10.1146/annurev-marine-041921-013023 – volume: 194 year: 2019 ident: B49 article-title: Phytoplankton species richness along coastal and estuarine salinity continua publication-title: Am. Nat. doi: 10.1086/703657 – start-page: 1 year: 2020 ident: B62 article-title: Leveraging similarity metrics to in-situ discover planktonic interspecies variations or mutations publication-title: Global Oceans 2020: Singapore–US. Gulf Coast, 2020 doi: 10.1109/IEEECONF38699.2020.9388998 – start-page: 20 year: 2017 ident: B9 article-title: Deep learning for microalgae classification – volume: 140 start-page: 1 year: 2014 ident: B32 article-title: Introduction to special issue: 5th ferrybox workshop–celebrating 20 years of the alg@ line publication-title: J. Mar. Syst. doi: 10.1016/j.jmarsys.2014.10.001 – volume: 5 start-page: 204 year: 2007 ident: B60 article-title: Automated taxonomic classification of phytoplankton sampled with imaging-in-flow cytometry publication-title: Limnol. Oceanogr. Methods doi: 10.4319/lom.2007.5.204 – start-page: 248 year: 2009 ident: B12 article-title: Imagenet: A large-scale hierarchical image database – start-page: 770 year: 2016 ident: B24 article-title: Deep residual learning for image recognition – volume: 20 start-page: 273 year: 1995 ident: B10 article-title: Support-vector networks publication-title: Mach. Learn. doi: 10.1007/BF00994018 – volume: 5 year: 2018 ident: B47 article-title: Advancing marine biological observations and data requirements of the complementary essential ocean variables (EOVs) and essential biodiversity variables (EBVs) frameworks publication-title: Front. Mar. Sci. doi: 10.3389/fmars.2018.00211 – volume: 28 start-page: 28544 year: 2021 ident: B23 article-title: Application of a convolutional neural network to improve automated early warning of harmful algal blooms publication-title: Environ. Sci. pollut. Res. doi: 10.1007/s11356-021-12471-2 – volume: 105 start-page: 30 year: 2014 ident: B38 article-title: Phytoplankton assemblage structure in and around a massive under-ice bloom in the chukchi Sea publication-title: Deep-Sea Res. II doi: 10.1016/j.dsr2.2014.03.012 – volume: 45 start-page: 5 year: 2001 ident: B3 article-title: Random forests publication-title: Mach. Learn. doi: 10.1023/A:1010933404324 – volume: 46 year: 2010 ident: B6 article-title: First harmful Dinophysis (Dinophyceae, Dinophysiales) bloom in the US revealed by automated imaging flow cytometry publication-title: J. Phycol. doi: 10.1111/j.1529-8817.2009.00791.x – volume: 7 year: 2017 ident: B4 article-title: Automated diatom classification (Part a): Handcrafted feature approaches publication-title: Appl. Sci. doi: 10.3390/app7080753 – start-page: 1082 year: 2017 ident: B52 article-title: Transfer learning and deep feature extraction for planktonic image data sets – year: 2017 ident: B54 article-title: EcoTaxa, a tool for the taxonomic classification of images – volume-title: The ecology of phytoplankton year: 2006 ident: B57 doi: 10.1017/CBO9780511542145 – year: 2014 ident: B34 article-title: Adam: A method for stochastic optimization publication-title: arXiv – volume: 173 start-page: 26 year: 2019 ident: B2 article-title: Influence of coastal upwelling and river discharge on the phytoplankton community composition in the northwestern gulf of Mexico publication-title: Progr. Oceanogr. doi: 10.1016/j.pocean.2019.02.001 – volume: 18 start-page: 51 year: 2018 ident: B13 article-title: Combining high-throughput imaging flow cytometry and deep learning for efficient species and life-cycle stage identification of phytoplankton publication-title: BMC Ecol. doi: 10.1186/s12898-018-0209-5 – volume: 8 start-page: 170013 year: 2020 ident: B33 article-title: Collaborative deep learning models to handle class imbalance in FlowCam plankton imagery publication-title: IEEE Access doi: 10.1109/ACCESS.2020.3022242 – volume: 5 start-page: 195 year: 2007 ident: B51 article-title: A submersible imaging-in-flow instrument to analyze nano-and microplankton: Imaging FlowCytobot. Limnol. oceanogr publication-title: Methods doi: 10.4319/lom.2007.5.195 – start-page: 5389 year: 2019 ident: B56 article-title: Do ImageNet classifiers generalize to ImageNet – volume: 5 year: 2019 ident: B58 article-title: Global pattern of phytoplankton diversity driven by temperature and environmental variability publication-title: Sci. Adv. doi: 10.1126/sciadv.aau6253 – volume: 10 start-page: 278 year: 2012 ident: B45 article-title: Distance maps to estimate cell volume from two-dimensional plankton images. Limnol. oceanogr publication-title: Methods doi: 10.4319/lom.2012.10.278 – volume: 2 start-page: 17058 year: 2017 ident: B27 article-title: Microorganisms and ocean global change publication-title: Nat. Microbiol. doi: 10.1038/nmicrobiol.2017.58 – volume: 8 year: 2021 ident: B36 article-title: First application of IFCB high-frequency imaging-in-flow cytometry to investigate bloom-forming filamentous cyanobacteria in the Baltic Sea publication-title: Front. Mar. Sci. doi: 10.3389/fmars.2021.594144 – year: 2010 ident: B63 article-title: Cost-sensitive learning methods for imbalanced data doi: 10.1109/IJCNN.2010.5596486 – volume: 80 start-page: 77 year: 2017 ident: B20 article-title: Monitoring natural phytoplankton communities: A comparison between traditional methods and pulse-shape recording flow cytometry publication-title: Aquat. Microb. Ecol. doi: 10.3354/ame01842 – volume: 15 start-page: 221 year: 2017 ident: B17 article-title: Validation methods for plankton image classification systems publication-title: Limnol. Oceanogr. Methods doi: 10.1002/lom3.10151 – volume: 45 start-page: 521 year: 2012 ident: B46 article-title: A unifying view on dataset shift in classification publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2011.06.019 – volume: 51 start-page: 33 year: 2019 ident: B41 article-title: Deep learning and transfer learning features for plankton classification publication-title: Ecol. Inform. doi: 10.1016/j.ecoinf.2019.02.007 – start-page: 8024 year: 2019 ident: B53 article-title: Pytorch: An imperative style, high-performance deep learning library – start-page: 3672 year: 2021 ident: B64 article-title: Improving rare-class recognition of marine plankton with hard negative mining – volume: 95 start-page: 210 year: 2004 ident: B19 article-title: Checklist of Baltic Sea phytoplankton species (including some heterotrophic protistan groups) publication-title: Baltic Sea Environ. Proc. – volume: 17 start-page: 3 year: 1989 ident: B48 article-title: Blue-green algae and their nitrogen fixation in the Baltic Sea in 1980, 1982 and 1984 publication-title: Meri – volume: 24 start-page: 2416 year: 2018 ident: B44 article-title: Essential ocean variables for global sustained observations of biodiversity and ecosystem changes publication-title: Glob. Change Biol. doi: 10.1111/gcb.14108 – volume: 23 start-page: 1695 year: 2003 ident: B61 article-title: BASIC: Baltic Sea cyanobacteria. an investigation of the structure and dynamics of water blooms of cyanobacteria in the Baltic Sea–responses to a changing environment publication-title: Cont. Shelf Res. doi: 10.1016/j.csr.2003.06.001 – volume: 6 year: 2019 ident: B15 article-title: Towards a European coastal observing network to provide better answer to science and to societal challenges; the JERICO/JERICO-NEXT research infrastructure publication-title: Front. Mar. Sci. doi: 10.3389/fmars.2019.00529 – volume: 36 start-page: 1434 year: 2014 ident: B21 article-title: Predicting harmful algal blooms: A case study with Dinophysis ovum in the gulf of Mexico publication-title: J. Plankton Res. doi: 10.1093/plankt/fbu070 – start-page: 3654 year: 2021 ident: B55 article-title: Anomaly detection for In situ marine plankton images – start-page: 21 year: 2021 ident: B18 article-title: Automated plankton classification from holographic imagery with deep convolutional neural networks. Limnol. oceanogr publication-title: Methods 19 doi: 10.1002/lom3.10402 – volume: 6 year: 2019 ident: B40 article-title: Globally consistent quantitative observations of planktonic ecosystems publication-title: Front. Mar. Sci. doi: 10.3389/fmars.2019.00196 – year: 2021 ident: B5 article-title: “Plankton recognition in images with varying size” in Proceedings of the international conference on pattern recognition (ICPR) publication-title: Workshops Challenges doi: 10.1007/978-3-030-68780-9_11 – ident: B8 – volume: 65 start-page: 2125 year: 2020 ident: B16 article-title: Return of the “age of dinoflagellates” in Monterey bay: Drivers of dinoflagellate dominance examined using automated imaging flow cytometry and long-term time series analysis publication-title: Limnol. Oceanogr. doi: 10.1002/lno.11443 – volume: 15 start-page: 60 year: 2016 ident: B14 article-title: Imperfect automatic image classification successfully describes plankton distribution patterns publication-title: Methods Oceanogr. doi: 10.1016/j.mio.2016.04.003 – year: 2021 ident: B66 article-title: World register of marine species – volume: 91 year: 2020 ident: B50 article-title: Basin-specific changes in filamentous cyanobacteria community composition across four decades in the Baltic Sea publication-title: Harmful Algae doi: 10.1016/j.hal.2019.101685 – volume: 20 start-page: 6896 year: 2013 ident: B7 article-title: Continuous automated imaging-in-flow cytometry for detection and early warning of Karenia brevis blooms in the Gulf of Mexico publication-title: Environ. Sci. Pollut. Res. doi: 10.1007/s11356-012-1437-4 – volume: 6 start-page: 1 year: 2019 ident: B29 article-title: Survey on deep learning with class imbalance publication-title: J. Big Data doi: 10.1186/s40537-019-0192-5 – volume: 521 start-page: 436 year: 2015 ident: B39 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume-title: Computer Vision – ACCV 2016 Workshops. ACCV 2016. Lecture Notes in Computer Science() year: 2017 ident: B11 article-title: A hybrid convolutional neural network for plankton classification doi: 10.1007/978-3-319-54526-4_8 – ident: B22 – volume: 5 year: 2015 ident: B26 article-title: A review on evaluation metrics for data classification evaluations publication-title: Int. J. Data Min. knowledge Manage. process (IJDKP). doi: 10.5121/ijdkp.2015.5201 – volume: 16 start-page: 814 year: 2018 ident: B43 article-title: Automated plankton image analysis using convolutional neural networks publication-title: Limnol. Oceanogr. Methods doi: 10.1002/lom3.10285 – volume: 60 start-page: 1562 year: 2015 ident: B1 article-title: Responses of the coastal phytoplankton community to tropical cyclones revealed by high-frequency imaging flow cytometry publication-title: Limnol. Oceanogr. doi: 10.1002/lno.10117 – volume: 17 start-page: 1657 year: 2021 ident: B25 article-title: The diurnal cycle of pCO 2 in the coastal region of the Baltic Sea publication-title: Ocean Sci. doi: 10.5194/os-17-1657-2021 |
| SSID | ssj0001340549 |
| Score | 2.3965197 |
| Snippet | Plankton communities form the basis of aquatic ecosystems and elucidating their role in increasingly important environmental issues is a persistent research... |
| SourceID | doaj crossref |
| SourceType | Open Website Enrichment Source Index Database |
| SubjectTerms | automated data processing convolutional neural network IFCB imaging flow cytometry (IFC) near-real-time classification phytoplankton imaging |
| Title | Towards operational phytoplankton recognition with automated high-throughput imaging, near-real-time data processing, and convolutional neural networks |
| URI | https://doaj.org/article/3883e8a950e64409b554283c6f6cda49 |
| Volume | 9 |
| WOSCitedRecordID | wos000855100200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2296-7745 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001340549 issn: 2296-7745 databaseCode: DOA dateStart: 20140101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2296-7745 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001340549 issn: 2296-7745 databaseCode: M~E dateStart: 20140101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 2296-7745 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001340549 issn: 2296-7745 databaseCode: M7P dateStart: 20140225 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Earth, Atmospheric & Aquatic Science Database customDbUrl: eissn: 2296-7745 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001340549 issn: 2296-7745 databaseCode: PCBAR dateStart: 20140225 isFulltext: true titleUrlDefault: https://search.proquest.com/eaasdb providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2296-7745 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001340549 issn: 2296-7745 databaseCode: BENPR dateStart: 20140225 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2296-7745 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001340549 issn: 2296-7745 databaseCode: PIMPY dateStart: 20140225 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database customDbUrl: eissn: 2296-7745 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001340549 issn: 2296-7745 databaseCode: M2P dateStart: 20140225 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Na9wwEBVl20MplH7SJG3QoadQtVrLsqRjUjb0tA1lA3sz0kiGkI3X7Hr7V_J3OyO7y_aSXHqysWRZaAbmjfz0hrHPnk7I6CoI2wCIEgGC8FY1wurCyGAMONfkYhNmPrfLpbs6KPVFnLBBHnhYuG_KWpWsd1omDN3SBYx_GBKhaiqIvsxH96RxB8lU3l1RCERKN_zGxCzMoZkwUcR8sCi-WqJ16n8C0YFefw4sl6_YyxER8vNhJq_Zk9S-YS9-QvLtKCf9lt0vMrt1y9dd2ozbdxxb-nW38u0t4je-ZwLhPW2ucr_r1whHU-QkSSzGgjzdruc3d7k00RfeopsLRI0rQSXmObFFeTecHMjtvo2caOmje-I3Sf4yXzJ5fPuOXV_OFt9_iLGkggCly16YNI1VAIzSoE2cpkb5pKxRYQo-mML7JnlXRFclGRVIMLpSJgYw1CCjU-_ZpF236QPjjQ6QQOFowZTea-sRGinKtqdJqlAeMfl3fWsY9cap7MWqxryDTFJnk9RkknowyRE727_SDWIbD3W-IKPtO5JOdn6A3lOP3lM_5j3H_2OQE_ac5pWZZ8VHNuk3u_SJPYPf_c12c8qeXszmV79Os4P-AdKX7wA |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Towards+operational+phytoplankton+recognition+with+automated+high-throughput+imaging%2C+near-real-time+data+processing%2C+and+convolutional+neural+networks&rft.jtitle=Frontiers+in+Marine+Science&rft.au=Kraft%2C+Kaisa&rft.au=Velhonoja%2C+Otso&rft.au=Eerola%2C+Tuomas&rft.au=Suikkanen%2C+Sanna&rft.date=2022-09-02&rft.issn=2296-7745&rft.eissn=2296-7745&rft.volume=9&rft_id=info:doi/10.3389%2Ffmars.2022.867695&rft.externalDBID=n%2Fa&rft.externalDocID=10_3389_fmars_2022_867695 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2296-7745&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2296-7745&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2296-7745&client=summon |