Machine learning techniques to characterize functional traits of plankton from image data - Université de Lorraine
Journal Articles Limnology and Oceanography Year : 2022

Machine learning techniques to characterize functional traits of plankton from image data

1 LOV - Laboratoire d'océanographie de Villefranche
2 LOCEAN-PROTEO - Processus et interactions de fine échelle océanique
3 ULaval - Université Laval [Québec]
4 UFSC - Universidade Federal de Santa Catarina = Federal University of Santa Catarina [Florianópolis]
5 IBP - Institute of Biogeochemistry and Pollutant Dynamics [ETH Zürich]
6 LOG - Laboratoire d’Océanologie et de Géosciences (LOG) - UMR 8187
7 CEREGE - Centre Européen de Recherche et d'Enseignement des Géosciences de l'Environnement
8 SIO - UC San Diego - Scripps Institution of Oceanography
9 NOC - National Oceanography Centre [Southampton]
10 IOLR - Israel Oceanographic and Limnological Research
11 UGENT - Universiteit Gent = Ghent University = Université de Gand
12 AWI - Alfred Wegener Institute for Polar and Marine Research
13 DTU Centre for Ocean Life
14 LVSN - Laboratoire de Vision et Systèmes Numériques
15 IMEDEA - Institut Mediterrani d'Estudis Avancats = Instituto Mediterráneo de Estudios Avanzados
16 LIEC - Laboratoire Interdisciplinaire des Environnements Continentaux
17 IUF - Institut universitaire de France
18 EAWAG - Swiss Federal Insitute of Aquatic Science and Technology [Dübendorf]
19 MIO - Institut méditerranéen d'océanologie
20 Helmholtz-Zentrum Hereon
21 Georgia Tech Lorraine [Metz]
22 EMH - Unité Écologie et Modèles pour l'Halieutique
23 DECOD - Dynamique et durabilité des écosystèmes : de la source à l’océan
24 CAU - Christian-Albrechts-Universität zu Kiel = Christian-Albrechts University of Kiel = Université Christian-Albrechts de Kiel
25 URI - University of Rhode Island
26 WHOI - Woods Hole Oceanographic Institution
27 Cukurova University
28 IEO - Instituto Español de Oceanografía - Spanish Institute of Oceanography
29 IFREMER - Institut Français de Recherche pour l'Exploitation de la Mer
30 Dalhousie University [Halifax]
Frédéric Maps
Cedric Pradalier
Virginie Sonnet
Heidi M. Sosik

Abstract

Plankton imaging systems supported by automated classification and analysis have improved ecologists' ability to observe aquatic ecosystems. Today, we are on the cusp of reliably tracking plankton populations with a suite of lab-based and in situ tools, collecting imaging data at unprecedentedly fine spatial and temporal scales. But these data streams have potential well beyond examining the abundances of different taxa; the individual images themselves contain a wealth of information on functional traits. Here we outline traits that could be measured from image data, suggest computer vision approaches to extract functional trait information from the images, and discuss promising avenues for novel studies. The approaches we discuss are data agnostic and are broadly applicable to other aquatic or terrestrial organisms.
Fichier principal
Vignette du fichier
Limnology Oceanography - 2022 - Orenstein - Machine learning techniques to characterize functional traits of plankton.pdf (1.16 Mo) Télécharger le fichier
Origin Publication funded by an institution

Dates and versions

hal-03482282 , version 1 (15-12-2021)
hal-03482282 , version 2 (30-06-2022)

Licence

Identifiers

Cite

Eric C. Orenstein, Sakina-Dorothée Ayata, Frédéric Maps, Érica C. Becker, Fabio Benedetti, et al.. Machine learning techniques to characterize functional traits of plankton from image data. Limnology and Oceanography, 2022, 67 (8), pp.1647-1669. ⟨10.1002/lno.12101⟩. ⟨hal-03482282v2⟩
823 View
762 Download

Altmetric

Share

More