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

Autor: Orenstein EC; Sorbonne Université, CNRS, Laboratoire d'Océanographie de Villefranche Villefranche-sur-Mer France., Ayata SD; Sorbonne Université, CNRS, Laboratoire d'Océanographie de Villefranche Villefranche-sur-Mer France.; Sorbonne Université, Laboratoire d'Océanographie et du Climat, Institut Pierre Simon Laplace (LOCEAN-IPSL, SU/CNRS/IRD/MNHN) Paris France., Maps F; Département de Biologie Université Laval Québec Canada.; Takuvik Joint International Laboratory Université Laval-CNRS (UMI 3376), Québec-Océan, Université Laval Québec Canada., Becker ÉC; Universidade Federal de Santa Catarina (UFSC) Florianópolis Santa Catarina Brazil., Benedetti F; ETH Zürich Institute of Biogeochemistry and Pollutant Dynamics Zürich Switzerland., Biard T; Laboratoire d'Océanologie et de Géosciences Université du Littoral Côte d'Opale, Université de Lille, CNRS, UMR 8187 Wimereux France., de Garidel-Thoron T; Aix-Marseille Université, CNRS, IRD, Coll. de France, INRAE, CEREGE Aix en Provence France., Ellen JS; Scripps Institution of Oceanography, University of California San Diego La Jolla California., Ferrario F; Département de Biologie Université Laval Québec Canada.; Takuvik Joint International Laboratory Université Laval-CNRS (UMI 3376), Québec-Océan, Université Laval Québec Canada.; Department of Fisheries and Oceans Maurice Lamontagne Institute Mont-Joli Québec Canada., Giering SLC; Ocean Biogeosciences National Oceanography Centre Southampton UK., Guy-Haim T; National Institute of Oceanography, Israel Oceanographic and Limnological Research Haifa Israel., Hoebeke L; KERMIT, Department of Data Analysis and Mathematical Modelling Ghent University Ghent Belgium., Iversen MH; Alfred Wegener Institute for Polar and Marine Research Bremerhaven Germany., Kiørboe T; Centre for Ocean Life, DTU-Aqua Technical University of Denmark Kongens Lyngby Denmark., Lalonde JF; Laboratoire de Vision et Systèmes Numériques Université Laval Québec City Québec Canada., Lana A; Institut Mediterrani d'Estudis Avançats (IMEDEA, UIB-CSIC) Balearic Islands Spain., Laviale M; Université de Lorraine, CNRS, LIEC Metz France., Lombard F; Sorbonne Université, CNRS, Laboratoire d'Océanographie de Villefranche Villefranche-sur-Mer France., Lorimer T; Eawag Dübendorf Switzerland., Martini S; Aix Marseille University, Université de Toulon, CNRS, IRD, MIO UM Marseille France., Meyer A; Université de Lorraine, CNRS, LIEC Metz France., Möller KO; Helmholtz-Zentrum Hereon Institute of Carbon Cycle Geesthacht Germany., Niehoff B; Alfred Wegener Institute for Polar and Marine Research Bremerhaven Germany., Ohman MD; Scripps Institution of Oceanography, University of California San Diego La Jolla California., Pradalier C; GeorgiaTech Lorraine CNRS IRL GT-CNRS Metz France., Romagnan JB; IFREMER, Centre Atlantique, Laboratoire Ecologie et Modèles pour l'Halieutique (EMH) Unité HALGO, UMR DECOD Nantes France., Schröder SM; Kiel University Kiel Germany., Sonnet V; Graduate School of Oceanography University of Rhode Island Narragansett Rhode Island., Sosik HM; Woods Hole Oceanographic Institution Woods Hole Massachusetts., Stemmann LS; Sorbonne Université, CNRS, Laboratoire d'Océanographie de Villefranche Villefranche-sur-Mer France., Stock M; KERMIT, Department of Data Analysis and Mathematical Modelling Ghent University Ghent Belgium., Terbiyik-Kurt T; Department of Basic Sciences Cukurova University, Faculty of Fisheries Adana Turkey., Valcárcel-Pérez N; Centro Oceanográfico de Málaga, IEO, CSIC Fuengirola Spain., Vilgrain L; Sorbonne Université, CNRS, Laboratoire d'Océanographie de Villefranche Villefranche-sur-Mer France., Wacquet G; IFREMER, Laboratoire Environnement Ressources Boulogne-sur-Mer France., Waite AM; Ocean Frontier Institute, Dalhousie University Halifax Nova Scotia Canada., Irisson JO; Sorbonne Université, CNRS, Laboratoire d'Océanographie de Villefranche Villefranche-sur-Mer France.
Jazyk: angličtina
Zdroj: Limnology and oceanography [Limnol Oceanogr] 2022 Aug; Vol. 67 (8), pp. 1647-1669. Date of Electronic Publication: 2022 Jun 30.
DOI: 10.1002/lno.12101
Abstrakt: 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 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 machine learning and 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 imagery of other aquatic or terrestrial organisms.
Competing Interests: None declared.
(© 2022 The Authors. Limnology and Oceanography published by Wiley Periodicals LLC on behalf of Association for the Sciences of Limnology and Oceanography.)
Databáze: MEDLINE
Externí odkaz: