Machine learning in marine ecology an overview of techniques and applications

Allbwn ymchwil: Cyfraniad at gyfnodolynErthygladolygiad gan gymheiriaid

Fersiynau electronig

Dangosydd eitem ddigidol (DOI)

  • Peter Rubbens
    Flanders Marine Institute (VLIZ), Belgium
  • Stephanie Brodie
    University of California, Santa Cruz
  • Tristan Cordier
    University of Geneva, Geneva, Switzerland
  • Diogo Destro Barcellos
    University of Sao Paulo
  • Paul Devos
    Department of Experimental Clinical and Health Psychology, Ghent University, Ghent, Belgium
  • Jose A Fernandes-Salvador
    AZTI, Spain
  • Jennifer I Fincham
    CEFAS
  • Alessandra Gomes
    University of Sao Paulo
  • Nils Olav Handegard
    Institute of Marine Research, Nordnes, Bergen, Norway
  • Kerry L. Howell
    University of Plymouth
  • Cédric Jamet
    Université du Littoral Côte d'Opale
  • Kyrre Heldal Kartveit
    Institute of Marine Research, Nordnes, Bergen, Norway
  • Hassan Moustahfid
    U.S. National Oceanic and Atmospheric Administration
  • Clea Parcerisas
    Flanders Marine Institute (VLIZ), Belgium
  • Dimitris Politikos
    Hellenic Centre for Marine Research
  • Raphaëlle Sauzède
    Sorbonne Universités
  • Maria Sokolova
    Wageningen University and Research
  • Laura Uusitalo
    Finnish Environment Institute
  • Laure Van den Bulcke
    Flanders Research Institute for Agriculture, Fisheries and Food
  • Aloysius TM van Helmond
    Wageningen University and Research
  • Jordan T Watson
    Joint Institute for Marine and Atmospheric Research, University of Hawaii, Manoa, Honolulu, Hawaii 96822, USA.
  • Heather Welch
    University of California, Santa Cruz
  • Oscar Beltran-Perez
    Leibniz Institute of Baltic Sea Research, Rostock
  • Samuel Chaffron
    Nantes University
  • David S Greenberg
    Helmholtz Zentrum Hereon
  • Bernhard Kühn
    Johann Heinrich von Thünen Institute of Sea Fisheries
  • Rainer Kiko
    Sorbonne Universités
  • Madiop Lo
    Aix-Marseille Universite
  • Rubens M Lopes
    University of Sao Paulo
  • Klas Ove Möller
    Helmholtz Zentrum Hereon
  • William Michaels
    NOAA, National Marine Fisheries Service, USA
  • Ahmet Pala
    University of Bergen
  • Jean-Baptiste Romagnan
    DECOD (Ecosystem Dynamics and Sustainability), France
  • Pia Schuchert
    Agri-food and Biosciences Institute of Northern Ireland (AFBINI)
  • Vahid Seydi
  • Sebastian Villasante
    University of Santiago de Compostela
  • Ketil Malde
    Institute of Marine Research, Nordnes, Bergen, Norway
  • Jean-Olivier Irisson
    Sorbonne Universités
Machine learning covers a large set of algorithms that can be trained to identify patterns in data. Thanks to the increase in the amount of data and computing power available, it has become pervasive across scientific disciplines. We first highlight why machine learning is needed in marine ecology. Then we provide a quick primer on machine learning techniques and vocabulary. We built a database of ∼1000 publications that implement such techniques to analyse marine ecology data. For various data types (images, optical spectra, acoustics, omics, geolocations, biogeochemical profiles, and satellite imagery), we present a historical perspective on applications that proved influential, can serve as templates for new work, or represent the diversity of approaches. Then, we illustrate how machine learning can be used to better understand ecological systems, by combining various sources of marine data. Through this coverage of the literature, we demonstrate an increase in the proportion of marine ecology studies that use machine learning, the pervasiveness of images as a data source, the dominance of machine learning for classification-type problems, and a shift towards deep learning for all data types. This overview is meant to guide researchers who wish to apply machine learning methods to their marine datasets.

Iaith wreiddiolSaesneg
CyfnodolynICES Journal of Marine Science
Cyfrol80
Rhif y cyfnodolyn7
Dyddiad ar-lein cynnar3 Awst 2023
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsCyhoeddwyd - 1 Medi 2023
Gweld graff cysylltiadau