TY - JOUR

T1 - Machine learning in marine ecology an overview of techniques and applications

AU - Rubbens, Peter

AU - Brodie, Stephanie

AU - Cordier, Tristan

AU - Destro Barcellos, Diogo

AU - Devos, Paul

AU - A Fernandes-Salvador, Jose

AU - I Fincham, Jennifer

AU - Gomes, Alessandra

AU - Olav Handegard, Nils

AU - Howell, Kerry L.

AU - Jamet, Cédric

AU - Heldal Kartveit, Kyrre

AU - Moustahfid, Hassan

AU - Parcerisas, Clea

AU - Politikos, Dimitris

AU - Sauzède, Raphaëlle

AU - Sokolova, Maria

AU - Uusitalo, Laura

AU - Van den Bulcke, Laure

AU - TM van Helmond, Aloysius

AU - T Watson, Jordan

AU - Welch, Heather

AU - Beltran-Perez, Oscar

AU - Chaffron, Samuel

AU - S Greenberg, David

AU - Kühn, Bernhard

AU - Kiko, Rainer

AU - Lo, Madiop

AU - M Lopes, Rubens

AU - Ove Möller, Klas

AU - Michaels, William

AU - Pala, Ahmet

AU - Romagnan, Jean-Baptiste

AU - Schuchert, Pia

AU - Seydi, Vahid

AU - Villasante, Sebastian

AU - Malde, Ketil

AU - Irisson, Jean-Olivier

PY - 2023/9/1

Y1 - 2023/9/1

N2 - 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.

AB - 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.

U2 - 10.1093/icesjms/fsad100

DO - 10.1093/icesjms/fsad100

M3 - Article

VL - 80

JO - ICES Journal of Marine Science

JF - ICES Journal of Marine Science

SN - 1054-3139

IS - 7

ER -