Machine Learning Applications for Fisheries—At Scales from Genomics to Ecosystems
2025
Kühn, Bernhard | Cayetano, Arjay | Fincham, Jennifer I. | Moustahfid, Hassan | Sokolova, Maria | Trifonova, Neda | Watson, Jordan T. | Fernandes-Salvador, Jose A. | Uusitalo, Laura
Fisheries science aims to understand and manage marine natural resources. It relies on resource-intensive sampling and data analysis. Within this context, the emergence of machine learning (ML) systems holds significant promise for understanding disparate components of these marine ecosystems and gaining a greater understanding of their dynamics. The goal of this paper is to present a review of ML applications in fisheries science. It highlights both their advantages over conventional approaches and their drawbacks, particularly in terms of operationality and possible robustness issues. This review is organized from small to large scales. It begins with genomics and subsequently expands to individuals (catch items), aggregations of different species in situ, on-board processing, stock/populations assessment and dynamics, spatial mapping, fishing-related organizational units, and finally ecosystem dynamics. Each field has its own set of challenges, such as pre-processing steps, the quantity and quality of training data, the necessity of appropriate model validation, and knowing where ML algorithms are more limited, and we discuss some of these discipline-specific challenges. The scope of discussion of applied methods ranges from conventional statistical methods to data-specific approaches that use a higher level of semantics. The paper concludes with the potential implications of ML applications on management decisions and a summary of the benefits and challenges of using these techniques in fisheries.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Wageningen University & Research
Découvrez la collection de ce fournisseur de données dans AGRIS