Fishing vessels as met-ocean data collection platforms: data lifecycle from acquisition to sharing DOI Creative Commons
Ivan Manso-Narvarte, Lohitzune Solabarrieta, Ainhoa Caballero

et al.

Frontiers in Marine Science, Journal Year: 2024, Volume and Issue: 11

Published: Dec. 20, 2024

The collection of meteorological and oceanographic (met-ocean) data is essential to advance knowledge the state oceans, leading better-informed decisions. Despite technological advances increase in recent years, met-ocean still not trivial as it requires a high effort cost. In this context, resulting from commercial activities increasingly complement existing scientific collections vast ocean. Commercial fishing vessels (herein vessels) are an example observing platforms for collection, providing valuable additional temporal spatial coverage, particularly regions often covered by platforms. These could contribute Global Ocean Observing System (GOOS) with Essential Variables (EOV) provided that accessibility manageability created datasets guaranteed adhering FAIR principles, reproducible uncertainty included datasets. Like other industrial activities, fisheries sometimes reluctant share their data, thus anonymization techniques, well license access restrictions help foster collaboration between them community. main aim article guide, practical point view, how create highly vessel observations towards establishing new First, principles presented comprehensively described, context later implementation. Then, lifecycle three showcased case studies illustrate steps be followed. It starts acquisition follows quality control, processing validation which shows good general performance therefore further reassures potential next making possible, richly documenting standardized convention-based vocabularies, metadata format. Subsequently, submitted widely used repositories while persistent identifier also assigned. Finally, take-home messages lessons learned they useful dataset creators.

Language: Английский

A grey-box deep learning modelling strategy for fuel oil consumption prediction: A case study of tuna purse seiner DOI Creative Commons
Yi Zhou, Kayvan Pazouki, Rosemary Norman

et al.

Ocean Engineering, Journal Year: 2025, Volume and Issue: 324, P. 120733 - 120733

Published: Feb. 24, 2025

Language: Английский

Citations

1
Yapay Zeka Uygulamalarının Mavi Yüzgeçli Orkinos (Thunnus Thynnus (Linnaeus, 1758))’un Avcılığı ve Yetiştiriciliği’nin Rolü DOI
Oğulcan Kemal Sagun, Hülya Sayğı

Menba Kastamonu Üniversitesi Su Ürünleri Fakültesi Dergisi, Journal Year: 2025, Volume and Issue: 11(1), P. 96 - 115

Published: March 28, 2025

Yapay Zeka (AI); öğrenme, problem çözme ve karar verme gibi tipik olarak insan zekası gerektiren görevleri yerine getirebilen bilgisayar sistemlerinin geliştirilmesi uygulanması anlamına gelmektedir son yıllarda birçok sektörde kullanımı yaygınlaşmıştır. zeka; balık yetiştiriciliğinde büyümesi sağlığının anlaşılmasını yönetimini önemli ölçüde artırabilecek gerçek zamanlı izleme, veri analitiği, tahmine dayalı modelleme destek sistemleri için fırsatlar sunmaktadır. zekanın orkinos avcılığı et kalitesinin belirlenmesinde de kullanılmaya başlandığı görülmektedir. Ton balığının kalitesini değerlendiren bir AI sistemi olan TUNA SCOPE, Cermaq Umitron Corporation şirketlerin sağlığını refahını iyileştirmek çeşitli girişimlerde bulundukları AI'nın su ürünleri yetiştiriciliğine entegrasyonunun, işgücü maliyetlerini çevresel etkileri azaltırken verimliliği artıran odaklı kararlara olanak tanıyarak sürdürülebilir uygulamalarda devrim yaratması beklenmektedir. Çalışmamızın amacı; yapay zeka kullanımı, balıkçılık yetiştiriciliğindeki orkinoslarda ile ilgili yapılmış çalışmaların detaylı şekilde incelenerek sunmak ileride yapılacak uygulamaları alt yapı oluşturmaktır.

Citations

0
⁠Marine Ecosystem Monitoring Based on Remote Sensing Using Underwater Image Analysis for Biodiversity Conservation Model DOI
Chandana Narasimha Rao, A. Venkateswara Rao,

G. Shanmugasundar

et al.

Remote Sensing in Earth Systems Sciences, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 16, 2024

Language: Английский

Citations

0
Machine Learning Applications for Fisheries—At Scales from Genomics to Ecosystems DOI Creative Commons

Bernhard Kühn,

Arjay Cayetano, Jennifer I. Fincham

et al.

Reviews in Fisheries Science & Aquaculture, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 24

Published: Nov. 9, 2024

Fisheries science aims to understand and manage marine natural resources. It relies on resource-intensive sampling data analysis. Within this context, the emergence of machine learning (ML) systems holds significant promise for understanding disparate components these ecosystems gaining a greater their dynamics. The goal paper is present review ML applications in fisheries science. highlights both advantages over conventional approaches drawbacks, particularly terms operationality possible robustness issues. This organized from small large scales. begins with genomics subsequently expands individuals (catch items), aggregations different species situ, on-board processing, stock/populations assessment dynamics, spatial mapping, fishing-related organizational units, finally ecosystem Each field has its own set challenges, such as pre-processing steps, quantity quality training data, necessity appropriate model validation, knowing where algorithms are more limited, we discuss some discipline-specific challenges. scope discussion applied methods ranges statistical data-specific that use higher level semantics. concludes potential implications management decisions summary benefits challenges using techniques fisheries.

Language: Английский

Citations

0
Fishing vessels as met-ocean data collection platforms: data lifecycle from acquisition to sharing DOI Creative Commons
Ivan Manso-Narvarte, Lohitzune Solabarrieta, Ainhoa Caballero

et al.

Frontiers in Marine Science, Journal Year: 2024, Volume and Issue: 11

Published: Dec. 20, 2024

The collection of meteorological and oceanographic (met-ocean) data is essential to advance knowledge the state oceans, leading better-informed decisions. Despite technological advances increase in recent years, met-ocean still not trivial as it requires a high effort cost. In this context, resulting from commercial activities increasingly complement existing scientific collections vast ocean. Commercial fishing vessels (herein vessels) are an example observing platforms for collection, providing valuable additional temporal spatial coverage, particularly regions often covered by platforms. These could contribute Global Ocean Observing System (GOOS) with Essential Variables (EOV) provided that accessibility manageability created datasets guaranteed adhering FAIR principles, reproducible uncertainty included datasets. Like other industrial activities, fisheries sometimes reluctant share their data, thus anonymization techniques, well license access restrictions help foster collaboration between them community. main aim article guide, practical point view, how create highly vessel observations towards establishing new First, principles presented comprehensively described, context later implementation. Then, lifecycle three showcased case studies illustrate steps be followed. It starts acquisition follows quality control, processing validation which shows good general performance therefore further reassures potential next making possible, richly documenting standardized convention-based vocabularies, metadata format. Subsequently, submitted widely used repositories while persistent identifier also assigned. Finally, take-home messages lessons learned they useful dataset creators.

Language: Английский

Citations

0