An analytical framework to predict slaughter traits from images in fish DOI Creative Commons

Yuuko Xue,

J.W.M. Bastiaansen, Haris Ahmad Khan

et al.

Aquaculture, Journal Year: 2022, Volume and Issue: 566, P. 739175 - 739175

Published: Dec. 22, 2022

Accurate measurements of breeding traits on individuals are critical in aquaculture for obtaining values and tracking the progress program. Modern programs prioritize not only production but also complex related to production, product quality, body composition, disease resistance, fish health, such as slaughter traits. Slaughter can be selected indirectly incorporated into programs. Indirect selection is cost-effective, there often little genetic correlation between measured target phenotypic prediction using modern phenotyping technology game-changing indirect selection. This paper proposes an analytical framework predicting images. The demonstrated that images addition weight improved fat percentage accuracy from 0.4 0.7 when compared a model used its numerical derivations. allowed interpretation by providing imaginal features. In case study, dorsal side, upper edge pectoral fin, operculum were discovered three regions seabream have properties negatively correlated with fillet percentage. showed both visceral highly total area. revealed lower edge, anal fin explain variation Future research will required segment quantify each predictive feature calculate heritability. potentially predict other harvest, post-slaughter, metabolic aquacultural study.

Language: Английский

Exploring opportunities of Artificial Intelligence in aquaculture to meet increasing food demand DOI Creative Commons
Mohd Ashraf Rather, Ishtiyaq Ahmad,

Azra Shah

et al.

Food Chemistry X, Journal Year: 2024, Volume and Issue: 22, P. 101309 - 101309

Published: March 19, 2024

The increasing global population drives a rising demand for food, particularly fish as preferred protein source, straining capture fisheries. Overfishing has depleted wild stocks, emphasizing the need advanced aquaculture technologies. Unlike agriculture, not seen substantial technological advancements. Artificial Intelligence (AI) tools like Internet of Things (IoT), machine learning, cameras, and algorithms offer solutions to reduce human intervention, enhance productivity, monitor health, feed optimization, water resource management. However, challenges such data collection, standardization, model accuracy, interpretability, integration with existing systems persist. This review explores adoption AI techniques advance industry bridge gap between food supply demand.

Language: Английский

Citations

28
Digital Twins in intensive aquaculture — Challenges, opportunities and future prospects DOI Creative Commons
Martin Føre,

Morten Omholt Alver,

Jo Arve Alfredsen

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 218, P. 108676 - 108676

Published: Feb. 1, 2024

Digital Twin technology has emerged to become a key enabling in the ongoing transition into Industry 4.0. A is essence digital representation of an asset that provides better insight its dynamics by combining priori knowledge system through mathematical models with online data acquired from sensors and instruments deployed or at physical asset. While seeing increased use across several different industrial, governmental research sectors, scientific disciplines, application within aquaculture still infancy. However, due rapid development technological methods aquaculture, increasing number building blocks required make for purposes are becoming available. We set out explore these possibilities first defining — what components it should contain, how be constructed, outlining capability levels finished Twin. Our next step was then state-of-the-art technologies thereby identifying current foundation developing this sector. Following this, we developed concrete case studies elaborate upon existing new tools could envision Twins three areas high industrial relevance, namely oxygen conditions sea-cages, fish growth sea-cages in-cage robotics vehicle operations. In conclusion, present our thoughts on potential being component ushering 4.0 outline pathway way onward towards achieving goal.

Language: Английский

Citations

15
Advancing genetic improvement in the omics era: status and priorities for United States aquaculture DOI Creative Commons
Linnea K. Andersen, Neil F. Thompson, Jason Abernathy

et al.

BMC Genomics, Journal Year: 2025, Volume and Issue: 26(1)

Published: Feb. 17, 2025

The innovations of the "Omics Era" have ushered in significant advancements genetic improvement agriculturally important animal species through transforming genetics, genomics and breeding strategies. These were often coordinated, part, by support provided over 30 years 1993-2023 National Research Support Project 8 (NRSP8, Animal Genome Program, NAGRP) affiliate projects focused on enabling genomic discoveries livestock, poultry, aquaculture species. parallel advances demand strategic planning future research priorities. This paper, as an output from May 2023 Aquaculture Genomics, Genetics, Breeding Workshop, provides updated status resources for United States species, highlighting major achievements emerging Finfish shellfish genome omics enhance our understanding architecture heritability performance production traits. Workshop identified present aims genomics/omics to build this progress: (1) advancing reference assembly quality; (2) integrating multi-omics data analysis traits; (3) developing collection integration phenomics data; (4) creating pathways applying information across industries; (5) providing training, extension, outreach application phenome. focuses should emphasize collection, artificial intelligence, identifying causative relationships between genotypes phenotypes, establishing apply tools industries, expansion training programs next-generation workforce facilitate sciences into operations productivity, competitiveness, sustainability. collective vision with focus highlighted priorities is intended continued advancement genomics, genetics community industries. Critical challenges ahead include practical analytical frameworks beyond academic communities that require collaborative partnerships academia, government, industry. scope review encompasses use applications study aquatic animals cultivated human consumption settings throughout their life-cycle.

Language: Английский

Citations

2
Genomic selection and its research progress in aquaculture breeding DOI
Hailiang Song, Tian Dong, Xiaoyu Yan

et al.

Reviews in Aquaculture, Journal Year: 2022, Volume and Issue: 15(1), P. 274 - 291

Published: Aug. 1, 2022

Abstract Since its introduction in 2001, genomic selection (GS) has progressed rapidly. As a research and application hot topic, GS led to revolution the field of animal plant breeding. Thanks ability overcome shortcomings traditional breeding methods, garnered increasing attention. Both theoretical practical studies have revealed higher accuracy than that breeding, which can accelerate genetic gain. In recent years, many been conducted on aquaculture species, shown produces prediction pedigree‐based method. The present study reviews principles processes, preconditions, advantages, analytical methods factors influencing as well progress into these aspects. Furthermore, future directions are also discussed, should expand more species.

Language: Английский

Citations

61
AI-driven aquaculture: A review of technological innovations and their sustainable impacts DOI Creative Commons
Hang Yang, Feng Qi, Shibin Xia

et al.

Artificial Intelligence in Agriculture, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

1
Fish Genomics and Its Application in Disease‐Resistance Breeding DOI Creative Commons
Yu Huang, Zeyu Li,

Mengcheng Li

et al.

Reviews in Aquaculture, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 10, 2024

ABSTRACT Global aquaculture production has been rising for several decades, with up to 76% of the total from fish. However, problem fish diseases is becoming more and prominent in today's context pursuing sustainable aquaculture. Since first genome assembly reported 2002, genomic approaches have successfully implemented breeding enhance disease resistance reduce economic losses caused by diverse diseases. Here, we present a review current progress genomics its application disease‐resistance breeding. First, data all publicly available genomes were curated statistical analysis these performed. Subsequently, genomics‐assisted (including quantitative trait loci mapping, genome‐wide association study, marker‐assisted selection, gene transfer, editing) that applied practical disease–resistance programs are outlined. In addition, candidate genetic markers could possibly be utilized summarized. Finally, remaining challenges further directions discussed. summary, this provides insight into disease‐resistant varieties.

Language: Английский

Citations

7
Unlocking the Potential: Artificial Intelligence Applications in Aquaculture Greenhouse Development DOI Creative Commons
Einar Ringø, Amr M. Helal,

Ehab El-Haron

et al.

IntechOpen eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: March 24, 2025

Aquaculture plays a significant role in the expanding agricultural sector, with historical challenges stemming from experimental limitations. Upholding ecological balance and water quality improvements stands as pivotal factor bolstering efficiency sustainability of aquaculture production. Notably, greenhouse setups have addressed various environmental concerns, boosting productivity sustainability. The ongoing advancement science technology has ushered new era aquaculture, marked by integration Artificial Intelligence (AI) digitalization. AI represents fascinating powerful machine learning-based techniques for solving many real-world problems. To regulate is used to assess sensor data real time using sophisticated algorithms, allowing proactive adjustments maintain ideal conditions. Likewise, essential disease identification since it uses Internet Things (IoT) learning (ML) models identify subtle patterns fish behavior or health parameters, facilitating early intervention mitigation strategies. This book chapter overviews transformative potential applications development systems, including monitoring, feed management, detection, predictive analytics, collection, model development, ethical considerations. By unlocking AI, can benefit increased productivity, reduced impact, enhanced

Language: Английский

Citations

0
Fish Disease Detection in Aquaculture using Pseudo Hamiltonian Neural network Optimized with Philippine Eagle Optimization Algorithm DOI

Mr. Prasanna kumar M,

Saravana Kumar K,

K. P.

et al.

Knowledge-Based Systems, Journal Year: 2025, Volume and Issue: unknown, P. 113374 - 113374

Published: March 1, 2025

Language: Английский

Citations

0
Deep learning for genomic selection of aquatic animals DOI
Yangfan Wang, Ping Ni, Marc Sturrock

et al.

Marine Life Science & Technology, Journal Year: 2024, Volume and Issue: 6(4), P. 631 - 650

Published: Sept. 27, 2024

Language: Английский

Citations

3
Towards a Novel Architectural Design for IoT-Based Smart Marine Aquaculture DOI
Rodolfo W. L. Coutinho, Azzedine Boukerche

IEEE Internet of Things Magazine, Journal Year: 2022, Volume and Issue: 5(3), P. 174 - 179

Published: Sept. 1, 2022

Marine farms must employ innovative solutions and new technologies to increase productivity supply the seafood demand sustainably. In this paper, we propose a novel four-layers architecture for smart marine farms. The proposed relies on recent advancements proposes integration of Internet Things (IoT) Underwater (loUT), edge cloud computing, machine learning (ML) efficient reliable underwater sensors, data transfer among components in aquaculture farm, real-time processing inference monitoring control designed will tackle many fundamental challenges aimed at autonomous, intelligent, For each component, issues it tackles guidelines implementing are presented. Finally, shed light open that still prevent features aquaculture.

Language: Английский

Citations

15