Artificial intelligence and digital innovations in precision aquaculture: Advancements, applications, and future directions
Искусственный интеллект и цифровые инновации в прецизионном аквакультуре: достижения, применения и перспективы
2026-03-10
SCID: 54.1/5ths3w2u
Discuss with AI
AI in precision aquacultureIoT and Big Data integrationdigital twinsedge AI deploymentfederated learning
Figures from the paper
Abstract (AI)
• Integration of AI, IoT, and Big Data is revolutionising automation and predictive control in aquaculture. • Advanced technologies, including federated learning, blockchain, and digital twins, enhance process optimisation. • Socioeconomic, infrastructural, and regulatory barriers impact large-scale AI implementation in aquaculture. The aquaculture sector is undergoing a rapid digital transformation, driven by the accelerated advancement of artificial intelligence (AI) technologies. This review examines how AI, alongside the Internet of Things (IoT) and Big Data, is reshaping smart aquafarming systems through intelligent automation, real-time decision-making, and predictive analytics. AI methodologies, such as machine learning, deep learning, attention-based models, and hybrid algorithms, are enabling significant improvements in water quality prediction, disease detection, feed optimisation, and behavioural analysis. The review also explores cutting-edge innovations beyond conventional AI applications. These include federated learning, explainable AI, edge AI deployment, and transfer learning, which address critical challenges related to data and system scalability in dynamic aquaculture environments. Particular emphasis is placed on the integration of AI with IoT systems and the development of digital twins to simulate and optimise aquaculture processes for predictive control. Furthermore, the potential of quantum AI and blockchain technologies are also assessed in the context of future-proof aquaculture systems. The review also provides a critical assessment of the socioeconomic barriers, infrastructural limitations, ethical considerations, and regulatory gaps that hinder the widespread implementation of AI—especially in rural and resource-constrained settings. This analysis presents a prospective framework for the development of scalable, resilient, and sustainable aquaculture systems empowered by next-generation AI technologies.
Key Findings
1
Advanced approaches—federated learning, explainable AI, edge AI, and transfer learning—address data and scalability challenges in dynamic aquaculture environments.
2
Integration of AI with IoT and development of digital twins enables simulation and optimization of aquaculture processes for predictive control.
3
Integration of AI, IoT, and Big Data is revolutionizing automation, real-time decision-making, and predictive control in aquaculture.
4
Machine learning, deep learning, attention-based models, and hybrid algorithms improve water quality prediction, disease detection, feed optimization, and behavioral analysis.
5
Socioeconomic, infrastructural, ethical, and regulatory barriers, especially in rural and resource-constrained settings, hinder large-scale AI implementation; blockchain and quantum AI are assessed as potential future enablers.
Research Object
Smart/precision aquaculture systems (AI-, IoT-, and Big Data-enabled aquafarming systems)
Research Subject
Integration and application of AI and digital innovations (machine learning, deep learning, federated learning, explainable AI, edge AI, digital twins, blockchain, quantum AI) for automation, real-time decision-making, predictive control, water quality prediction, disease detection, feed optimisation, behavioural analysis, and scalability/resilience challenges in aquaculture
Publication Details
Publication Date
2026-03-10
Journal
Publisher
ISSN
Cited by
2
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence2023
The contribution of aquaculture systems to global aquaculture production2023
Integrating Artificial Intelligence Agents with the Internet of Things for Enhanced Environmental Monitoring: Applications in Water Quality and Climate Data2025
Deep Learning for Sustainable Aquaculture: Opportunities and Challenges2025
Nonintrusive methods for biomass estimation in aquaculture with emphasis on fish: a review2019