AI and IoT for Water Quality Monitoring and Aquatic Animal Health in Aquaculture: A Review of Applications and Challenges

AI and IoT for Water Quality Monitoring and Aquatic Animal Health in Aquaculture: A Review of Applications and Challenges

Mohammad zahedi1

1) Mohammad Zahedi PhD Candidate in Aquatic Animal Health and Diseases Faculty of Veterinary Medicine, Shahid Chamran University of Ahvaz Ahvaz, Iran Email:

IOI Code : AAHD-ACZFDK
Publication : National Conference on Information Technology, Nanotechnology, Artificial Intelligence and Technological Futures Studies(itnaf.ir)
Abstract :
    Aquatic animal health is increasingly threatened by deteriorating water quality, intensifying aquaculture production, and climate-driven changes in coastal ecosystems, while conventional monitoring based on manual sampling and laboratory diagnosis remains laborious, delayed, and poorly suited to remote coastal environments. This narrative review synthesizes the literature published between 2020 and 2026 regarding the application of artificial intelligence (AI) and the Internet of Things (IoT) for water quality monitoring and aquatic animal health management, with an emphasis on coastal ecosystems and aquaculture. Searches were conducted in Scopus, Web of Science, IEEE Xplore, PubMed, and Google Scholar using combinations of keywords related to AI, IoT, water quality, machine learning, aquatic animal health, and coastal ecosystems. Thematic analysis of the included studies identified seven domains: limitations of traditional monitoring; IoT-based sensing and telemetry; AI and machine learning for water quality prediction; AI-driven disease detection, behavioral analysis, and early warning; applications in coastal aquaculture; existing challenges; and future directions. The evidence indicates that IoT sensor networks monitoring pH, temperature, dissolved oxygen, ammonia, salinity, and turbidity enable continuous, real-time data acquisition, while machine learning and deep learning models—particularly long short-term memory (LSTM) networks, convolutional neural networks (CNN), and hybrid architectures—have shown promising predictive performance in forecasting water quality deterioration and automating the detection of disease-associated phenotypes or clinical signs. However, challenges such as data quality, sensor biofouling, model generalizability, infrastructure costs, and regulatory gaps remain significant. This review suggests that AI and IoT should be regarded as complementary decision-support tools for veterinarians and farm managers rather than replacements. Integrating these technologies supports sustainable aquaculture, coastal ecosystem stability, veterinary public health, and progress toward the Sustainable Development Goals.

Keywords : artificial intelligence internet of things water quality aquatic animal health aquaculture coastal ecosystems