Background
The aquaculture as a whole and cage-based tilapia industry, particularly in tropical regions, face persistent environmental variability, disease outbreaks, and inefficient resource utilization challenges. AI and ML are being used in aquaculture to predict water quality changes, detect disease outbreaks early, and optimize feeding through real-time data analysis. By analyzing sensor and image data, water conditions, and disease symptoms are identified, and precise feeding decision automation is possible, thereby reducing waste, improving fish health, and enhancing resilience to environmental.
This paper systematically reviews Artificial Intelligence (AI) and Machine Learning (ML) applications in cage-based tilapia farming, aiming to explore how these technologies can enhance decision-making, predict critical parameters, and optimize production outcomes. Through an in-depth analysis of scholarly literature, the study identifies key AI/ML models used in water quality monitoring, growth prediction, feed optimization, and disease diagnostics. It also highlights gaps in data, infrastructure, local capacity, and model adaptability that hinder broader adoption in low- and middle-income countries.
Findings
A structured search across five academic databases yielded 2,064 articles on ML/AI in aquaculture, with only 213 focusing on tropical cage-based tilapia systems. Scopus alone returned 150 broadly relevant studies, narrowing to just 3 when filtered specifically for tropical tilapia cage farming. This highlights a scarcity of targeted research and exposes key gaps, such as limited access to high-resolution, location-specific environmental and production data; inadequate infrastructure like real-time water quality sensors and internet connectivity in remote farming areas, necessary to implement AI/ML tools effectively in tropical aquaculture contexts.
Conclusions
The findings underscore the transformative potential of AI and ML in improving productivity, sustainability, and resilience of aquaculture systems, while highlighting the need for integrated research, capacity-building, and policy frameworks to support responsible tech-driven innovation in tropical aquaculture.
Key Words: Artificial Intelligence, Machine Learning, Tilapia, Cage Aquaculture, Tropics, Systematic Review