Aim: The study aimed to evaluate the potential of Artificial Intelligence (AI) and Machine Learning (ML) in improving aquaculture production systems through enhanced monitoring, automation, and data-driven decision-making. Methods: The study was conducted through a comprehensive analysis of recent experimental and field-based reports integrating AI-driven technologies in aquaculture. Models such as convolutional neural networks, recurrent neural networks, and AIoT-based digital twins were reviewed for their applications in monitoring fish growth, detecting disease, and controlling water quality. Various aquatic species, including tilapia, salmon, and carp, were referenced as model organisms in these studies to evaluate performance accuracy and operational efficiency. Results: The findings revealed that AI-enabled image recognition models successfully detected fish health anomalies and feeding behaviours with high precision. Sensor-based water quality systems linked to AI algorithms improved environmental stability and reduced mortalities. Automated feeding and real-time decision-support frameworks minimized resource wastage, while predictive models optimized growth rates and harv
📖 افتح في inklap 🔗 DOI 📮 اطلب بحثاً