Artificial Intelligence-Driven Smart Aquaculture: Technologies, Applications and Future Directions

Abstract

Aquaculture is in a critical state globally, with unprecedented demand for sustainable seafood production and numerous environmental and operational challenges. In the era of modern aquaculture, artificial intelligence (AI) has become a game-changer, providing innovative solutions that include real-time sensing, predictive analytics and autonomous decision making into aquaculture production systems. This comprehensive review explores the state of the art, applications, and future trends of AI-enabled smart aquaculture. We methodically examine five research areas: water quality monitoring and predictive modelling, automated disease detection and diagnosis, precision feeding and nutritional optimization, biomass estimation and growth prediction, integrated risk management frameworks. Also, the intersection of AI with other emerging technologies such as IoT, blockchain, robotics, and cloud computing is discussed. From our analysis, we have found that the machine learning algorithms such as convolutional neural networks (CNNs) and long short term memory (LSTM) networks have been able to attain very high accuracy rates of more than 92% in the disease detection and biomass estimation. Despite this, major barriers still exist in the implementation process, such as high costs, lack of practitioner technical skills, data standardization problems, and the gap between algorithmic predictions and operational decision-making procedures. We pinpoint key research gaps and outline a research agenda for future development that focuses on explainable AI, federated learning and hybrid decision support systems. The review offers valuable insights for researchers, industry professionals, and policymakers to tap into the potential of AI to support sustainable aquaculture practices globally.