Efficient treatment of aquaculture effluent is a crucial measure for ensuring the green and sustainable development of fisheries and alleviating pressure on aquatic ecosystems. However, traditional treatment technologies face bottlenecks of low efficiency and poor adaptability, making it difficult to meet the pollution control demands of large-scale aquaculture development. This is a systematic review focusing on artificial intelligence (AI) applications in aquaculture effluent treatment, aiming to clarify the technical framework, core application scenarios, industry trends, challenges, and future directions of AI-driven aquaculture effluent treatment. It first outlines core machine learning technologies, compares model adaptability, and analyzes AI synergies with IoT and digital twins. It then details AI implementation pathways across four core scenarios: precision feeding for pollution reduction, water quality monitoring and prediction, development of denitrifying and phosphorus-removing engineering bacteria, and system module control. Finally, it validates technical effectiveness through case studies, identifies industry trends toward integrated models and predictive monitoring, highlights existing challenges, such as data quality bottlenecks, system coupling complexity, and insufficient implementation economics, and proposes future research directions. This study provides theoretical foundations and practical references for the intelligent upgrading of aquaculture effluent treatment and the high-quality development of the fisheries industry.
Wang et al. (2026) studied this question.