Artificial intelligence methods used in various aquaculture applications: A systematic literature review

Abstract

This research article presents a systematic literature review on the current state‐of‐the‐art artificial intelligence (AI) methodologies used in aquaculture applications. As the demand for seafood continues to grow, the aquaculture industry faces numerous challenges, including disease management, feeding optimization, water quality monitoring, and extraction of aquaculture area. To address these challenges effectively and sustainably, AI techniques have been increasingly applied in aquaculture systems over recent years. This review aims to analyze various AI methodologies utilized within different aspects of aquacultural practices. By examining existing studies and identifying trends and gaps in research areas related to AI integration into aquaculture practices, this paper provides valuable insights for further advancements. The purpose was to synthesize current knowledge on application and its challenges in implementing AI technologies within the commercial aquaculture industry. Specifically, the review is to identify and analyze peer‐reviewed studies reporting on applications of AI technologies in aquaculture industry, to classify and summarize the key findings from the selected studies in aquaculture operations through AI, and to evaluate and discuss any challenges reported regarding the implementation and adoption of AI solutions in commercial aquaculture. The overall goal was to comprehensively assess these via a systematic literature review process. Challenges of AI technologies and methods were identified in the research literature for applying AI to optimize commercial aquaculture practices and production. An exhaustive search of a scholarly database from Scopus, was performed and papers published in English between 2020 and 2024 were considered for inclusion. After a rigorous screening process involving over 116 studies, 57 highly relevant works were identified and analyzed according to key themes involving demonstrated AI applications, employed methodologies and challenges that are expected when applying such methods. The findings revealed that AI‐driven tools such as computer vision, machine learning, and predictive modeling hold much potential for enhancing sustainability, efficiency, and productivity within aquaculture operations through applications like disease monitoring, environmental management, and production optimization. However, the review also uncovered substantial challenges that will continue limiting widespread adoption, including restricted access to representative data, prohibitive expenses, technical complexities, lack of social acceptance, and data privacy and security concerns. This comprehensive synthesis of the current evidence available provides an empirical foundation upon which further progress can be built by identifying priority areas requiring additional research efforts to fully address challenges on the responsible integration of suitable solutions for the commercial aquaculture industry globally.