YOLO in precision aquaculture: A decadal bibliometric and systematic review of applications, architectural adaptations, and deployment challenges

Authors: RANJAN, RAKESH - Freshwater Institute

Submitted to: Journal of Agriculture and Food Research
Publication Type: Review Article
Publication Acceptance Date: 5/6/2026
Publication Date: 5/13/2026
Citation: Ranjan, R. 2026. YOLO in precision aquaculture: A decadal bibliometric and systematic review of applications, architectural adaptations, and deployment challenges. Journal of Agriculture and Food Research. 28. Article 102982. https://doi.org/10.1016/j.jafr.2026.102982.
DOI: https://doi.org/10.1016/j.jafr.2026.102982

Interpretive Summary: Scientists are using artificial intelligence (AI) and computer vision to improve fish farming. A popular AI model, called YOLO, can quickly detect and track objects in real time. In this review, researchers analyzed over 200 studies to see how YOLO is applied and improved in aquaculture for tasks like monitoring fish behavior, checking health, counting fish, and managing feeding. The review highlights the progress so far and the challenges that still need to be solved for smarter, more efficient fish farming in the future.

Technical Abstract: Computer vision and artificial intelligence technologies have been increasingly adopted in aquaculture in recent years. Among the various convolutional neural network (CNN) frameworks investigated for these applications, You Only Look Once (YOLO) models have gained prominence for the balance between detection performance and inference speed, which is critical for real-time decision support. This study critically evaluates and documents the applications and domain-specific advances of the YOLO architecture adopted in aquaculture through a comprehensive bibliometric and systematic literature review. An extensive search of the Scopus database using relevant keywords yielded 201 documents related to this topic. After screening the dataset based on language and article type, 181 documents were selected for bibliometric analysis to examine research trends through publication patterns, citation frequencies, and keyword relationships. A further set of specific exclusion criteria was applied to these databases, resulting in 50 documents selected for a comprehensive review. Aquaculture applications ranging from animal detection and tracking to health assessment, behavior monitoring, precision feeding, biomass monitoring, and system inspection were identified, and YOLO adaptations with domain-specific improvements to address aquaculture-specific challenges were systematically reviewed. Optimization of YOLO’s backbone, neck, and prediction layers through architectural refinements such as attention mechanism integration, lightweight backbones, redesigned loss functions, and transformer modules reportedly improved detection accuracy and adaptability for real-time decision support in aquaculture. The presented review also highlights the key technological gaps in model training, validation, testing, and deployment, and lays a scientific groundwork for future investigations to promote the application of cutting-edge computer vision toward smarter aquaculture management.