AI-driven analysis of fish reproductive behaviour

Understanding animal behaviour is essential for wildlife management and conservation. However, studying the intricate behaviours of marine fish presents unique challenges, including their mobility, size, and the difficulty of maintaining continuous visibility in dynamic underwater environments. Traditional methods, such as manual video analysis and direct observation, are time-consuming, labor-intensive, and often limited in scope. While AI has been applied to aquaculture and species identification, its use in decoding complex mating behaviours of wild fish—particularly nest-building species like the grey wrasse ( Symphodus cinereus )—remains underexplored. This study bridges this gap by leveraging advancements in Artificial Intelligence (AI) and computer vision to automate the analysis of S. cinereus reproductive behaviours. By labelling image datasets and using the YOLOv9 algorithm, we developed a robust system to detect nest maintenance, courtship, egg care, and territorial defence behaviours during mating seasons. Observations revealed intricate male behavioural patterns, including nest building, courtship displays, and parental care, with high detection accuracy for key objects (e.g., nests, females) and varied performance across behaviour categories. Our work highlights the potential of AI-driven tools to overcome the constraints of manual methods, providing scalable, precise methodologies for ethological research. Beyond S. cinereus , this framework can be adapted to study other nest-building fish (e.g., damselfish, cichlids), supporting conservation efforts through large-scale behavioural monitoring and guiding sustainable ecotourism practices. By integrating AI and behavioural ecology, this study advances both scientific understanding and practical applications for marine ecosystem management. • AI-based system detects complex mating behaviours in Symphodus cinereus. • YOLOv9 used to classify courtship, nest care, and territorial defence. • High accuracy in identifying key behavioural patterns and objects. • Method reduces effort and bias of manual ethological video analysis. • Scalable approach applicable to other nest-building fish species.