This study employs a random forest model combined with interpretable machine learning techniques to analyze the habitat preferences of South Pacific albacore tuna, incorporating a broad range of marine environmental variables. Among these, several factors derived from mesoscale eddy structures, including eddy polarity, eddy radius, and eddy kinetic energy, are integrated to further enhance the characterization of mesoscale eddy features. Interpretable methods were applied to provide intuitive visualizations of albacore tuna habitat preferences, with a focus on the most influential factors, including seawater temperature, dissolved oxygen concentration, and normalized mesoscale eddy radius. Seawater temperature and oxygen concentration are directly linked to the physiological needs of albacore tuna, while mesoscale eddy characteristics influence foraging and behavior by altering water column properties. This study provides a comprehensive perspective on the characteristics of albacore tuna habitat and the mechanisms driving its oceanographic variables, providing valuable insights for developing location-based, practical science-based management strategies for fishery resources.

Tuna fish school detection provides information on the fishing decisions of purse seine fleets. Here, we present a recognition system that included fish shoal image acquisition, point extraction, point matching, and data storage. Points are a crucial characteristic for images of free-swimming tuna schools, and point algorithm analysis and point matching were studied for their applications in fish shoal recognition. The feature points were obtained by using one of the best point algorithms (scale invariant feature transform, speeded up robust features, oriented fast and rotated brief). The k-nearest neighbors (KNN) algorithm uses ‘feature similarity’ to predict the values of new points, which means that new data points will be assigned a value based on how closely they match the points that exist in the database. Finally, we tested the model, and the experimental results show that the proposed method can accurately and effectively recognize tuna free-swimming schools.