Liang Chen , Rudi Mai

Tropical Marine Fisheries Research Center, Hainan Institute of Tropical Agricultural Resources, Sanya, 572025, Hainan, China
Author    Correspondence author
International Journal of Marine Science, 2026, Vol. 16, No. 4   
Received: 25 Jun., 2026    Accepted: 31 Jul., 2026    Published: 12 Aug., 2026

This is an open access article published under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

The rapid expansion of aquaculture production has increased the demand for efficient approaches to optimize growth performance and feeding management. Computational analysis provides powerful tools for understanding complex interactions among biological traits, nutritional factors, and environmental conditions in cultured aquatic species. This review summarizes recent advances in mathematical modeling, statistical analysis, machine learning, and artificial intelligence applications for evaluating growth dynamics and feeding efficiency in aquaculture systems. Key production indicators, including weight gain, specific growth rate, feed conversion ratio, and nutrient utilization efficiency, are analyzed through computational frameworks integrating feeding records, environmental monitoring, and physiological responses. Growth prediction models, nonlinear growth simulations, and machine learning algorithms are discussed for their ability to identify critical factors affecting production outcomes and improve management decisions. A case study of Pacific white shrimp (Litopenaeus vannamei) demonstrates the application of computational models in predicting growth performance and optimizing feeding strategies under different culture conditions. Furthermore, the integration of computational technologies with IoT-based monitoring and precision aquaculture systems provides new opportunities for reducing feed waste, enhancing production efficiency, and promoting sustainable aquaculture development. Future research should focus on developing more accurate, interpretable, and adaptive models that integrate multi-source biological and environmental data.

Computational analysis; Aquaculture species; Growth performance; Feeding efficiency; Machine learning models