This study aims to develop a comprehensive optimization framework for seafood supply chains that simultaneously addresses economic, environmental, social and risk-resilience objectives. The goal is to provide a decision-support tool that enhances sustainability, transparency and operational robustness.
A multi-objective mathematical model is proposed for a four-tier seafood supply chain that incorporates forward and reverse logistics. The model integrates blockchain for traceability, machine learning (ML) for demand forecasting and circular economy principles for resource recovery. It is solved using three metaheuristic algorithms, NSGA-II, MOPSO and MOEA-D. Performance is assessed using criteria such as optimality gap, Pareto spread, time efficiency and solution diversity.
MOEA-D consistently outperformed NSGA-II and MOPSO, particularly in large-scale scenarios, by offering better balance among conflicting objectives and superior solution diversity. The model effectively reduces costs and emissions, improves customer satisfaction, enhances job creation in underdeveloped regions and mitigates supply chain risks. Sensitivity analyses confirm the model’s robustness across varying demand levels.
To the best of the authors’ knowledge, this is among the first studies to jointly integrate blockchain, ML and circular economy strategies into a unified multi-objective model for seafood supply chains. The framework advances academic discourse and provides managers with a scalable tool aligned with Sustainable Development Goals (SDGs), particularly SDG 8, SDG 9 and SDG 12.
