Climate change remains one of the greatest challenges facing humanity, with greenhouse gas emissions playing a critical role in global warming. The maritime sector is a significant contributor to these emissions, underscoring the need for innovative reduction strategies. This paper presents a multiobjective optimization framework for vessel emissions control, which leverages vessel operational and environmental data to enhance emission prediction. Using the Non-Dominated Sorting Genetic Algorithm (NSGA-II), we identify trade-offs between minimizing CO \(_2\) emissions and maintaining vessel maneuverability. To improve the interpretability of the optimization results, we integrate SHapley Additive exPlanations (SHAP), providing deeper insights into how propulsion parameters influence emissions. We detail the methodology, dataset characteristics, feature engineering techniques, and model evaluation metrics. Computational experiments demonstrate the efficacy and efficiency of the proposed approach.