<p>This study presents a hybrid optimization framework for designing resilient and robust food supply chains under uncertainty. The proposed methodology integrates the Multi-Objective Whale Optimization Algorithm (MOWOA) with machine learning techniques to optimize cost-efficiency and service levels while addressing disruptions and demand variability. Robust optimization is incorporated to handle uncertainties, ensuring adaptability and reliability in dynamic environments. A K-means clustering algorithm is used as the machine learning component, which enhances the MOWOA by promoting exploration in underrepresented regions of the solution space, guiding exploitation toward high-quality clusters, and accelerating convergence through dynamic clustering. The hybrid approach is evaluated through numerical experiments, demonstrating superior performance in terms of hypervolume, spread, and execution time compared to MOWOA, NSGA-II, and Augmented Epsilon Constraint-II methods. Results highlight the model’s ability to deliver high-quality Pareto fronts and computational efficiency, making it suitable for large-scale and complex supply chain problems. The findings validate the effectiveness of integrating machine learning with meta-heuristics, providing a robust framework for optimizing resilient food supply chains.</p>