Learning-based hybrid optimization for circular E-waste supply chains under uncertainty

The rapid growth of electronic waste and increasing pressure to adopt circular-economy practices challenge conventional supply-chain design, particularly under uncertain demand, return flows, recovery yields, and technology performance. This study develops a Circular, Sustainable, and Resilient Supply Chain (CSRSC) framework for e-waste management using a multi-objective mixed-integer programming model (MOMIP) that minimizes total cost and environmental impact while maximizing social benefits. The conceptual contribution lies in integrating circular-economy strategies, Clean Technology adoption, social sustainability, and resilience mechanisms within a unified closed-loop network design under uncertainty. Circular-economy principles are operationalized through closed-loop product and material flows, refurbishment, recycling, and clean-technology selection, while resilience is represented through capacity flexibility, reserve capacity, and scenario-responsive operational decisions. Uncertainty in demand, e-waste returns, processing yields, operating costs, and Clean Technology performance is addressed through a risk-weighted robust scenario-based stochastic formulation with pessimistic, most-likely, and optimistic scenarios. The technical contribution is the development of a learning-based hybrid multi-objective metaheuristic solution approach for efficiently generating high-quality Pareto solutions for large-scale instances, while the augmented \\(\\varepsilon\\) -constraint method is used as a benchmark for smaller instances. An anonymized case study from the Iranian electronics industry demonstrates the applicability of the proposed framework. The results show that the proposed method achieves a median normalized IGD + of 0.0086 and a median hypervolume of 0.814 under an equal exact-evaluation budget, reducing median IGD + by 60.6% relative to standard NSGA-II while maintaining competitive computational time. The findings provide managerial insights into facility configuration, capacity flexibility, Clean Technology investment, and circular recovery planning under uncertain operating conditions.