Navigating the profitability-emissions trade-off in green intermodal transport planning

This study presents a bi-objective model for intermodal transportation that minimises CO2 emissions while maximising logistics profitability, incorporating government financial incentives. The model is applied to real-world data from an international logistics provider in Turkey’s Aegean region, focusing on demand allocation and transportation mode selection to balance economic and environmental objectives in intermodal transport planning. A Dynamic Epsilon-Greedy Selection-based Hyper-Heuristic (DEG_HH) algorithm is proposed to enhance predefined initial solutions through adaptive heuristic selection. The framework is rigorously evaluated using key performance metrics, demonstrating that DEG_HH outperforms traditional optimisation algorithms in both solution quality and adaptability, making it well-suited for evolving logistics challenges. This study represents the first application of a hyper-heuristic framework in green intermodal transportation planning, providing valuable insights for policymakers and practitioners. It also lays the groundwork for future research on hybrid approaches, machine learning, and real-time data adaptation to enhance the sustainability of global logistics.