Artificial Intelligence for Energy and Cost Resilience in Sustainable Supply Chains: A Dynamic LCA/TCO Approach to Multimodal Transport

The decarbonization of multimodal transport systems requires assessment approaches that simultaneously address environmental impacts and economic performance at dynamic operational conditions. Conventional Life Cycle Assessment (LCA) and Life Cycle Costing (LCC), including Total Cost of Ownership (TCO), are widely used for this purpose; however, they often rely on static assumptions and averaged data, limiting their ability to capture real-world variability. This study proposes an AI-enhanced LCA–LCC/TCO framework for the integrated evaluation of decarbonised multimodal Door-to-Port transport systems. Artificial intelligence is embedded directly into the life cycle inventory and cost inventory stages to generate scenario-specific estimates of energy consumption, greenhouse gas emissions, and operational costs. The framework is demonstrated through a case study of a multimodal Door-to-Port transport chain comprising road pre-haulage, rail line-haul, and port terminal operations. Three scenarios are analysed: conventional, partially decarbonised, and fully decarbonised configurations. The results indicate that partial decarbonization reduces greenhouse gas emissions by more than 60% compared to the baseline while achieving the lowest total cost of ownership. Full decarbonization achieves emission reductions exceeding 95% but is associated with slightly higher costs under current assumptions. Sensitivity analysis verifies the robustness of the relative scenario ranking under different energy prices, carbon pricing, and electricity carbon intensity. The proposed framework provides a structured decision-support framework for logistics operators, port authorities, and policymakers seeking cost-effective pathways to low-emission multimodal transport systems.