Assessing Urban Freight Tours: A Machine Learning and Life Cycle Sustainability Assessment Approach for Logistics Management

The main aim of this study is to assess urban freight tours through integrating machine learning with the Life Cycle Sustainability Assessment (LCSA). The research captures supply chain operations using the Gradient Boosting Regressor (GBR) model with real‐time data from surveys and Global Positioning System (GPS) tracking. These predictions were analysed using LCSA to assess the sustainability impacts of Hydrogen Fuel Light Commercial Vehicles (HFLCVs) and Electric Light Commercial Vehicles (ELCVs) compared to traditional fuel‐based vehicles. HFLCVs show remarkable reductions in ecosystem and health damage by 58% and 61%, indicating substantial environmental and health benefits. Findings suggest that strategic investment in hydrogen‐fuel and electric LCVs can significantly decrease operational costs and environmental impacts, making them crucial for advancing sustainable urban logistics. This research highlights the benefits and possibilities of using an integrated data‐driven approach to achieve urban sustainability, thus creating an urgency to shift policies favouring green urban freight systems.