Decarbonization pathways in transportation systems

The transportation sector represents a major source of greenhouse gas (GHG) emissions, presenting critical challenges to both local environmental health and global climate change mitigation objectives. This research aims to analyze decarbonization pathways and forecast carbon emissions in the transportation sector through a case study of a logistics company operating in a developing country context. Based on real operational data, we evaluate current emission levels and identify key determinants driving emissions across various regions and truck types. This research employs advanced machine learning (ML) algorithms to model and predict future emissions, enabling a comparative analysis across geographical areas and vehicle categories. Furthermore, this research integrated a scenario-based projection of carbon emissions for the year 2030, which allows for a forward-looking analysis of regional and vehicle-specific emission trends under business conditions. The results offer insights into the emission strategies of different transportation practices and their alignment with national and international reduction targets. Therefore, this study highlights the need for context-specific, data-driven decarbonization strategies in transportation systems and proposes actionable recommendations for policymakers, logistics companies, and stakeholders. Consequently, this research contributes to the advancement of sustainable transportation management and demonstrates the potential of artificial intelligence (AI) in supporting effective environmental policy and climate resilience planning. Ultimately, the findings serve both global and local agendas by enhancing transport emission control while promoting sustainable logistics operations.