Search for: All records

Abstract Urban mobility is a critical contributor to greenhouse gas emissions, accounting for over 30% of urban carbon emissions in the United States in 2021. Addressing this challenge requires a comprehensive and data-driven approach to transform transportation systems into sustainable networks. This paper presents an integrated framework that leverages artificial intelligence (AI), machine learning (ML), and life cycle assessment (LCA) to analyze, model, and optimize urban mobility. The framework consists of four key components: AI-powered analysis and models, synthetic urban mobility data generation, LCA for environmental footprint analysis, and data-driven policy interventions. By combining these elements, the framework not only deciphers complex mobility patterns but also quantifies their environmental impacts, providing actionable insights for policy decisions aimed at reducing carbon emissions and promoting sustainable urban transportation. The implications of this approach extend beyond individual cities, offering a blueprint for global sustainable urban mobility.