Artificial Intelligence and Machine Learning in Smart Transportation Systems: Improving Road Safety, Traffic Flow, and Environmental Sustainability

Abstract

The study examined the transformative role of Artificial Intelligence (AI) and Machine Learning (ML) in advancing smart transportation systems with a focus on improving road safety, optimizing traffic flow, and promoting environmental sustainability. Using a mixed-method research design, the study integrated quantitative data from transportation authorities and simulation outputs with qualitative insights from AI and traffic management experts. The analysis demonstrated that AI-driven models significantly enhanced traffic prediction accuracy, reduced accident frequency, and optimized route management through real-time analytics and adaptive control mechanisms. Results also indicated that ML-based systems contributed to lower carbon emissions by enabling fuel-efficient driving patterns and reducing idle times at intersections. However, the study identified ongoing challenges, including data privacy concerns, lack of standardized regulatory frameworks, and limited public trust in AI-based decision-making. The discussion emphasized that sustainable implementation required collaborative governance, ethical design, and policy integration. The findings concluded that AI and ML could fundamentally redefine urban mobility when combined with robust data governance and continuous monitoring. Future research directions were proposed to explore explainable AI, edge-based optimization, and multi-modal integration for enhanced system resilience and transparency. This study contributed to the growing body of literature emphasizing data-driven, sustainable, and human-centered approaches to intelligent transportation systems.