Smart Transportation System: Evaluating the Effectiveness of Smart Transportation Systems in Reducing Congestion and Emissions in Kaduna Metropolis, Nigeria

Abstract

Urban transportation in Nigeria faces critical challenges of traffic congestion and rising emissions, which undermine economic productivity, environmental health, and urban livability. This study explores the potential and the actual use of smart transportation technologies, including Internet of Things (IoT), Machine Learning (ML), and Geographic Information Systems (GIS), to mitigate these challenges, with a specific focus on Kaduna Metropolis. A comparative case study approach is employed, using Lagos and Enugu as benchmarks for both established and emerging smart mobility interventions. Data were drawn from traffic volume counts, Peak Hour Factor (PHF) analysis, pollution metrics, and a comprehensive review of peer-reviewed studies. GIS mapping visualized congestion hotspots, while a proposed ML model demonstrates the potential for real-time traffic prediction. Results indicate that Kaduna metropolis experiences severe traffic congestion, with an average PHF of 0.78 and CO2 concentrations exceeding World Health Organization (WHO) safety thresholds. Lagos shows moderate improvements through initiatives such as Bus Rapid Transit (BRT) and ride-hailing platforms, while Enugu faces episodic traffic congestion due to socio-political disruptions. Based on these findings, the study proposes a context-specific smart transportation framework for Kaduna, integrating IoT-enabled traffic sensors, ML-driven analytics, and GIS-based spatial planning. The findings have broader implications for urban transport policy, infrastructure development, and sustainable mobility strategies in Nigerian cities and comparable urban contexts across Africa.