Optimizing Urban Traffic Management with Artificial Intelligence. A Case Study of Kitwe, Zambia for Enhanced Climate Resilience

Main Article Content

Trevor Muluta
Jameson Mbale

Abstract

Zambia's Road Transport and Safety Agency (RTSA) reports a significant rise in active vehicles, reaching 695,740, which has exacerbated traffic control challenges as of July 2024. Traditional traffic management systems, reliant on fixed schedules, struggle to adapt to dynamic traffic conditions, leading to increased congestion, prolonged travel times, higher CO2, CO emissions, and inefficiencies in human-managed intersections. This study explores the application of Artificial Intelligence to optimize traffic light control in Kitwe, Copperbelt Province, aiming to mitigate congestion and reduce carbon emissions. By employing advanced Artificial Intelligence techniques such as machine learning and reinforcement learning, traffic light systems can dynamically adjust to real-time traffic patterns, thereby improving signal timings and overall traffic flow. Our research includes a comprehensive review of Artificial Intelligence driven traffic management systems globally, evaluating their benefits and challenges. Preliminary simulations and test scenarios in Kitwe suggest that Artificial Intelligence enhanced traffic control can significantly reduce wait times at intersections and lower vehicle emissions, thereby contributing to more efficient urban transportation. The findings highlight the potential for Artificial Intelligence to transform traffic management in Zambia, suggesting further research and pilot projects to address technical, infrastructural, and regulatory challenges and fully realize Artificial Intelligence benefits for sustainable urban mobility.

Article Details

How to Cite
Muluta , T., & Mbale, J. (2025). Optimizing Urban Traffic Management with Artificial Intelligence. A Case Study of Kitwe, Zambia for Enhanced Climate Resilience. Proceedings of International Conference for ICT (ICICT) - Zambia, 6(1), 63–67. Retrieved from https://ictjournal.icict.org.zm/index.php/icict/article/view/351
Section
Articles