AI in Public Transport Optimization for Emerging Egyptian Cities

Abstract

Purpose: This paper investigates how Artificial Intelligence (AI) can optimize public transport in the New Administrative Capital (NAC) in Egypt to improve sustainable urban mobility, with reflections on applicability in new cities across the MENA region. The study emphasizes the AI applications in the optimization of public transportation, including dynamic bus scheduling, route optimization, demand-responsive transit (DRT), and multimodal integration with the Light Rail Transit (LRT) and monorail. Methodology: This paper employs a quantitative, scenario-based methodology using microsimulation to utilize anticipated NAC transport information, simulation models, and benchmarks from international cases. Three scenarios were examined: (1) baseline fixed routes, (2) AI-enhanced dynamic scheduling and routing, and (3) AI-integrated DRT coupled with LRT and monorail. The evaluation criteria encompassed efficiency metrics (waiting time), accessibility indicators, and sustainability measures (CO₂ reduction). Results: This paper illustrates that AI-driven optimization can decrease waiting times by 50%, increase accessibility by 27%, and lower emissions by 23% relative to the baseline. These results are similar to what has been implemented in Singapore, Shenzhen, and Helsinki. The results also fit with the concepts about mobility in emerging smart cities in MENA region, such as NEOM and Masdar City, where AI is a key part of sustainable urban planning. Originality: This paper systematically evaluates AI-driven public transport optimization in Egypt and offers insights that are applicable to other emerging cities in the MENA region. It shows how NAC can be a model for the area in helping to create sustainable urban mobility plans that fit with the SDGs.