Scholarlink

<p>Urban expansion and the rapid development of highways have led to a sharp rise in private vehicle use, causing severe traffic congestion in megacities like Tehran, where drivers lose approximately 150–170&#xa0;h annually in traffic with an average congestion index of 55–60%. The city records roughly 40,000 traffic accidents yearly, including 500–600 fatalities, significantly impacting both mobility and residents’ quality of life. This study introduces a novel approach to identifying critical traffic bottlenecks in Tehran’s major highway network using big data analytics and multi-criteria decision-making methods. Over a 16-month period, researchers processed more than 100,000 images from Google traffic maps using OpenCV and machine learning algorithms to detect congestion patterns. The analysis identified and classified traffic hotspots into two categories: Level of Service (LOS) points showing persistent congestion and Safety points indicating rapid traffic flow transitions that correlate with accident data. To prioritize these hotspots, the Analytical Hierarchy Process (AHP) was applied with weights of 0.6 for LOS and 0.4 for safety, determined through consultation with 20 transportation experts. Results revealed that among the top 10 priority points, Sayad Shirazi Highway and Mohammad Ali Jenah Street received the highest scores, with a 72% correlation between identified hotspots and historical accident data. The findings provide a data-driven foundation for urban planners and policymakers to develop targeted interventions for congestion relief and safety improvement, while offering a flexible methodology applicable to other growing cities facing similar transportation challenges.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Pinpointing critical traffic hotspots in megacities: a data-driven approach using Google Maps and AHP in Tehran

  • 期刊论文

  • 发表日期：

    2025年5月27日

查看全文
  • Hamid Mirzahossein,
  • Pedram Nobakht,
  • Travis Waller,
  • Dung-Ying Lin

摘要

Urban expansion and the rapid development of highways have led to a sharp rise in private vehicle use, causing severe traffic congestion in megacities like Tehran, where drivers lose approximately 150–170 h annually in traffic with an average congestion index of 55–60%. The city records roughly 40,000 traffic accidents yearly, including 500–600 fatalities, significantly impacting both mobility and residents’ quality of life. This study introduces a novel approach to identifying critical traffic bottlenecks in Tehran’s major highway network using big data analytics and multi-criteria decision-making methods. Over a 16-month period, researchers processed more than 100,000 images from Google traffic maps using OpenCV and machine learning algorithms to detect congestion patterns. The analysis identified and classified traffic hotspots into two categories: Level of Service (LOS) points showing persistent congestion and Safety points indicating rapid traffic flow transitions that correlate with accident data. To prioritize these hotspots, the Analytical Hierarchy Process (AHP) was applied with weights of 0.6 for LOS and 0.4 for safety, determined through consultation with 20 transportation experts. Results revealed that among the top 10 priority points, Sayad Shirazi Highway and Mohammad Ali Jenah Street received the highest scores, with a 72% correlation between identified hotspots and historical accident data. The findings provide a data-driven foundation for urban planners and policymakers to develop targeted interventions for congestion relief and safety improvement, while offering a flexible methodology applicable to other growing cities facing similar transportation challenges.