Scholarlink

<p>The pedestrian volume, a critical indicator of urban vitality, has been broadly investigated in urban streets, particularly in China. However, how the street environment impacts the pedestrian volume has not received much attention in current Chinese cities. This study has adopted a machine learning model of LightGBM to test the association between 22 typical street environmental factors (spatial elements &amp; spatial proximity) and the pedestrian volume (two models: the average value &amp; the distance weighted value), and the SHAP approach to interpret and visualize the results achieved using the model. Guangzhou, a mega city in southern China, was chosen as the location studied. Key findings achieved are as follows: 1) Several environmental factors, particularly the density of commercial points of interest (POIs) and functional density, could significantly affect the average pedestrian volume. While most paired environmental factors may also produce important interaction effects, the strongest one was specifically observed between commercial and transportation POIs. 2) The distance-weighted pedestrian volume was significantly impacted by all 22 environmental factors, with commercial POIs having the highest impact. Furthermore, although most paired environmental factors had significant interaction effects, these effects were generally small. 3) Most paired environmental factors had significant interaction effects on both average and distance-weighted pedestrian volumes. However, the size of these effects was smaller relative to their main effects.</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

Investigating the association between street environmental factors and pedestrian volume in a southern Chinese city: a machine learning based analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月6日

查看全文
  • Jilong Li,
  • Shiping Lin,
  • Jiangtao Du

摘要

The pedestrian volume, a critical indicator of urban vitality, has been broadly investigated in urban streets, particularly in China. However, how the street environment impacts the pedestrian volume has not received much attention in current Chinese cities. This study has adopted a machine learning model of LightGBM to test the association between 22 typical street environmental factors (spatial elements & spatial proximity) and the pedestrian volume (two models: the average value & the distance weighted value), and the SHAP approach to interpret and visualize the results achieved using the model. Guangzhou, a mega city in southern China, was chosen as the location studied. Key findings achieved are as follows: 1) Several environmental factors, particularly the density of commercial points of interest (POIs) and functional density, could significantly affect the average pedestrian volume. While most paired environmental factors may also produce important interaction effects, the strongest one was specifically observed between commercial and transportation POIs. 2) The distance-weighted pedestrian volume was significantly impacted by all 22 environmental factors, with commercial POIs having the highest impact. Furthermore, although most paired environmental factors had significant interaction effects, these effects were generally small. 3) Most paired environmental factors had significant interaction effects on both average and distance-weighted pedestrian volumes. However, the size of these effects was smaller relative to their main effects.