Scholarlink

<p>Human mobility, exemplified by low-speed transportation, profoundly influences urban economics, vibrancy, and progression. With the enlarging climate change impact, a detailed exploration of the interplay between low-speed transportation and environmental elements is crucial yet seldom investigated spatially. Harnessing high-resolution origin–destination (OD) data with both spatial and temporal granularity, we construct an exceptionally precise predictive model with 88.29% accuracy. This model unravels the relationship leveraging environmental data from satellite data between January 2019 and December 2020. This study pioneers the use of Shapley additive explanation and geographically weighted panel regression to interpret extreme gradient boosting findings and spatial variability in OD data. Our analysis reveals an intriguing dichotomy: urban areas experience a decline in low-speed transportation with rising temperatures, while a positive correlation surfaces in rural regions. On average, a 1°C increase in temperature correlates to a significant reduction of 466,851 person time in low-speed transportation in Tokyo, Japan. We also identify that other environmental factors, including air pressure, wind speed, and so on, exert spatially varying impacts on low-speed transportation. Altogether, this study furnishes robust empirical evidence of the environmental effects on human mobility, presenting valuable insights for academics, policymakers, and society at large.</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

Human mobility and environmental factors

  • 期刊论文

  • 发表日期：

    2025年4月21日

查看全文
  • Chao Li,
  • Alexander Ryota Keeley,
  • Shunsuke Managi

摘要

Human mobility, exemplified by low-speed transportation, profoundly influences urban economics, vibrancy, and progression. With the enlarging climate change impact, a detailed exploration of the interplay between low-speed transportation and environmental elements is crucial yet seldom investigated spatially. Harnessing high-resolution origin–destination (OD) data with both spatial and temporal granularity, we construct an exceptionally precise predictive model with 88.29% accuracy. This model unravels the relationship leveraging environmental data from satellite data between January 2019 and December 2020. This study pioneers the use of Shapley additive explanation and geographically weighted panel regression to interpret extreme gradient boosting findings and spatial variability in OD data. Our analysis reveals an intriguing dichotomy: urban areas experience a decline in low-speed transportation with rising temperatures, while a positive correlation surfaces in rural regions. On average, a 1°C increase in temperature correlates to a significant reduction of 466,851 person time in low-speed transportation in Tokyo, Japan. We also identify that other environmental factors, including air pressure, wind speed, and so on, exert spatially varying impacts on low-speed transportation. Altogether, this study furnishes robust empirical evidence of the environmental effects on human mobility, presenting valuable insights for academics, policymakers, and society at large.