Scholarlink

<p>This study examines the impact of industrialization on urbanization in Istanbul using remote sensing and statistical analysis. Spatio-temporal data from IKONOS (2007) and Orthophoto (2017) images were analyzed using the Support Vector Machine (SVM) classification method, achieving accuracies of 87% (Kappa 0.85) and 88% (Kappa 0.86), respectively. Additionally, industry registry, administrative divisions, road and numbering data, and topographic contours were incorporated into the analysis. Ordinary Least Squares (OLS) regression analyzed the relationship between industrialization and urbanization. The results indicate that while the coefficient for industrialization decreased from 11.02 in 2007 to 8.73 in 2017, the relationship remained statistically significant in both years. Robust standard errors, t-values (50.39 for 2007, 53.35 for 2017), and p-values (0.001) confirmed the reliability and significance of the findings. This study highlights the importance of combining remote sensing, SVM classification, and OLS regression to analyze the relationship between industrialization and urbanization, providing valuable insights for urban planning in rapidly industrializing cities.</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

Testing the effects of industrialization on urbanization: RS and OLS insights

  • 期刊论文

  • 发表日期：

    2025年6月16日

查看全文
  • Gülcan Sarp,
  • Kadir Temurçin,
  • Yolcu Aldırmaz

摘要

This study examines the impact of industrialization on urbanization in Istanbul using remote sensing and statistical analysis. Spatio-temporal data from IKONOS (2007) and Orthophoto (2017) images were analyzed using the Support Vector Machine (SVM) classification method, achieving accuracies of 87% (Kappa 0.85) and 88% (Kappa 0.86), respectively. Additionally, industry registry, administrative divisions, road and numbering data, and topographic contours were incorporated into the analysis. Ordinary Least Squares (OLS) regression analyzed the relationship between industrialization and urbanization. The results indicate that while the coefficient for industrialization decreased from 11.02 in 2007 to 8.73 in 2017, the relationship remained statistically significant in both years. Robust standard errors, t-values (50.39 for 2007, 53.35 for 2017), and p-values (0.001) confirmed the reliability and significance of the findings. This study highlights the importance of combining remote sensing, SVM classification, and OLS regression to analyze the relationship between industrialization and urbanization, providing valuable insights for urban planning in rapidly industrializing cities.