Scholarlink

<p>The rapid expansion of urban centers due to population growth has altered Land Use/Land Cover (LULC), raising environmental concerns. This study examined and forecasted the changes in LULC patterns, utilizing multi-temporal Landsat images of 1995, 2010, and 2025. The pre-processing and analysis of images were performed through Google Earth Engine and ArcGIS 10.8. Image pre-processing and analysis were conducted using Google Earth Engine and ArcGIS 10.8, where three machine learning classifiers: Classification and Regression Trees (CART), Random Forest (RF), and Support Vector Machines (SVM), were applied to classify six LULC classes. Classification accuracy was assessed using overall accuracy, producer’s and user’s accuracy, and the Kappa coefficient, while the LULC changes (1995-2025) were detected using post-classification comparison.Future LULC for 2055 was projected by integrating historical changes (1995–2025) with machine learning classifiers, implemented in Google Earth Engine using multi-temporal satellite data and environmental drivers. The results indicate that the built-up area increased by approximately 25–26% between 1995 and 2025, agricultural land decreased by 43.5%, and vegetation cover decreased by 5.3%. Among the classifiers, the highest accuracy of 93.5% was achieved with the Random Forest algorithm, indicating that the built-up area may cover approximately 53% of the total area in 2055, replacing agricultural land. The results have significant implications for highlighting the need to develop a sustainable city and to conserve agricultural land and vegetation cover in the peri-urban area.</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

Modeling urban land use and land cover change using multiple machine learning algorithms in central Ethiopian cities

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月2日

查看全文
  • Gedefa Adugna Tamene,
  • Mitiku Badasa Moisa,
  • Debelo Negeri Begna,
  • Fedhasa Benti Chalchissa,
  • Zenebe Reta Roba,
  • Harison Kiplagat Kipkulei,
  • Kiros Tsegay Deribew,
  • Mengistu Muleta Gurmessa,
  • Habtamu Tolera,
  • Mehmet Ali Celik,
  • Indale Niguse Dejene,
  • Dessalegn Obsi Gemeda

摘要

The rapid expansion of urban centers due to population growth has altered Land Use/Land Cover (LULC), raising environmental concerns. This study examined and forecasted the changes in LULC patterns, utilizing multi-temporal Landsat images of 1995, 2010, and 2025. The pre-processing and analysis of images were performed through Google Earth Engine and ArcGIS 10.8. Image pre-processing and analysis were conducted using Google Earth Engine and ArcGIS 10.8, where three machine learning classifiers: Classification and Regression Trees (CART), Random Forest (RF), and Support Vector Machines (SVM), were applied to classify six LULC classes. Classification accuracy was assessed using overall accuracy, producer’s and user’s accuracy, and the Kappa coefficient, while the LULC changes (1995-2025) were detected using post-classification comparison.Future LULC for 2055 was projected by integrating historical changes (1995–2025) with machine learning classifiers, implemented in Google Earth Engine using multi-temporal satellite data and environmental drivers. The results indicate that the built-up area increased by approximately 25–26% between 1995 and 2025, agricultural land decreased by 43.5%, and vegetation cover decreased by 5.3%. Among the classifiers, the highest accuracy of 93.5% was achieved with the Random Forest algorithm, indicating that the built-up area may cover approximately 53% of the total area in 2055, replacing agricultural land. The results have significant implications for highlighting the need to develop a sustainable city and to conserve agricultural land and vegetation cover in the peri-urban area.