Document Type : Original Article
Authors
1 PhD in Geography and Urban Planning, Larestan Branch, Islamic Azad University, Larestan, Iran.
2 Associate Professor, Department of Geography, Larestan Branch, Islamic Azad University, Larestan, Iran.
3 Assistant Professor, Department of Geography, Larestan Branch, Islamic Azad University, Larestan, Iran.
Abstract
The rapid expansion of cities in Iran, particularly in metropolitan areas such as Shiraz, has had profound impacts on land use, the environment, and spatial planning. This study aims to analyze the physical expansion of Shiraz between 1999 and 2025, utilizing the Landscape Expansion Index (LEI) and a set of landscape metrics (CA, ND, NT, LPI, ED, LSI). Land use data were derived and processed from multi-temporal Landsat satellite imagery in a GIS environment using remote sensing techniques. The LEI results indicate that edge-expansion has been the dominant pattern of urban growth in Shiraz, covering approximately 138.374 square kilometers, which accounts for more than 99% of the total expansion. In contrast, infilling accounted for only 0.1667 square kilometers and outlying expansion for about 0.1005 square kilometers, both primarily observed on distant urban fringes. Landscape metrics analysis revealed that, over this period, urban land area increased from about 72.5 million square meters to over 146 million square meters; agricultural land declined from 79 million square meters to less than 4 million square meters, and natural lands decreased from 41 million square meters to around 11 million square meters. Furthermore, the urban Largest Patch Index (LPI) reached 100%, indicating complete consolidation of urban patches and the elimination of former spatial fragmentation. To enhance the accuracy of results, a machine learning (ML) approach was employed using Random Forest and Support Vector Machine (SVM) algorithms, with land use classifications validated through a confusion matrix.
Keywords
Main Subjects