Document Type : Original Research Paper
Authors
Faculty of Civil, Water and Environmental Engineering, Shahid Beheshti University, Tehran, Iran
Abstract
The rapid urbanization and expansion of settlements in recent decades have increased the necessity of monitoring land-use changes through remote sensing technologies in urban planning. As one of Iran’s new towns, Parand City has experienced remarkable physical growth over the past two decades. The main objective of this study is to analyze land-use changes and evaluate the spatial pattern of Parand’s urban development with an emphasis on the expansion of built-up areas. For this purpose, Landsat-7 imagery from 2000 and Sentinel-2 imagery from 2024, along with Sentinel-1 radar data, were processed and classified in the cloud-based Google Earth Engine platform. The Random Forest algorithm was applied for land-use classification, and accuracy assessment was performed using an error matrix and the Kappa coefficient. Results showed that the built-up area increased more than fourfold during the study period, mainly concentrated in the eastern and southern parts of the city. The significant reduction of barren lands indicates the conversion of these areas into urban zones. The 2024 classification map achieved higher accuracy (95.97%) compared to 2000 (89.06%), due to higher resolution and the fusion of optical and radar data. Overall, integrating multi-source remote sensing datasets with machine learning algorithms proved to be an effective and repeatable approach for urban monitoring and can support sustainable land-use management and urban planning.
Main Subjects
)