Journal of Sustainable Urban & Regional Development Studies (JSURDS)

Abstract Background and Objective: Land use and land cover (LULC) are among the most critical indicators of human-environment interaction, reflecting how societies exploit and transform the natural landscape. Understanding temporal changes in land use is essential for sustainable planning, environmental management, and agricultural policy development. This study aims to detect and analyze land use changes in Miandoab County over the period 2013 to 2024 using remote sensing techniques.
Methodology: Landsat 8 OLI/TIRS satellite images for the years 2013 and 2024 were used as the primary data source. After applying radiometric and geometric preprocessing, the images were classified using the Maximum Likelihood Classification (MLC) algorithm, which relies on the statistical distribution of spectral data and assigns each pixel to the most probable class. Eight land use categories were defined: built-up areas, soil, roads, farmlands, orchards, water bodies, salt flats, and saline soils. The classification accuracy was assessed using overall accuracy and Kappa coefficient.
Results and Findings: The classification results revealed significant land use changes over the 11-year period. Farmlands increased from 3,183 ha in 2013 to 4,963 ha in 2024, indicating a major shift toward agricultural expansion. Conversely, orchards and soil areas showed marked decreases, likely due to water scarcity and urban encroachment. Built-up areas expanded to 1,849 ha, reflecting urban development. The classification achieved high accuracy levels (94.07% in 2013 and 94% in 2024), validating the reliability of the MLC approach. The study demonstrates that remote sensing and supervised classification are effective tools for land use monitoring. The observed trends highlight the need for integrated land management strategies to balance development with environmental sustainability in Miandoab.