Abstract
Urban land degradation poses a growing challenge in rapidly developing countries like Indonesia, where population growth and limited space drive uncontrolled land cover changes. This study detects urban land degradation through spatial modelling and semi-automatic classification of multi-temporal remote sensing imagery. Landsat-5 TM (2011) and Landsat-9 OLI-2 (2023) were used with preprocessing, band stacking, subsetting, and enhancement.
Supervised classification mapped seven land-cover classes: agricultural dry land, rice field, forest, plantation, non-agricultural land, water body, and settlement. Change detection showed a 1664.65 ha increase in industrial areas, with large decreases in rice fields (-1726.92 ha) and dry farmland (-1644.57 ha).
Classification accuracy reached 80.24% and 75.11% with kappa coefficients of 0.76 and 0.65. Results indicate urban expansion as a major driver of land degradation, and support remote sensing-based monitoring for sustainable land-use planning.