Purpose Studying land-use change represents a core dimension in urban morphology and planning research. The purpose of this study is to present a synthesised multi-scale workflow for the land use and land cover (LULC) change in Cairo, Egypt, as a case study. Our investigation utilised multi-scale levels to cover the city scale, pixel/local entropy scale, and administrative neighbourhood scale. We aim to support a deeper understanding of urban transformation processes and provide spatial evidence for decision-makers and researchers in cities of the Global South. Design/methodology/approach We examined LULC change in Cairo between 2014 and 2024 using multi-temporal Landsat 8 imagery processed in Google Earth Engine and classified with a Random Forest algorithm. Four urban land-use classes were analysed, including water surfaces, vegetation, built-up areas, and bare land. Classification performance was evaluated using conventional random sampling and spatial cross-validation to address spatial autocorrelation. Post-classification analysis in ArcGIS Pro included transition matrices, percentage change analysis, and Shannon’s entropy to assess spatial heterogeneity, land-use mixing, and urban expansion patterns. Findings The results reveal a clear pattern of rapid urban expansion in Cairo, primarily driven by the conversion of bare land and the gradual reduction of vegetation areas. While water surfaces remained largely stable, the land-use structure shifted in 2024 toward greater dominance of built-up areas than in 2014. Spatial heterogeneity analysis indicates a decline in land-use diversity and an increase in spatial consolidation within the urban form, with localised heterogeneity emerging along desert-edge expansion zones and in transitional landscapes. Originality/value This study presents a transferable, multi-scale analytical workflow, a structured synthesis of existing methods that integrates machine learning, change detection, and spatial heterogeneity metrics to systematically assess urban transformation. This workflow supports mapping LULC changes to guide decision-makers and urban design and planning researchers. It provides evidence-based insights into spatial change processes in rapidly urbanising cities.
Abdelkhalik et al. (Sat,) studied this question.