REMOTE SENSING-BASED SPATIO-TEMPORAL ANALYSIS OF LAND USE LAND COVER CHANGES AND THEIR IMPACT ON LAND SURFACE TEMPERATURE AND URBAN HEAT ISLAND FORMATION OVER KARACHI

Abstract

Rapid urbanisation has emerged as one of the principal drivers of Land Use Land Cover (LULC) change in developing countries, with direct consequences for Land Surface Temperature (LST) and the formation of Urban Heat Islands (UHIs). Karachi, the largest and most populous city of Pakistan, has experienced an uncontrolled built-up expansion over the past three decades owing to economic migration and natural population growth. The present study investigates the spatio-temporal dynamics of LULC and LST in Karachi during the period 1990–2020 and forecasts LULC changes for 2030, 2040 and 2050 using a Cellular Automata (CA) Logistic model. Multi-temporal Landsat 5-TM, Landsat 7-ETM+ and Landsat 8-OLI satellite images were classified into four LULC classes (built-up, vegetation, barren land, water bodies) using the Support Vector Machine (SVM) algorithm. LST was retrieved from the thermal bands and classified into five temperature zones. Results indicate that the built-up area expanded by approximately 146.86% (from 310.23 km² to 765.79 km²), while vegetation, barren land and water bodies declined by 33.3%, 7.5% and 52.0% respectively between 1990 and 2020. The area above 30 °C increased from 2.79% to 13.96%, representing a net change of +400.4%. The highest mean LST was observed over built-up surfaces, followed by barren land, vegetation and water bodies. Simulation results indicate that the built-up fraction could reach 22.7%, 24.2% and 25.5% of the total area by 2030, 2040 and 2050 respectively. The overall classification accuracy exceeded 90% for all years with Kappa coefficients ranging from 0.79 to 0.86. The findings provide a quantitative basis for urban planning, sustainable land management and UHI mitigation strategies in Karachi and can be replicated for other rapidly urbanising cities of Pakistan