Seasonal Dynamics in Land Surface Temperature in Response to Land Use Land Cover Changes Using Google Earth Engine

Abstract

Changes in land use and land cover (LULC) are critical for evaluating global spatiotemporal trends, especially regarding climate change and urbanization. This study investigates the dynamics of Landsat surface temperature (LST) in response to LULC changes and their effects on the seasonal microclimate in Kasur District, Pakistan. Using the Google Earth Engine platform, we employed a random forest algorithm to detect LULC changes (cropland, forest, built-up, fallow, barren, and water) and analyze seasonal spectral indices from Landsat imagery for 1988, 2002, and 2022. Significant LULC changes were observed, including a 9.8% increase in built-up areas, a 4.2% decrease in cropland, and a 1.4% decrease in forested areas, linked to urban heat island effects and population growth. Additionally, there was a 2.7% increase in fallow and open land, contributing to the district's impervious surface area. Significant correlations (p < 0.001) were found between LST and spectral indices—normalized difference vegetation index, enhanced vegetation index, and normalized difference built index (NDBI)—ranging from 0.7 to 0.8 in both winter and summer. In summer, the maximum LST increased from 43 °C in 1988 to 44 °C in 2002, with a linear correlation (R²) increase from 0.57 to 0.75 and a polynomial correlation (R²) increase from 0.63 to 0.76 with NDBI from 1988 to 2022. Understanding these dynamics is crucial as LULC changes and the resulting temperature variations have significant implications for local climate, agriculture, and human health. This study underscores the need for effective LULC policies to mitigate impacts, protect vegetation cover, and ensure sustainable land management. These findings provide valuable insights for policymakers and urban planners aiming to balance development with environmental sustainability.

Keywords

• Google Earth engine (GEE)
• normalized difference built-up index (NDBI)
• normalized difference vegetation index (NDVI)
• polynomial regression
• random forest (RF)