Spatiotemporal analysis of Urban Heat Island and land use land cover changes using Landsat images and CA-ANN machine learning techniques: a case study of Dakahlia government, Egypt

ABSTRACT

This study explores the relationship between Land Use Land Cover (LULC), Land Surface Temperature (LST), and Urban Heat Island (UHI) in Dakahlia Government using Landsat 8 images from 2014 to 2020. Support Vector Machine (SVM) and Mono-Window Algorithm were used to generate LULC and estimate LST. Results reveal an increase in built-up areas, rising LST, and variable UHI thresholds. The study highlights the impact of COVID-19 on LST in 2020. Positive correlations between LST and Normalized difference build-up index (NDBI) and negative correlations with Normalized difference vegetation index (NDVI) were observed. Projections for 2030 suggest an increase in high-temperature areas.

KEYWORDS:

• Land Surface Temperature
• Urban Heat Island
• land use land cover
• LULC indices
• CA-ANN algorithm

Disclosure statement

No potential conflict of interest was reported by the author(s).