Spatiotemporal Dynamics of Urban Heat Islands in India: A Multivariate Analysis Using High-Resolution Remote Sensing, Machine Learning, and Geospatial Modeling for Climate-Resilient Urban Planning

The Urban Heat Island (UHI) effect, a phenomenon where urban areas experience significantly higher temperatures than their rural surroundings, has drawn global attention due to its far-reaching environmental and public health consequences. The interplay between urbanization, land surface temperature (LST), and population density significantly influences microclimatic conditions, leading to increased energy consumption, thermal discomfort, and elevated health risks. This study integrates high-resolution satellite-derived LST data from Landsat and Sentinel-2 with demographic information from ind_ppp_2020.tif to investigate spatial temperature variations across major Indian metropolitan regions. By applying advanced machine learning models, including XGBoost and Convolutional Neural Networks (CNNs), the study seeks to establish predictive relationships between urbanization patterns and temperature anomalies. The results contribute to climate-responsive urban planning and mitigation strategies aimed at reducing urban heat stress and enhancing environmental sustainability. This research highlights the necessity of integrating geospatial analytics, artificial intelligence, and climate-sensitive infrastructure planning to develop effective countermeasures against the intensifying UHI effect in rapidly urbanizing regions.