The creation of urban heat islands (UHI) is a major problem for industrialized and developing countries worldwide. Its growth and development have far-reaching effects on many environmental variables, including global warming, crop yield, and water and air quality. Changes in the topography of the land brought about mainly by urbanization and industrialization have increased the severity of urban heat islands (UHI). In areas where there is rapid urbanization without proper town planning or in dry regions, the impacts of UHI are more pronounced. Nevertheless, to detect and reduce the UHI effect, a thorough comprehension is necessary, which can be attained through regular surface monitoring of the Earth. However, this method requires considerable time, energy, and resources. Several computational and numerical approaches have been devised to detect the appearance and spread of UHI to address this problem. Among these methodologies, the Urban Canopy Model (UCM), Building Energy Model (BEM), and Urban Heat Island Intensity (UHII) are prominent. Remote sensing photography shows great promise as a method for studying and predicting UHI. To evaluate the UHI effect, this research examines Land Surface Temperature (LST) and plant health using Remote Sensing data collected in Chennai, India. Using classifiers such as Random Forest (RF), Maximum Likelihood Classification (MLC), Support Vector Machine (SVM), and Land Use Land Cover (LULC), change analysis assesses the health of the vegetation. By visualizing changes in land cover, these classifiers make it easier to classify the land into different categories. Classifiers provide insight into the dynamics of land cover change and its relationship with UHI generation by computing pixel similarity and effectively grouping each pixel into its own class.