Time Series Analysis of Land Surface Temperature and Drivers of Urban Heat Island Effect Based on Remotely Sensed Data to Develop a Prediction Model

The local climate of cities is changing, and one the primary reasons for this change rapid urbanization. Lahore district situated in Punjab province Pakistan mainly comprised city. This city among fastest expanding Pakistan. Due to urbanization, natural land surfaces are being altered, harming environment thus causing urban heat island (UHI) effect. For analysis UHI effect, fundamental essential step assessing surface temperature (LST). Therefore, current investigation assessed LST evaluate effect district. study used remote sensing data retrieved from Advanced Spaceborne Thermal Emission Reflection Radiometer Global Digital Elevation Model (ASTER GDEM) Moderate-Resolution Imaging Spectroradiometer (MODIS) sensor. Different new generation algorithms were initially used, but a convolutional neural network (CNN) model was based on accuracy. developed by utilizing past 19 years’ values along with elevation, road density (RD), enhanced vegetation index (EVI) as input parameters analyzing predicting LST. year 2020 validation outcomes CNN model. Among predicted observed LST, high correlation noticed. mean absolute percentage error (MAPE), (MAE), squared (MSE) considered two different periods (January May) also computed both training processes. prediction most parts within 0.1 K values. Hence, formulated can be utilized an tool evaluation at any location.