Land surface temperature (LST) is the temperature of the Earth’s surface, typically measured in degrees Celsius (°C). It is the temperature of the surface of the Earth, including the soil, vegetation, and buildings. This study investigates the temporal variations of land surface temperature (LST) using MODIS data and analyzes its correlation with air temperature using ERA5 data in the Google Earth Engine. The results show a clear trend of increasing LST over the years, with the highest temperatures observed in May and June. The spatial distribution of LST reveals an expansion of the highest temperature values, indicating a general increase in LST across the region. The correlation between LST and air temperature was strong, with a coefficient of 0.99. The results suggest that LST can be used as a proxy for air temperature in various applications, such as climate modeling and environmental monitoring. The predictive modeling of air temperature using an artificial neural network (ANN) model, which incorporates LST, NDVI, and elevation data, showed promising results. The model accurately estimated air temperature with a mean squared error of 0.4950 in 2013 and 0.6889 in 2023. The study emphasizes the importance of considering LST’s temporal and spatial variations and its correlation with air temperature in climate modeling and environmental monitoring applications. The results can be used to inform policy decisions and develop strategies to mitigate the effects of rising temperatures and climate change.