Machine learning-based modeling of land surface temperature at an open dumpsite in Khulna, Bangladesh

Open dumping of untreated waste is a very common practice in developing countries. The municipality of Khulna dumps all waste in the Rajbandh landfill without any prior treatment. The biodegradation process of waste produces gases and heat, which can lead to difficulties in landfill operation. This study aims to predict the Land Surface Temperature (LST) of the Rajbandh landfill by utilizing Generalized Additive Model (GAM), MLR and ANN. The amount of waste received by the open dump has been collected from the municipality’s logbook. LandGEM has been used for modeling methane emissions. NDBI, NDVI, specific humidity, wind speed and LST was obtained from Google Earth Engine. The GAM results show that all predictors of LST are statistically significant (p < 0.001). A strong cubic relationship was found between humidity and LST (R 2 = 0.92), while NDVI and wind speed exhibited strong linear correlations (R 2 = 0.73 and 0.71, respectively). Variable importance analysis highlighted that methane and humidity emerged as the most influential variables, contributing 25.40% and 24.35% to LST variation, whereas NDBI had a minor impact. The MLR also showed statistical significance (p < 0.001) with a moderate predictive power with an R 2 of 0.60. These findings demonstrate the effectiveness of integrating remote sensing data with waste management parameters to develop reliable LST prediction models. The approach offers a cost-effective monitoring solution for landfill management in resource-constrained regions to anticipate thermal variations and environmental impacts.