This study aims to simulate LULC and predict urban sprawl. Predictive modeling was conducted using the Land Change Modeler (LCM) from Clark Labs, employing advanced algorithms like Multi-Layer Perceptron-Neural Network (MLP-NN) and Markov Chain (MC). LCM was trained with 12 variables including elevation and distances from roads, rails, water bodies, forests, builtup areas, etc. The model prediction accuracy has been accessed by evaluating Receiver Operating Characteristic (ROC) values. The ROC/AUC values for agricultural land, vegetative cover, built-up, waterbody, scrub land and sodic land has been recorded as 0.62, 0.65, 0.91, 0.71, 0.79 and 0.81, respectively. The findings highlight a significant increase in built-up areas, indicative of urban sprawl, alongside decreases in agricultural land, wasteland, and tree cover from 2020 to 2030.