<p>In fostering economic growth, the effects of changes in Land Use and Land Cover (LULC) plays an important role for sustainable urban development. To address this issue, an efficient hybrid model is proposed to enhance the prediction accuracy of LULC for sustainable urban development. Initially, sentinel-2 satellite images of a region of interest for the study area Durgapur in West Bengal, India, and its neighboring areas, for 2018 and 2022 are processed using the Google Earth Engine (GEE) platform. Image acquisition and preprocessing are performed to ensure the suitability of input data for classification. The preprocessed images are classified using a Convolutional Neural Network (CNN), which excels at extracting spatial features of each class from the imagery. The CNN classification method ensures high accuracy in distinguishing between LULC classes. The classified images are then processed using a Random Forest Regressor (RFR) to predict future LULC changes. The RFR effectively handles nonlinear relationships in the data to make the predictions more accurate. The proposed hybrid model predicts the changes in LULC at 5-year intervals for the years 2025, 2030, and 2035. Hence, the proposed hybrid model captures both spatial patterns and temporal trends by combining CNN and RFR for spatial feature extraction and predictive modeling, respectively. The results demonstrate a high prediction accuracy of 98.7% with a kappa coefficient of 0.977, validating its effectiveness for LULC monitoring. This research provides valuable information related to measure the planning strategies for efficient sustainable land management in rapidly developing urban regions.</p>