The increasing pressure on natural resources results from considerable changes in land use and land cover (LULC) patterns brought on by the rapid rise of the world’s population. Alternative fields have begun to recognize the necessity to track and comprehend LULC changes, and the requirement for precise LULC mapping from remote sensing data highlights the significance of comparing alternative machine learning classifiers. Support Vector Machine (SVM), Random Forest (RF), and Classification and Regression Trees (CART) are three well-known machine learning techniques that were used in this work to categorize LULC using Google Earth Engine (GEE). Each classifier’s performance was evaluated and compared based on its accuracy. The Brahmani River basin, taken from USGS’s Earth Explore and retrieved using ArcGIS, was included in the research region. For 2018 through 2022, supervised classification was used with Sentinel-2 data with 10 m and 30 m spatial resolutions. There were four main LULC categories: “Water,” “Bareland,” “Vegetation,” and “Built-up Area.” Regarding accuracy, the results showed that RF had the greatest score among the classifiers, scoring 81% overall, while SVM and CART scored 72% and 78%, respectively. The success of RF classifiers in LULC classification using Sentinel-2 imagery is underlined in this study, emphasizing the need to select the proper machine-learning technique for precise LULC mapping. The results help to clarify the potential of machine learning for analyzing and tracking LULC changes over time.