The accurate classification of crops is essential for efficient agricultural management and monitoring. This study focuses on integrating remote sensing data with machine learning techniques to classify crops in Latur District, Maharashtra, using the Google Earth Engine (GEE) platform and the random forest algorithm. High-resolution satellite imagery from Sentinel-2 was used to capture temporal and spatial variations in crop patterns. The study involved preprocessing the data, including atmospheric correction and cloud masking, followed by feature extraction to derive key vegetation indices such as NDVI and EVI. The random forest classifier was employed due to its robustness in handling complex datasets and its ability to manage high-dimensional data with multiple features. The model was trained on a dataset of ground truth points, and the classification accuracy was validated using confusion matrices and other statistical metrics. The results demonstrated that the integration of GEE and random forest provided a reliable and efficient approach for crop classification, achieving high accuracy in distinguishing between different crop types. This methodology offers significant potential for large-scale agricultural monitoring, allowing for timely decision-making and resource allocation.