<![CDATA[This research aims to map land cover in Bandung City using the Random Forest (RF) algorithm implemented on the Google Earth Engine (GEE) cloud-based platform. Sentinel-2 satellite image data was used to analyze four main classes of land cover, namely residential land, green land, water, and open land. The classification process involved initial data processing, model training using sample data, and accuracy evaluation through confusion matrix and cross-validation. The results showed that the RF algorithm had an overall accuracy of 89%, with the highest accuracy in the residential land class (92%) and the lowest in the water class (80%). Cross-validation showed stable performance with an average accuracy of 88.5%, precision 0.91, recall 0.88, and F1-score 0.89. Confusion matrix analysis identified misclassification in certain classes due to spectral overlap, especially between green land and open area. This research proves that the RF algorithm in GEE is an efficient and accurate method for land cover classification, while supporting spatial planning and environmental management. Further developments could include the use of higher resolution data, advanced learning algorithms and time-based analysis to understand the dynamics of land cover change.]]>
