Satellite imagery has numerous applications, including land use and land cover classification, change detection, and object detection. However, satellite-based remote sensing sensors often face challenges from cloud cover, which can obscure the Earth’s surface and hinder accurate analysis. To ensure the imagery is suitable for use, cloud-covered areas must be either excluded or corrected using cloud removal techniques. These pre-processing steps typically rely on a cloud mask. While creating a cloud mask manually for a single scene is possible, though time-consuming, it becomes impractical when dealing with large volumes of imagery. This is where automation becomes essential. The described model offers an efficient solution by automatically generating cloud masks for Sentinel-2 imagery, streamlining the pre-processing workflow, and enabling scalable image analysis.