Environmental monitoring, urban planning, and disaster management are just a few of the many important fields that rely on the identification and categorization of objects inside satellite pictures. Our research suggests using a CNN and ALEXNET50 strategy to automatically identify and categorize items in satellite photos. Because of its inherent capability to automatically acquire hierarchical features, CNN and ALEXNET50s have shown exceptional performance in picture identification tasks. Following feature enhancement and noise removal in the preprocessing phase, we train a CNN and ALEXNET50 model on a labeled dataset. This completes our technique. Using their unique characteristics, CNN and ALEXNET50s learn to identify and categorize a wide variety of things, including buildings, roads, flora, and bodies of water. Our method has been tested and shown to successfully classify and identify objects in satellite images. This has significant ramifications for various areas, including environmental monitoring, urban development, and disaster management.