Satellite imagery plays a pivotal role in monitoring and understanding the Earth’s ecosystems. Accurate and efficient segmentation of vegetation in these images is crucial for a wide range of applications, including environmental monitoring, land-use planning, and disaster management. In this study, we propose a novel approach for vegetation segmentation in satellite images utilizing the U-Net architecture with an accuracy of 88%, a convolutional neural network renowned for its excellence in semantic segmentation tasks. The proposed method leverages the rich spatial information in high-resolution satellite imagery to achieve state-of-the-art results in vegetation segmentation. Comprehensive experiments demonstrate the superiority of the U-Net-based approach in achieving efficient and accurate vegetation segmentation, even in complex natural environments. This research contributes to advancing the capabilities of satellite-based vegetation monitoring, supporting conservation efforts, and land management strategies.