Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178230,
        author = {Pranay Undirwade and Imran Ahmad},
        title = {Wind Sight: Precision Windmill Detection Using Satellite Images with U-net Model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4204-4212},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178230},
        abstract = {The rising development of renewable energy infrastructure, particularly wind farms, calls for effective monitoring and management solutions. This research explores the use of deep learning, specifically convolutional neural networks (CNN) and semantic segmentation models, to detect windmills in satellite imagery. Leveraging high- resolution satellite imagery and the U-Net architecture, this study emphasizes precise identification and localization of windmills. The methodology includes collecting and annotating a windmill satellite image dataset, followed by data preprocessing to improve image quality and generate binary masks. This dataset trains the U-Net model, which successfully segments windmills from test images with a validation accuracy of 93.7%. This research demonstrates the effective combination of deep learning and geospatial analysis, presenting a scalable approach for wind energy resource monitoring.},
        keywords = {windmill, images, QGIS, Annotations, CNN, Tensorflow, keras, augmentations, satellite imagery)},
        month = {May},
        }