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{189698,
        author = {MS. KIMAYA CHURI and MRS. BHAKTI PATIL},
        title = {FireFly: A Deep Learning-Based Forest Fire Detection System Using Drone and Satellite Imagery},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {7501-7504},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189698},
        abstract = {Forest fires are among the most devastating environmental disasters, leading to widespread destruction of ecosystems, biodiversity loss, and air pollution. Traditional forest fire detection systems, such as manual patrolling and satellite-based observation, suffer from slow response times, low accuracy, and limited real-time capabilities. This paper presents FireFly, an intelligent deep learning–based system for the detection and monitoring of forest fires using drone and satellite imagery. FireFly leverages Convolutional Neural Networks (CNNs) to analyze high-resolution images captured from aerial sources to identify fire and smoke patterns. The system employs advanced image segmentation and object detection techniques to ensure precise recognition even in complex forest conditions. FireFly enhances early detection accuracy, reduces false alarms, and provides a scalable solution for large-area surveillance. The results show that FireFly achieves over 95% accuracy in identifying fire-prone regions, making it a reliable and efficient approach for modern wildfire management systems.},
        keywords = {Forest Fire Detection, Deep Learning, CNN, Drone Imagery, Satellite Data, Image Segmentation, FireFly, Real-Time Detection},
        month = {December},
        }