Preventing Wildfires in Energy Transmission by Automatic Power Line Defects Detection Using Machine Learning and AI

Wildfires caused by faults in electrical power lines remain a significant threat to lives, infrastructure, economy and ecosystems. When transmission lines fail or contact vegetation, electrical arcing can easily ignite fires that spread rapidly under dry and windy conditions. This paper reviews state-of-the-art technologies for wildfire prevention in energy transmission systems and presents an initial framework that leverages computer vision for automatic detection of power line defects and potential ignition sources. As a proof of concept, a rule-based falling-wire detection pipeline is implemented using computer vision methods such as Canny edge detection and the Hough Transform. The results demonstrate the feasibility of identifying hazardous conditions through visual analysis. Building on this foundation, future work will incorporate advanced machine learning and deep learning models to achieve more robust, scalable, and adaptive inspection systems for proactive wildfire prevention.