Automated Power Lines Vegetation Monitoring using High-Resolution Satellite Imagery

Abstract

Vegetation Management is a significant preventive maintenance expense in many power transmission and distribution companies. Traditional Vegetation Management operational practices have proven ineffective and are rapidly becoming obsolete due to the lack of frequent inspection of vegetation and environmental states. The rise of satellite imagery data and machine learning provides an opportunity to close the loop with continuous data-driven vegetation monitoring. This paper proposes an automated framework for monitoring vegetation along power lines using high-resolution satellite imagery and a semi-supervised machine learning algorithm. The proposed satellite-based vegetation monitoring framework aims to reduce the cost and time of power line monitoring by partially replacing ground patrols and helicopter or drone inspection with satellite data analytics. It is implemented and demonstrated for a power distribution system operator (DSO) in the west of Norway. For further assessment, the satellite-based algorithm outcomes are compared with LiDAR survey data collected by helicopters. The results show the potential of the solution for reducing the monitoring costs for electric utilities.