Recently published by Geo Week News – with the original article authored by Ada Perello and EAASI (the European Association of Aerial Surveying Industries, of which RIEGL is an Observer Member) – this project highlights a scalable approach to managing utility infrastructure using advanced airborne RIEGL LiDAR and AI. 

Vegetation encroachment is a leading cause of power outages worldwide, particularly across large-scale distribution networks. In Eastern Canada, a major utility managing more than 103,000 km of power lines is working to reduce outages by 50% by 2028 - driving the need for a scalable, data-driven approach to vegetation management.

To help meet this challenge, the utility network partnered with XEOS Imaging, a Canada-based geospatial firm specializing in high-precision aerial imaging and LiDAR data acquisition. Founded in 2004, XEOS supports a wide range of applications, including infrastructure corridor mapping, urban modeling, environmental monitoring, and large-scale 3D city mapping. Operating at the forefront of geospatial technology, XEOS combines advanced sensor systems with AI-driven LiDAR processing to produce highly accurate and reliable data.

Central to this capability is the RIEGL VQ-1460 airborne laser scanner that they acquired in November of 2023 – a high-performance system designed for efficient, large-scale data acquisition. It produces dense, high-accuracy point clouds and excels at detecting fine features such as power lines and complex vegetation structures, making it particularly well suited for utility corridor mapping.

Managing such an extensive network presents significant operational challenges. Traditional inspection methods cannot efficiently scale across 103,000 km of infrastructure, prompting the need for automated vegetation detection and high-quality geospatial data. To address this, XEOS developed an integrated workflow combining airborne LiDAR acquisition and AI-driven analytics. Using a Piper Navajo aircraft equipped with the RIEGL VQ-1460, the team captured detailed data and automatically identified infrastructure, encroaching vegetation, and potential fall-in hazards.

Deployed across 11 municipalities in winter 2025-2026, the project delivered a detailed 3D model of the network – transforming large datasets into actionable insights that enable more proactive, predictive maintenance and improved grid reliability.

Read the full article here to explore the complete project, workflow, and results.