Using satellite imagery to identify 37 different species of vegetation and reduce risk.

A case study by Overstory and Red Eléctrica de España.

Which tree, of the millions that are located near power lines, could be the one to grow into a powerline or fall and cause a power outage?

That’s a question every electric utility around the world thinks about. Overstory reduces that risk by using satellite data and machine learning to help its customers understand the position of the trees, their height, their species and whether they’re healthy.

For Red Eléctrica de España (REE), knowing the vegetation species is key to managing risk and compliance. REE is responsible for 27,340 miles of transmission lines in Spain and is working with Overstory to classify 37 different species of vegetation along its lines.

Overstory and REE distinguish between 37 different vegetation classes, over a terrain of 10,000 miles with a corridor width of 492 feet.

Overstory and REE distinguish between 37 different vegetation classes, over a terrain of 10,000 miles with a corridor width of 492 feet.

Knowing the tree species to understand risk

Like many utilities, REE wants to spend its vegetation management budget in the most efficient, targeted way possible. Knowing the tree and shrub species that grow near their lines is critical for understanding risks and for prioritizing money and time spent around those risks.

In the past it has been a real challenge to properly label or annotate all the species near the right-of-way. Vegetation changes constantly, and mapping the tree species by hand meant having a snapshot for only one moment in time. Trees such as Pine and Eucalyptus grow quickly in Spain. There was a need to frequently monitor species in a more scalable, cost-effective and quality-controlled way. Technology from Overstory that combines satellite images and machine learning was perfect to take on this challenge.

“The high costs of manual interpretation made the business case unbearable, until we discovered Overstory’s approach based on machine learning and satellite data.”

— Iago Veiras Lens, Artificial Intelligence Partner, Elewit, Red Eléctrica Group

Picture 2.png
 
 
Picture 1.png

Tree species intelligence created by REE and Overstory

Optimizing budget by a risk-based pruning approach

REE is now able to monitor 37 species across all the 13 different climate zones of Spain. As a result of the collaboration with Overstory, REE has a detailed and efficient-to-maintain vegetation map. The species identification, which is input to the applications and algorithms of REE, allows REE to manage the maintenance of the vegetation, optimize the budget by focusing pruning in the areas of greatest risk and guarantee compliance with regulations.

“The vegetation management experts have validated the accuracy of the deliverables for all of mainland Spain and the Balearic Islands, and they’ve confirmed that the accuracy exceeded our expectations. The results from Overstory are currently implemented in the vegetation management cycle for 10,000 miles of powerline.”

— Iago Veiras Lens, Artificial Intelligence Partner, Elewit, Red Eléctrica Group

Learn more about:

  • How Overstory and REE have combined satellite imagery and machine learning to identify vegetation species

  • How the operational requirements were achieved and validated, including accuracy, agility and affordability

  • The business results of implementing the vegetation intelligence into REE operations

Written by: Overstory, Elewit, Red Eléctrica Group and Red Eléctrica de España