This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: VUB researcher Robbe Neyns has developed artificial intelligence capable of identifying trees down to the species level in satellite and aerial imagery. The technology can help cities better map their trees and biodiversity, making the urban environment as livable as possible, particularly in the face of a warming climate.
Trees fulfill important functions in our cities. They provide shade and cooling, filter the air and serve as a habitat and food source for numerous animals. Surprisingly, however, we often do not know exactly which trees are where.
Existing tree inventories are not always complete or up to date, and identifying thousands of trees on the ground is labor-intensive. Neyns therefore investigated whether AI could take over part of this work from the air. For the Brussels-Capital Region, he combined satellite images taken at different times of the year with highly detailed aerial photographs.
Deep learning is used to train the system to recognize different tree species from these images. He defended his PhD dissertation, titled "Beyond the Canopy: Deep Learning for Urban Tree Species Classification Applications in Pollinator Ecology and Tree Phenological Responses to Urban Stressors" on Sept. 9. "Recognizing a tree crown is one thing, but in a densely built-up city, crowns overlap, buildings cast shadows over the images, and you have to deal with different background materials," says Neyns.
"By combining different types of images, we provide the model with sufficient information to distinguish between tree species. After all, each tree species has its own characteristics and follows a different cycle throughout the year." This creates a sort of digital tree expert that can help identify which tree is where on a large scale. Neyns then used the technology for ecological research.
In Braunschweig, Germany, he mapped willow trees for research into Andrena vaga, a wild bee that is heavily dependent on willows for its pollen. By combining the tree map with other environmental factors and observations of bee nests, it was possible to predict which areas of the city provided suitable habitat. In a second application, he investigated the health of the city's trees themselves.
Extract — continue reading at the source.
