Researchers at the New York University Tandon School of Engineering have developed an innovative artificial intelligence system that maps urban green spaces with unprecedented accuracy, according to a news release. The technology tracks trees and grass with 89.4% accuracy — dramatically better than traditional methods that miss up to 37% of urban vegetation.
The system is intended to help with long-term tracking, especially in dense city areas where traditional satellite analysis falls short. Using a technique called green augmentation, researchers trained the AI to recognize subtle patterns that distinguish trees from grass even under varying lighting and seasonal conditions, improving detection accuracy by 13.4% compared to existing methods.
This tech emerged from work led by Rumi Chunara, an NYU associate professor with appointments in both the Tandon School of Engineering and School of Global Public Health. "Our system learns to recognize more subtle patterns that distinguish trees from grass, even in challenging urban environments," Chunara explains. "This type of data is necessary for urban planners to identify neighborhoods that lack vegetation so they can develop new green spaces that will deliver the most benefits possible."
Testing the system in Karachi, Pakistan, exposed dramatic environmental divides. The city averages just 4.2 square meters of green space per person — less than half the World Health Organization's recommended minimum. Additionally, while some areas enjoy over 80 square meters of green space per person, five neighborhoods have less than 0.1 square meters per capita.
The research confirms what many urban dwellers already experience: Neighborhoods with tree-lined streets are able to stay cooler, while others in concrete jungles suffer excessive heat. Urban trees reduce temperatures in hot cities, filter air pollution that causes respiratory problems, and provide essential spaces for exercise and better mental health.
While this AI system helps create healthier cities, it's worth noting that artificial intelligence generally consumes significant energy through massive data centers and growing computing infrastructure, contributing to increased carbon pollution that harms the planet. The environmental benefits of better urban planning must be balanced against the energy footprint of the technologies used to enable these improvements.
"Our system learns to recognize more subtle patterns that distinguish trees from grass, even in challenging urban environments," Chunara said. "This type of data is necessary for urban planners to identify neighborhoods that lack vegetation so they can develop new green spaces that will deliver the most benefits possible. Without accurate mapping, cities cannot address disparities effectively."
|
Do you think your city has good air quality? Click your choice to see results and speak your mind. |
Definitely 🥰 
Join our free newsletter for weekly updates on the latest innovations improving our lives and shaping our future, and don't miss this cool list of easy ways to help yourself while helping the planet.
Cool Picks
