Scientists unveil AI breakthrough that could expose hidden problems in urban planning: 'Cannot address disparities effectively'

NYU Tandon researchers have developed an AI system that maps urban green spaces with 89.4% accuracy, significantly outperforming traditional methods. Led by Associate Professor Rumi Chunara – who also holds an appointment in the NYU School of Global Public Health – the technology differentiates between trees and grass even in challenging conditions. "Our system learns to recognize more subtle patterns that distinguish trees from grass, even in challenging urban environments," Chunara explains. Testing in Karachi revealed stark environmental inequalities, with some neighborhoods having almost no green space, highlighting the importance of accurate mapping to address urban environmental disparities.