As extreme heat drives dangerous temperatures across much of the United States, USC researchers have released a free AI tool that helps cities map their tree canopy using publicly available aerial imagery. The tool eliminates the need for expensive lidar surveys or commercial satellite data, making it feasible for communities with limited budgets to identify where planting trees would most reduce heat risks.
Mapping tree cover without expensive surveys
Unlike many high-accuracy tree-mapping systems, the USC-developed tool works with aerial photographs collected every two to three years through the U.S. Department of Agriculture's National Agriculture Imagery Program. By combining those free images with AI, the researchers dramatically reduced the cost of producing detailed canopy maps.
"Trees provide a wide range of benefits, including helping reduce the health risks associated with rising temperatures in cities," said John Wilson, founding director of the Spatial Sciences Institute at the USC Dornsife College of Letters, Arts and Sciences and the study's corresponding author. "But to plant trees where they'll make the biggest difference, cities first need a clear picture of their existing tree canopy."
"We need fine-scale data to know where to plant new trees that provide the best return on investment," Wilson said. "Our work shows how we can use free, publicly accessible data to map tree canopy over time-data cities can use to guide planting plans at every scale, from a single street block to an entire county."
Testing in Los Angeles and beyond
The researchers developed and tested the system in Boyle Heights and City Terrace, two densely populated, majority-Latino neighborhoods east of downtown Los Angeles that have historically had less tree cover than wealthier parts of the city. The canopy-mapping model accurately identified tree cover, and the individual tree-detection model performed competitively with far more expensive lidar-based approaches.
To test whether the approach could work elsewhere, the team applied the trained models, without additional retraining, to neighborhoods in San Francisco and Phoenix. Despite the different climates and urban layouts, the tool produced consistently strong results. The ArcGIS deep learning package developed through the project has been downloaded more than 12,900 times from Esri's Living Atlas platform over the past six months, reflecting growing interest in AI for IT & Development among GIS specialists and city planners.
The research, code and a ready-to-use ArcGIS deep learning model are freely available online, enabling municipalities to apply Data Analysis to urban forestry even without in-house machine learning expertise.
What's next: adding 3D structure
Wilson said the team's next step is to pair its AI tool with freely available lidar data that captures the height and three-dimensional structure of tree canopies. "Knowing both the height and extent of the canopy will allow us to estimate the shade trees provide today-and model how much additional shade new plantings could create," he said. The researchers plan to begin by analyzing individual street blocks, school playgrounds and parks before expanding the approach to neighborhoods, cities and counties.
Why this matters for IT and development professionals
This project offers a practical case study in deploying computer vision models on publicly available datasets. Pre-trained models and open-source code lower the barrier to entry for geospatial AI, giving developers a reusable template for municipal or environmental projects. The combination of free imagery, cloud-based deep learning packages, and a growing community of practice around tools like ArcGIS means IT teams can prototype and deploy similar canopy analysis without starting from scratch.
Your membership also unlocks:
