Researchers have created an interactive map identifying 1.8 million individual trees in New York City, with a new approach that could optimize the placement of trees for cooling in cities around the world. 

In the study, published Aug. 14 in Scientific Data, researchers identify the types of trees using satellite imagery as well as on-the-ground datasets and 3D data collected with lidar, short for light detection and ranging. The approach was 82% accurate overall and higher for common types of New York City trees. 

It’s the first “wall-to-wall,” citywide map identifying trees, and it includes trees on private property, in natural areas and other unsurveyed areas, which together constitute an estimated 65% of the city’s canopy and have not been accounted for on previous maps. The research team will use the map to determine which trees are best for cooling, and the data could inform a host of other planting decisions where the type of tree makes a difference, from reducing allergens to managing invasive pests. 

“If we’re going to be managing these urban forests well, we need to know what’s there, and now we know that for another 1.4 million trees beyond the street trees that were already surveyed,” said Daniel Katz, a senior author and assistant professor in the School of Integrative Plant Science in the College of Agriculture and Life Sciences. “We can now use this information to make sure we get the most benefits from trees, from cooling to reducing air pollution and flooding. We also hope people will enjoy looking at their own neighborhood and seeing which trees are around them.” 

The research is part of the Cool Trees project, led by co-author Dr. Arnab Ghosh, M.S. ’19, ’23, associate professor of medicine at Weill Cornell Medicine. Optimizing trees’ cooling effects is increasingly important, as heat waves in New York City become more frequent and intense. An unrelated Cornell project, “The Generative Canopy,” aims to leverage street-tree data to determine where more trees are needed to provide shade to vulnerable New York City residents.  

The city recently set a goal of expanding tree cover from 22% to 30% by 2040, and the new map could directly inform those efforts, along with broader research from the Cool Trees team to determine the relationship between tree density and type, temperature and heat-related health risks.  

“By connecting all of these pieces, we’ll be able to say: If you make this planting or management decision about a tree, here’s how it’ll affect temperature and here’s how it will affect the number of people going to the emergency room during a heat wave,” said Katz, a co-investigator with Cool Trees. “That’s really powerful.” 

A major breakthrough in the research was figuring out how to use images taken by “constellations” of PlanetScope satellites, deployed by satellite imaging company Planet, which take high resolution pictures and circle the Earth every 90 minutes. Katz said using satellite images for tree identification has been a “holy grail” in his field for decades, but the images are often difficult to access and not at the scale needed for tree identification. The Cool Trees team, including first author and researcher David Miller, took advantage of the large quantity of PlanetScope images taken over time, so they could track the trees’ leaves changing in the fall or when they first put out buds in spring, for example. 

“That allowed us to look at these trees in a much more dynamic way,” Katz said. “It isn’t perfect, but it’s a really good start at showing you what’s where.” 

The team also used 3D lidar data from New York state, a map delineating the edges of tree crowns from The Nature Conservancy and the University of Vermont, as well as on-the-ground data from the New York City Department of Parks and Recreation to train their classifier and verify predictions. Because the PlanetScope satellites collect information across the country (and globe), Katz said they hope to apply their approach to many more locations; the team has compiled a database of 405 medium and large U.S. cities they hope to map. 

“We were able to get this accuracy from images which are ubiquitous, and it just opens up such a world of possibilities,” Katz said. “It’s really exciting to think about scaling this up.” 

Katz said he hopes making the data available and user-friendly for planners, researchers and the public will also expand its impact. 

“This is science for the public good, so it was important for us to make it available,” Katz said. “We think a lot of others will have ideas for how to use this map, and we hope people have fun with it, too.” 

Co-authors include Miller, now a researcher at the Cornell Lab of Ornithology, and Ghosh, who is also an internist at New York-Presbyterian/Weill Cornell Medical Center; and Weill Cornell Medicine co-authors Ghislaine Jumonville, research data analyst; Sarah Young, associate professor of social work research in medicine; Olivia Keenan, former research assistant; and Wenna Xi, former postdoctoral researcher. Ithaca-based co-authors include doctoral student Aalayna Rae Green and Ging-Yan Ho, MPS ’25. Additional contributors include Alexander Young from the University of New Hampshire and Chenghao Wang from the University of Oklahoma. 

Funding for the research came from the USDA’s National Institute of Food and Agriculture, the Cornell Atkinson Center for Sustainability and the Leona M. and Harry B. Helmsley Charitable Trust.