Using Artificial Intelligence to Measure Urban Tree Canopies

Machine learning has opened a new frontier in urban forest management.
December 30, 2018, 1pm PST | James Brasuell | @CasualBrasuell
Share Tweet LinkedIn Email Comments
La Citta Vita

Linda Poon shares news of a new mapping effort enabled by artificial intelligence (AI) that measures the number of trees in cities.

Finding the answer to the question of how many trees are living in a city can be a monumental task, according to Poon. "New York City’s 2015-2016 tree census, for example, took nearly two years (12,000 hours total) and more than 2,200 volunteers. Seattle’s tree inventory won’t be complete until at least 2024."

Still, there are good reasons to count the trees too, according to Poon. "[I]n the short term, they allow cities to better maintain their urban trees. And over the long run, they lay out the foundation for various initiatives that address everything from climate change to public health."

That's where Descartes Labs comes in, with new technology that leverages AI to measure trees in urban settings. "In their quest to leave no tree uncounted, they built a machine learning model that can map an entire city’s canopy, even subtracting other greenery that might look like trees in satellite imagery," reports Poon.

The article includes a lot more about the results (including detailed maps) and the potential of the new tool.

Full Story:
Published on Friday, December 28, 2018 in CityLab
Share Tweet LinkedIn Email