Mapping-All-of-the-Trees-with-Machine-Learning-d #

1*MZcIQRCAJX5fbn0Zw6cPlA.jpeg Descartes Labs built a machine learning model to identify tree canopy globally using a combination of lidar, aerial imagery and satellite imagery. San Francisco’s wonderful Open Forest Map tree inventory (point data) alternating with the Descartes Labs tree canopy layer (image data) This data gap is neither accidental nor purposeful. Note the city census does not include park trees or trees in private gardens. Boston vegetation (NDVI from an August 28, 2018 Sentinel 2 scene) alternating with the Descartes Labs tree canopy layer — looks like quite a lot of that vegetation might not be trees! Washington, D.C. tree canopy created with NAIP source imagery shown at different scales—all the way down to individual “TREES!” on The Ellipse. The ability to map tree canopy at a such a high resolution in areas that can’t be easily reached on foot would be helpful for utility companies to pinpoint encroachment issues—or for municipalities to find possible trouble spots beyond their official tree census (if they even have one). Scroll through this New York City tree image and notice how the landscape of trees ebbs and flows throughout.