Accurate and updated tree cover data is critical for effectively managing our tree resources. The US Tree Map (UTM) is the most detailed and up-to-date source of tree cover data for the country. It provides information on presence/absence of trees at 1-meter resolution, accurately capturing individual trees and small gaps in the forest. The data is refreshed annually to capture changes in tree cover due to deforestation, urbanization, land-use change and natural disasters.

EarthDefine has leveraged advancements in computer vision and AI to solve geospatial classification challenges. We developed a robust AI model that can consistently classify tree cover in aerial imagery across the continental US. The AI model was used to classify over 120 terabytes of high-resolution color-infrared aerial imagery spanning over 3.1 million square miles to create the US Tree Map.

Currently, the National Land Cover Database (NLCD) tree canopy data layer provides nationwide tree canopy estimates. However, with a 30-meter pixel resolution and a 5-year update cycle, the NLCD tree cover is not suitable for many kinds of geospatial analyses that require greater mapping precision and updated data. EarthDefine's US Tree Map overcomes these limitations by classifying tree canopy at 900 times the spatial resolution and updating the data annually. This captures even small individual trees besides accurately mapping the edges of forest patches.

The US Tree Map has an overall accuracy of 96.6%. In census defined urban areas the overall accuracy is higher at 97.3%. Accuracy was assessed using 48,000 random points (1000 points/state).

The US Tree Map AI model can be employed to map tree canopy using aerial imagery from previous years. For most areas in the US, we have access to historical imagery starting from 2005. Using older aerial imagery multiple snapshots of tree cover can be derived for change analysis.

High resolution tree canopy data is used for performing a wide range of mapping and analytical applications including:

• mapping actual and potential tree canopy in urban communities through Urban Tree Canopy (UTC) assessments
• assessing defensible space around buildings to reduce wildfire risk
• mapping risks to utility infrastructure like powerlines
• modeling of tree services like air and water pollution mitigation
• measuring carbon storage and sequestration
• wildfire modeling
• assessing tree risks to residential properties
• creating and analyzing forest inventory
• measuring agroforestry resources in rural landscapes

Tree Locations

Canopy Height Model (CHM)

Land Cover

US Impervious Map

US Building Footprints