BetaThis is a new service. Your feedback will help us improve it. Tell us what you think

Tree Canopy Mapping

Tree Canopy Mapping measures how much of each neighbourhood is covered by tree canopy, from aerial imagery captured every two years.

Keywords

  • Tags: Computer vision
  • Tags: Environment
  • Tags: Net zero
  • Tags: Equity
  • Stage: Production
  • Type: Image segmentation model
  • Sector: Environment
  • Language: English

How does our product work?

Aerial imagery is segmented into canopy and non-canopy, and the results are aggregated to neighbourhood level and compared with the previous survey.

The imagery is captured at a resolution that shows vegetation and buildings but not people.

Overview

Canopy cover was previously estimated by sampling, which was too coarse to see change between surveys or to compare neighbourhoods fairly.

Complete measurement made visible a strong correlation between low canopy cover and deprivation, which now drives where planting is prioritised.

Owner and responsibility

Parks and Greenspace

Callum Reid

greenspace@example.gov

See more information

More detailed information on the system

Here you can get acquainted with the information used by the system, the operating logic, and its governance in the areas that interest you.

System description

Neighbourhood-level results are published as open data. Model error is reported by land use type, since accuracy over dense urban tree cover differs from accuracy over parkland.

References

Canopy cover open dataset and method note.

Was this information useful?

Would you like to give feedback? Your feedback will help us develop our algorithms further.

If you wish for the system owner to get back to you personally, please contact them directly using the email address above. For more general comments, use the box below.