Tree Canopy Height Maps

A place to create and share code of newly made maps of canopy tree heights.

Meta and the World Resources Institute launched a global map of tree canopy height at a 1-meter resolution, allowing the detection of single trees on a global scale. Both the canopy height data and the models used to create the data are free and publicly available (Tolan, Couprie, et al. 2024). The maps were created using machine learning models on high-resolution worldwide Maxar satellite imagery. The details of the model used to create the data set are described in Tolan et al. (2024).

Working With RStudio

Download R/RStudio at this link: https://posit.co/download/rstudio-desktop

GitHub Resources

A great resource for using basemaps in R to produce the interactive maps using Leaflet, Carto, and TESS-Laboratories:

Leaflet: https://github.com/Leaflet/Leaflet

Carto: https://github.com/CartoDB/basemap-styles

TESS-Laboratories: https://github.com/TESS-Laboratory/chmloader

Docker

Docker is a uniqiue software in that it allows for you to create a containerized fully unbreakable proof since the code is contained with a single image.

Getting Started

Make a directory and then clone the github.

In Terminal: mkdir globalTreeHeight && git clone https://github.com/geodegarmo/treeHeightMaps_R.git

References

Tolan, Jamie, Camille Couprie, John Brandt, Justine Spore, Tobias Tiecke, Tracy Johns, and Patrick Nease. 2024. “Using Artificial Intelligence to Map the Earth’s Forests.” Meta Sustainability. https://sustainability.fb.com/blog/2024/04/22/using-artificial-intelligence-to-map-the-earths-forests/.

Tolan, Jamie, Hung-I Yang, Benjamin Nosarzewski, Guillaume Couairon, Huy V. Vo, John Brandt, Justine Spore, et al. 2024. “Very High Resolution Canopy Height Maps from RGB Imagery Using Self-Supervised Vision Transformer and Convolutional Decoder Trained on Aerial Lidar.” Remote Sensing of Environment 300 (January): 113888.
https://doi.org/10.1016/j.rse.2023.113888.