Skip to content

High Resolution 1m Global Canopy Height Maps

The Global Canopy Height Maps dataset offers comprehensive insights into tree canopy heights worldwide, providing an overview of tree canopy presence and height for the analysed period (2009-2020), with eighty per cent of the data obtained from imagery acquired between 2018 and 2020. This baseline can be used as a reference for supplementing field-based measurements of carbon in carbon credit monitoring and verification schema. When newer imagery is available, the publicly shared model can be used to detect changes in canopy heights. Developed through a collaboration between Meta and the World Resources Institute, this dataset stands as a cornerstone for understanding forest structure and dynamics. This dataset achieves an unparalleled level of detail through the fusion of state-of-the-art satellite imagery and advanced artificial intelligence techniques. By analyzing satellite imagery spanning from 2009 to 2020, with a focus on data from 2018 to 2020, it provides extensive temporal coverage for tracking changes in canopy height over time across the entire landmass of the planet. Using AI models such as DiNOv2, the dataset enables precise prediction of canopy height with a mean absolute error of 2.8 meters, empowering accurate assessment of carbon stocks and the effectiveness of mitigation strategies.

Moreover, its integration into conservation initiatives, carbon credit monitoring, and climate agreements underscores its significance in guiding sustainable forest management practices, afforestation, reforestation efforts, and biodiversity conservation. Complemented by the accessibility of the AI model used to generate the data on GitHub, this dataset catalyzes further research and development in forest monitoring and carbon sequestration, contributing to global efforts to combat climate change. You can read the blogpost from meta here and the associated paper here.


Tolan, J., Yang, H.I., Nosarzewski, B., Couairon, G., Vo, H.V., Brandt, J., Spore, J., Majumdar, S., Haziza, D., Vamaraju, J. and Moutakanni, T.,
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, p.113888.

Dataset citation

High Resolution Canopy Height Maps by WRI and Meta was accessed on DATE from Google Earth Engine. Meta and World Resources Institude (WRI) - 2023.
High Resolution Canopy Height Maps (CHM). Source imagery for CHM © 2016 Maxar. Accessed DAY MONTH YEAR.


Earth Engine Snippet

var canopy_ht = ee.ImageCollection("projects/meta-forest-monitoring-okw37/assets/CanopyHeight")

Sample code:

GEE app link:


This dataset is made available under a Creative Commons Attribution 4.0 International License

Dataset provider: Meta and WRI, Tolan et al 2023

Curated in GEE by: Meta & WRI

Keywords: DiNOv2, Maxar, Self Supervised Learning (SSL), Canopy height, Global dataset, Meta, WRI

Last updated on GEE: 2024-04-13