Cloud-native version of the Version 2 High Resolution Canopy Height Maps by WRI and Meta from https://registry.opendata.aws/dataforgood-fb-forestsv2/
A cloud-native repackaging of Meta's DINOv3 Global Canopy Height Map v2 (ml3): a global ~1.19 m canopy-height raster (213,109 Web-Mercator tiles).
Everything lives in this one bucket with CORS + HTTP range support, so it streams directly to browsers and analysis tools — no credentials, no second host:
0 is both true-zero and
no-data (the source sets no explicit nodata mask).This is a static STAC catalog: a collection.json plus a stac-geoparquet
items.parquet (213,109 Items). No STAC API server is required. The parquet is
written in 54 quadkey-sorted (Z-order) row groups with per-group bbox statistics, so a
spatial query reads only the matching byte ranges over HTTP — e.g. a city-scale bbox
touches ~3 of 54 row groups, skipping ~94% of the file. Point any of these tools straight
at the public URL:
https://data.source.coop/tge-labs/meta-chm-v2/stac/items.parquet
Collection metadata (pystac):
Search the Items — pick your tool, all stream + prune row groups:
Also works: geopandas read_parquet(..., bbox=...), Polars scan_parquet, and the
stac-geoparquet library. For teams that specifically need the pystac-client API
(Client.open(...).search(...)), serve items.parquet behind
stac-fastapi-geoparquet — no
database required.
Search → xarray (odc.stac): turn found Items into a lazily-loaded, dask-backed
xarray cube reading the COGs directly (EPSG:3857, no reprojection):
See examples/search_and_read.py and examples/odc_stac_load.py in the
chm-zarr repo.
The GeoZarr is virtual — its chunks are byte-range references into the COGs in this same
bucket, so it carries the full pyramid (1x native … 64x) with no duplicated pixels.
Also available as a managed Arraylake repo: taylor-geospatial/meta-chm-v2.
CC-BY-4.0. Underlying data © Meta / Data for Good; repackaging by Taylor
Geospatial Engine Labs. See LICENSE. Cite Tolan et al. (2024),
https://arxiv.org/abs/2304.07213, and Brandt et al. (2026, CHMv2),
https://arxiv.org/abs/2603.06382.
The GeoZarr store holds only chunk references (offsets/lengths) into the COGs in this
bucket (chm/), so it is self-contained — no dependency on Meta's bucket.