# HKH Glacier Mapping (ICIMOD, Landsat 7 and SRTM)

## Facts

- Provider: International Centre for Integrated Mountain Development (ICIMOD)
- License: CDLA-Permissive-1.0 (https://lila.science/datasets/hkh-glacier-mapping)
- Stored at: Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/icimod-glacier-mapping
- Access: public, readable without an account
- Category: Environmental Science
- Source: https://lila.science/datasets/hkh-glacier-mapping
- Page: https://scigantic.com/archive/1340c747-70fb-5c68-9375-ee141b0b3b2f
- Keywords: Environmental Science, image segmentation, satellite imagery, Azure Blob Storage

## About

Imagery of the Hindu Kush Himalaya (HKH), the Third Pole, paired with ICIMOD glacier polygons for 2002 to 2008, to train glacier segmentation models. LILA describes 35 Landsat 7 tiles as 15-channel GeoTIFFs at 30 m (LE7 bands B1 to B8 and BQA, NDVI, NDSI, NDWI, SRTM elevation and slope), 14,190 numpy patches of 512x512x15 with 512x512x2 masks for clean-ice and debris-covered glaciers, shapefile labels, and a GeoJSON of patch metadata. Python and PyTorch code is on GitHub. Layout (measured 2026-11-13): the folder holds one packaged archive, hkh_patches.tar.gz (73.9 GB); nothing is extracted in the container, so on the read-only mount copy the tarball to local storage and extract it before opening the .npy files with numpy and the GeoTIFFs with rasterio. Annotations are released under CDLA-Permissive-1.0 and the Landsat and SRTM data are public domain; credit ICIMOD for the glacier labels.

## Load the data

```python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/icimod-glacier-mapping/')[:10]
```

Lists the files with anonymous access. Runs on any machine, with no cloud account.

## Data structure

Example file: `hkh_patches.tar.gz`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/1340c747-70fb-5c68-9375-ee141b0b3b2f
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/1340c747-70fb-5c68-9375-ee141b0b3b2f
- Over MCP: `get_schema_card` with id `1340c747-70fb-5c68-9375-ee141b0b3b2f` at https://api.scigantic.com/mcp

## Related topics

- [Satellite imagery datasets](https://scigantic.com/topics/satellite-imagery)
- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
- [Environmental Science datasets](https://scigantic.com/topics/environmental-science)
