# Izembek Lagoon Waterfowl Aerial Imagery (Alaska)

## Facts

- Provider: U.S. Geological Survey Alaska Science Center
- License: CC0-1.0 (https://lila.science/datasets/izembek-lagoon-waterfowl/)
- Format: JPEG (in sampled files)
- Stored at: Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/izembek-lagoon-birds
- Access: public, readable without an account
- DOI: https://doi.org/10.5066/P9UHP1LE
- Category: Environmental Science
- Source: https://doi.org/10.5066/P9UHP1LE
- Page: https://scigantic.com/archive/1315f46a-fb20-5311-a821-206a53c4755d
- Keywords: Environmental Science, JPEG, Azure Blob Storage

## About

9,267 high-resolution (8688x5792) aerial images from fall waterfowl surveys at Izembek Lagoon, Alaska, 2017 to 2019, with 521,270 bounding boxes: Brant (424,790), Canada goose (47,561), gull (5,631), emperor goose (2,013) and other (5,631). Birds were annotated as points and converted to fixed-size boxes centred on each point for detector training; about half the images (4,281) are empty. It is a training-friendly subset of the 1.82 TB USGS data release, which keeps all non-empty images but few empty ones, so LILA advises evaluating against the original before claiming real-world precision and recall. Annotations are COCO Camera Traps JSON (pycocotools, json). Layout (measured 2026-11-13): unzipped JPEG images in images/ (about 18 MB each in the files listed), plus a 132.7 GB zip of the same images and a 10 MB metadata zip. The images are available as loose files, so they read directly from the read-only mount. Released under CC0 1.0; cite Weiser et al. 2022, USGS data release doi:10.5066/P9UHP1LE.

## Load the data

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

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

## Data structure

File types in sampled files: JPEG

Example file: `images/2017_Replicate_2017-09-30_Cam1_293A0006.JPG`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/1315f46a-fb20-5311-a821-206a53c4755d
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/1315f46a-fb20-5311-a821-206a53c4755d
- Over MCP: `get_schema_card` with id `1315f46a-fb20-5311-a821-206a53c4755d` at https://api.scigantic.com/mcp

## Related topics

- [Environmental Science datasets](https://scigantic.com/topics/environmental-science)
- [JPEG datasets](https://scigantic.com/topics/jpeg)
