# Duck Pictures in Wetlands (Finland)

## Facts

- Provider: Basile Marteau and collaborators
- License: CDLA-Permissive-1.0 (https://lila.science/datasets/duck-pictures-in-wetlands/)
- Format: JPEG (in sampled files)
- Stored at: Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/duck-pictures-in-wetlands
- Access: public, readable without an account
- Category: Environmental Science
- Source: https://lila.science/datasets/duck-pictures-in-wetlands/
- Page: https://scigantic.com/archive/f7c93c86-646c-5735-a6ac-dd6b17e0e4c6
- Keywords: Environmental Science, camera traps, JPEG, Azure Blob Storage

## About

674,426 camera trap images of birds and mammals from a variety of wetland sites in Finland. Where possible, birds are labeled with adult or juvenile status and counts. LILA lists the most common categories as empty (660,935 images), unidentified waterbird (5,718), adult mallard (3,973) and adult goldeneye (2,205), so the set is dominated by empty frames, which suits blank-filtering and rare-class waterfowl detection work. Labels are in COCO Camera Traps JSON (open with json, pandas or pycocotools), with species tags and location identifiers. Layout (measured 2026-11-13): 32 unzipped site folders named after the wetlands (e.g. Halsjarvi/, Lapinjarvi/, kuivaskorpi/), each holding dated camera subfolders of JPEG files, plus an 8 MB COCO metadata zip. The images are individual files, not zip archives, so they can be read straight from the read-only mount. Useful for duck and waterbird monitoring, boreal wetland ecology, age-class classification and counting. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0; contact Basile Marteau for questions.

## Load the data

```python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/duck-pictures-in-wetlands/')[: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: `Dylanplotti/100HUNTI/IMAG0002.JPG`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/f7c93c86-646c-5735-a6ac-dd6b17e0e4c6
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/f7c93c86-646c-5735-a6ac-dd6b17e0e4c6
- Over MCP: `get_schema_card` with id `f7c93c86-646c-5735-a6ac-dd6b17e0e4c6` at https://api.scigantic.com/mcp

## Related topics

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