# NOAA Arctic Seals 2019 (Kotzebue aerial RGB and thermal)

## Facts

- Provider: NOAA Alaska Fisheries Science Center
- License: CDLA-Permissive-1.0 (https://lila.science/datasets/noaa-arctic-seals-2019/)
- Format: CSV (in sampled files)
- Stored at: Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/noaa-kotz
- Access: public, readable without an account
- Category: Environmental Science
- Source: https://lila.science/datasets/noaa-arctic-seals-2019/
- Page: https://scigantic.com/archive/34978a6c-f45d-5fee-a285-ff736e8f373b
- Keywords: Environmental Science, CSV, Azure Blob Storage

## About

Around 80,000 colour and thermal infrared (IR) images from aerial survey flights in Alaska by the NOAA Alaska Fisheries Science Center in 2019, annotated with about 28,000 bounding boxes on ice seals (about 14,000 on colour and 14,000 on thermal images). Metadata is a CSV with one row per detection, giving the detection_type class (e.g. ringed_seal, ringed_pup), pixel boxes on the RGB image and the paired IR image, and both image paths; a file list includes empty images. Read it with pandas. Layout (measured 2026-11-13): unzipped folders Images/ (per-flight subfolders fl04 to fl07 and an image CSV), Detections/, Footprints/ and Homographies/, plus surv_test_kamera_files.txt. All images are individual files, not zip archives, so they open directly on the read-only mount. Use for seal detection, RGB-thermal fusion, multimodal registration with the provided homographies, and marine mammal abundance surveys. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0; cite Alaska Fisheries Science Center, 2021: A Dataset for Machine Learning Algorithm Development.

## Load the data

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

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

## Data structure

File types in sampled files: CSV

Example file: `Detections/surv_test_kamera_detections_20210212.csv`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/34978a6c-f45d-5fee-a285-ff736e8f373b
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/34978a6c-f45d-5fee-a285-ff736e8f373b
- Over MCP: `get_schema_card` with id `34978a6c-f45d-5fee-a285-ff736e8f373b` at https://api.scigantic.com/mcp

## Related topics

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