# Nkhotakota Camera Traps (Malawi)

## Facts

- Provider: Cara Appel, USDA Forest Service, African Parks and DNPW Malawi
- License: CDLA-Permissive-1.0 (https://lila.science/datasets/nkhotakota-camera-traps/)
- Format: JPEG (in sampled files)
- Stored at: Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/nkhotakota-camera-traps
- Access: public, readable without an account
- Category: Environmental Science
- Source: https://lila.science/datasets/nkhotakota-camera-traps/
- Page: https://scigantic.com/archive/6158a369-6c15-5357-ba9e-59e0aaa3ce3c
- Keywords: Environmental Science, camera traps, JPEG, Azure Blob Storage

## About

321,562 camera trap images from Nkhotakota Wildlife Reserve, Malawi, run by African Parks Network and the Malawi Department of National Parks and Wildlife with technical support from the USDA Forest Service. LILA states labels for 46 taxa with per-image animal counts, manually drawn bounding boxes on 33,813 images, and 164,139 empty false triggers; human images were removed. Classes mix species and higher groups; the most common are yellow baboon (54,119), cape bushbuck, bushpig, small antelope and elephant. Train, validation and test splits used for a YOLOv4 detector are in the metadata. Labels are in COCO Camera Traps JSON (open with json, pandas or pycocotools). Layout (measured 2026-11-13): 69 unzipped camera-site folders (e.g. B10/, J21/, T26/) with dated subfolders of JPEG files and an 8 MB metadata zip. Images are individual files, not zip archives, so they read directly from the read-only mount. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0; cite Appel et al., Ecological Applications 2025 (Njobvu-AI).

## Load the data

```python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/nkhotakota-camera-traps/')[: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: `B10/B10-A-2020-08-22/B10-A-2020-08-22_(14).JPG`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/6158a369-6c15-5357-ba9e-59e0aaa3ce3c
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/6158a369-6c15-5357-ba9e-59e0aaa3ce3c
- Over MCP: `get_schema_card` with id `6158a369-6c15-5357-ba9e-59e0aaa3ce3c` 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)
