Biome Health Project Maasai Mara 2018
- Provider
- WWF-UK and University College London (Kate Jones)
- License
- CDLA-Permissive-1.0 (source)
- Format
- JPEG (in sampled files)
- Stored at
- Azure Blob Storage, https://lilawildlife.blob.core.windows.net/lila-wildlife/biome-health-project-maasai-mara-2018
- Access
- Free and public. No account with the data provider is needed.
- Category
- Environmental Science
- Source
- https://lila.science/datasets/biome-health-project-maasai-mara
About Biome Health Project Maasai Mara 2018
37,075 camera trap images from the WWF-UK and UCL Biome Health Project site in the Maasai Mara, Kenya, forming the training, test and validation sets of the Maasai Mara classifier. One image was labeled per five-minute period across 176 camera sites. LILA states labels for 100 categories, mostly species plus groups such as shoat (sheep and goats combined), covering wild mammals, wild birds and domestic mammals; blank and human images were removed. Labels are in COCO Camera Traps JSON (open with json, pandas or pycocotools), with species tags and location identifiers. Layout (measured 2026-11-13): JPEG images sit as loose files directly in the dataset folder (the first two listing pages held 400 JPEGs totaling about 0.67 GB); they are not packaged as zip archives, so they can be read straight from the read-only mount. Useful for East African savanna species classification, livestock and wildlife coexistence research and community conservancy monitoring. Released by LILA BC under the Community Data License Agreement (permissive variant), CDLA-Permissive-1.0; cite Connolly et al., Sustainable cattle management by communities supports African wildlife, bioRxiv 2025.
How to access Biome Health Project Maasai Mara 2018 in Python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='lilawildlife', anon=True)
fs.ls('lila-wildlife/biome-health-project-maasai-mara-2018/')[:10]Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
File types in sampled files: JPEG
Files
Example file: 2018_MN02_000061.JPG
Path pattern: {YYYY}_{CODE}_{token}
Analyze this dataset without downloading it
On Scigantic, Biome Health Project Maasai Mara 2018 opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Environmental Science datasets
- SWAN Ocean Surface Wave Hindcast 1979-2020, US East Coast, Gulf of Mexico, Puerto Rico and US Virgin Islands (raw model output)
- Archival Tag Depth and Temperature Records from Eastern Bering Sea Snow Crab, 2010-2012
- USGS National Hydrography
- InsectSet459: 26,399 audio recordings of 459 Orthoptera and Cicadidae species
- Hawaii Ground Beetles: NEON PUUM Carabid Specimen Images with Elytra and Pronotum Measurements
- Oregon Critters Camera Traps
- ENA24-detection
- FloodCastBench: High- and Low-Fidelity Flood Inundation Simulations for Flood Forecasting (Australia, UK, Pakistan, Mozambique)