Hunting-pit detection

Detects hunting pits in 0.5 m lidar DEMs and writes them as polygons.

Field
Geomorphology
Method
Deep learning
Data it takes
imagery
License
MIT

The model detects hunting pits, hollows dug to trap game, in 0.5 m lidar DEMs and writes them as polygons. It was trained and tested on 2,519 hand-mapped pits in northern Sweden, 80% for training and 20% for testing (Lidberg et al. 2024, Journal of Field Archaeology 49:395–405). On the test pits it found 70%, 15% of its detections were false, and F1 was 0.76.

The code and the weights are MIT-licensed.

Upstream project → · Paper →

Catalog entry last checked 2026-10-11. All models →

Run Hunting-pit detection on your data

The lab runs this on its own compute, in a container, with the inputs and parameters recorded alongside the result. Initial scoping conversations are free.

Contact the Lab