ADAF
Detects archaeological features such as barrows, ringforts and enclosures in lidar terrain models.
- Field
- Geomorphology
- Method
- Deep learning
- Data it takes
- imagery
- License
- Apache-2.0 code, CC-BY-SA-4.0 weights — restricted use
ADAF works on relief visualizations computed from a lidar terrain model. It runs an HRNet segmentation model and a Faster R-CNN detector over simplified local relief maps and returns located candidate features.
The weights were trained on Irish and Slovenian survey data. What comes back is a set of candidates for field checking, and the model carries no knowledge of period or context.
The code is Apache-2.0 and the weights are CC-BY-SA-4.0. Share-alike attaches to derivative works, so anything trained on top of these weights inherits the same condition. Attribution to the ADAF authors is required.
Catalog entry last checked 2026-09-08. All models →
Run ADAF 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