Best practices for the application of computer vision-based machine learning in archaeology
• Defines seven best practices for CV-based ML in archaeology. • Links sources, preprocessing, training, post-treatment and validation. • Shows how to reduce false positives in low-density survey settings. • Integrates explainability, cross-validation and ethical responsibility. • Promotes reproducible, FAIR and archaeologically informed AI workflows.
Authors
- Héctor A. Orengo (ORCID: https://orcid.org/0000-0002-9385-2370)
- Felipe Lumbreras (ORCID: https://orcid.org/0000-0003-2887-8053)
- Iban Berganzo-Besga (ORCID: https://orcid.org/0000-0002-6161-2452)
Institutions
- Institució Catalana de Recerca i Estudis Avançats (ES)
- Universitat Autònoma de Barcelona (ES)
- Barcelona Supercomputing Center (ES)
- Centre for Research on Ecology and Forestry Applications (ES)
- Universitat Politècnica de Catalunya (ES)
Publication Details
- Journal
- Journal of Archaeological Science
- Published
- 2026-05-27
- DOI
- https://doi.org/10.1016/j.jas.2026.106577
- Primary Topic
- Image Processing and 3D Reconstruction
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Ministerio de Ciencia, Innovación y Universidades
- Agència de Gestió d'Ajuts Universitaris i de Recerca