Deep learning black box and pattern recognition analysis using Guided Grad-CAM for phytolith identification
The analysis of the microscope images using Guided Grad-CAM has validated the established patterns in phytolith identification, such as highlighting the significance of the wave pattern. Additionally, it revealed that varying phytolith characteristics might be prominent for different genera and led to the discovery that dendritic long-cell shape, as an independent category, is also distinctive. This research is part of an effort to establish a set of computer vision best practices in computational archaeology.
Authors
- Iban Berganzo‐Besga (ORCID: https://orcid.org/0000-0002-6161-2452)
- Héctor A. Orengo (ORCID: https://orcid.org/0000-0002-9385-2370)
- Monica N. Ramsey (ORCID: https://orcid.org/0000-0002-1223-1725)
- Felipe Lumbreras (ORCID: https://orcid.org/0000-0003-2887-8053)
Institutions
- Institució Catalana de Recerca i Estudis Avançats (ES)
- Universitat Autònoma de Barcelona (ES)
- Barcelona Supercomputing Center (ES)
- Amgen (Canada) (CA)
- Canadian Celiac Association (CA)
- Centre for Research on Ecology and Forestry Applications (ES)
- Institute of Archaeology (CN)
- Institut Català d'Arqueologia Clàssica (ES)
- Universitat Politècnica de Catalunya (ES)
Publication Details
- Journal
- Annals of Botany
- Published
- 2025-05-30
- DOI
- https://doi.org/10.1093/aob/mcaf088
- Citations
- 3
- Primary Topic
- Silicon Effects in Agriculture
- Type
- article
- Field-Weighted Citation Impact
- 5.25
Funders
- Compute Canada
- Leverhulme Trust
- Alliance de recherche numérique du Canada
- European Regional Development Fund
- Agencia Estatal de Investigación
- McDonald Institute for Archaeological Research