Machine learning recovers folk classification of Banisteriopsis caapi from herbarium leaves an ayahuasca liana
reflects morphological overlap. Confusion matrix and similarity network analyses showed only partial agreement with previous ethnobotanical classifications. Focusing on subtle variation within a single species, this study demonstrates that integrating traditional knowledge with machine learning enables automated validation of folk taxonomies.
Authors
- Rômulo Môra (ORCID: https://orcid.org/0000-0002-2234-6753)
- Scheila Cristina Biazatti (ORCID: https://orcid.org/0000-0001-5017-9780)
- Regina Célia de Oliveira (ORCID: https://orcid.org/0000-0001-7891-2630)
- Lúcio Flávio de Alencar Figueiredo (ORCID: https://orcid.org/0000-0001-8868-1717)
- Deborah Bambil
Institutions
- Universidade Federal de Rondônia (BR)
- Universidade de Brasília (BR)
- Brazilian Agricultural Research Corporation (BR)
- Institute of Physics (AZ)
- Universidade Federal Rural de Pernambuco (BR)
Publication Details
- Journal
- iScience
- Published
- 2026-04-15
- DOI
- https://doi.org/10.1016/j.isci.2026.115753
- Primary Topic
- Psychedelics and Drug Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Fundação de Apoio à Pesquisa do Distrito Federal