Machine learning recovers folk classification of Banisteriopsis caapi from herbarium leaves an ayahuasca liana
iScience April 15, 2026 Scheila Cristina Biazatti, Deborah Bambil, Rômulo Môra et al.
Machine learning analysis of morphological traits within a single plant species shows only partial agreement with traditional ethnobotanical classifications. Confusion matrix and similarity network analyses revealed that automated methods can validate folk taxonomies by detecting subtle variation, though they do not fully replicate previous classification systems. Integrating indigenous knowledge with computational approaches enables systematic assessment of how local communities categorize biological diversity.