Work

Machine learning recovers folk classification of Banisteriopsis caapi from herbarium leaves an ayahuasca liana

Year: 2026

Type: article

Abstract: 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.

Source: iScience

DOI: 10.1016/j.isci.2026.115753

Authors: Scheila Cristina Biazatti, Deborah Bambil, Rômulo Môra, Lúcio Flávio de Alencar Figueiredo, Regina Célia de Oliveira

Institutions: Universidade Federal de Rondônia, Universidade de Brasília, Brazilian Agricultural Research Corporation, Embrapa Recursos Genéticos e Biotecnologia, Universidade Federal Rural de Pernambuco

Language: English

Topic: Ethnobotanical and Medicinal Plants Studies

Subfield: Plant Science

Field: Agricultural and Biological Sciences

Domain: Life Sciences

Open Access status: gold

Estimated APC paid: $3,240

Funders: Conselho Nacional de Desenvolvimento Científico e Tecnológico, Fundação de Apoio à Pesquisa do Distrito Federal