Machine learning recovers folk classification of <i>Banisteriopsis caapi</i> from herbarium leaves an ayahuasca liana.

Abstract

Ayahuasca refers to an entheogenic brew and its main vine, <i>Banisteriopsis caapi</i>, whose high morphological diversity underlies traditional folk classifications. This study evaluated whether machine learning algorithms can recover folk classifications using images of dried leaves. We analyzed 47 vine plants, mainly <i>B. caapi</i> folk types and <i>Diplopterys cabrerana</i> as an outgroup, using adaxial and abaxial leaf image features related to color, shape, texture, and filters. All evaluated algorithms showed statistically similar performance; however, support vector machine (SVM) achieved the highest accuracy, reaching 70% overall and over 90% for the folk types <i>Hybrid</i> and <i>Arara</i>, and the related outgroup species <i>D. cabrerana</i>. Lower accuracy in <i>Cabi</i> and <i>Quebrador</i> 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.

Topics & conditions

Detected automatically by Psychedelic Commons from the title and abstract, not labels from the source. They may be incomplete.

Keywords