Machine Learning in Ethnobotany

Abstract

We describe new opportunities created by bring A.I. to the field of ethnobotany. In particular we describe a novel approach to ethnobotany documentation that harnesses machine learning opportunities, specifically for the documentation of traditional ecological knowledge with mobile phones in emerging economies. Using a case study on the island of Bali as a departure point, the project maps out machine learning approaches to documentation and responds to technology and capital gradients between research contexts in the global north and south in an attempt to capture knowledge that might otherwise not be represented.

A Plant Recognition Approach Using High Resolution Network

“…We evaluate the performance of plant recognition on the Bali26 dataset [46,47] which consists of 26 categories of ethnobotanically significant seeds, fruits, plants, and trees. The number of images is from 1000 to 2500 for each category.…”