Species Prediction of Marine Ragworms Based on Web-based Deep Learning Tool

Abstract

Species identification has been performed using morphological features and molecular techniques between each species. Recently, advances in machine learning technology have been applied to animal and plant identification based on deep learning approach with images. In this study, we constructed the deep learning model to predict 16 species of marine ragworms using the Teachable Machine which is a web-based tool. We have trained the deep learning model with 865 images including key characters of 16 species and measured prediction accuracy using 3-fold cross validation. The results showed 94% sensitivity, 99% specificity, and 99% accuracy. The deep learning model for marine ragworms is freely available at forensicdna.kr/ML/ nereididae.