Towards Monarch Butterfly Preservation: Applications of AI in Species Identification

This study developed a deep-learning model to distinguish monarch butterflies from visually similar species, achieving 83.5% accuracy on the testing set. The model could help novice conservationists identify monarchs more efficiently and support monitoring and conservation efforts.

Pollinators, especially monarch butterflies, are experiencing significant population declines, posing a threat to biodiversity and ecosystem stability. Therefore, it is crucial to prioritize their conservation. However, these butterflies are visually similar to other Lepidoptera species and thus pose significant challenges in field-based identification and monitoring. This project aimed to create a deep-learning classification model to serve as a tool for differentiating monarch butterflies from their various look-alikes. A convolutional neural network (CNN) was trained on labeled butterfly images sourced from publicly available datasets (Kaggle and images.cv ). Data preprocessing was performed to optimize performance. The trained model achieved an accuracy of 88% on the training dataset, and it was able to correctly identify 83.5% monarch butterflies in the testing set. We aim to further increase the accuracy by increasing monarch images in the training dataset. This model can thus serve as a practical tool for novice conservationists to efficiently identify monarch butterflies and thereby support conservation efforts.

Explore More!

Research Paper

Published Paper