Loading...
Assessing the potential for deep learning and computer vision to identify bumble bee species from images
Spiesman, Brian Gratton, Claudio Hatfield, Richard G. Hsu, William H. Sarina Jepsen McCornack, Brian Patel, Krushi Wang, Guanghui
Spiesman, Brian
Gratton, Claudio
Hatfield, Richard G.
Hsu, William H.
Sarina Jepsen
McCornack, Brian
Patel, Krushi
Wang, Guanghui
Abstract
Pollinators are undergoing a global decline. Although vital to pollinator conservation and ecological research, species-level identification is expensive, time consuming, and requires specialized taxonomic training. However, deep learning and computer vision are providing ways to open this methodological bottleneck through automated identification from images. Focusing on bumble bees, we compare four convolutional neural network classification models to evaluate prediction speed, accuracy, and the potential of this technology for automated bee identification. We gathered over 89,000 images of bumble bees, representing 36 species in North America, to train the ResNet, Wide ResNet, InceptionV3, and MnasNet models. Among these models, InceptionV3 presented a good balance of accuracy (91.6%) and average speed (3.34 ms). Species-level error rates were generally smaller for species represented by more training images. However, error rates also depended on the level of morphological variability among individuals within a species and similarity to other species. Continued development of this technology for automatic species identification and monitoring has the potential to be transformative for the fields of ecology and conservation. To this end, we present BeeMachine, a web application that allows anyone to use our classification model to identify bumble bees in their own images.
Description
Date
2021-04-07
Journal Title
Journal ISSN
Volume Title
Publisher
Nature Research
Files
Loading...
Spiesman_2021.pdf
Adobe PDF, 1.89 MB
Research Projects
Organizational Units
Journal Issue
Keywords
Machine learning, Ecology, Biodiversity, Community ecology, Conservation biology
Citation
Spiesman, B.J., Gratton, C., Hatfield, R.G. et al. Assessing the potential for deep learning and computer vision to identify bumble bee species from images. Sci Rep 11, 7580 (2021). https://doi.org/10.1038/s41598-021-87210-1