Accelerating the release of biodiversity data from natural history collections with automated insect classification
Increasing demand for digital access requires Natural History Collections to look at innovative ways to improve their sorting and digitization workflow. To allow more people to contribute to these processes, we developed an automated species identification app. After including 560 species of butterflies in the first app release, the project now aims to expand to more insect groups.
Specimens housed in Natural History Collections (NHCs) are needed as reliable historical baselines for researching climate change and biodiversity loss. But while demand for digital access to these historical records continues to grow, funding and availability of classification experts continues to be a challenge.
To assist collections and enable more people to participate in digitization projects, our classification app has been optimised for automatically classifying large quantities of preserved specimens, empowering a much larger community of volunteers and assistants to become an integral part of their collection’s workflow. Through the release of this app we hope to accelerate the sorting and digitization process, resulting in faster release of historical data and lower digitization and curation costs.
The app implements a hierarchical classification technique, researched by former Library Lab fellow Ankit Dhall (more detail here),and has been specifically designed for Collection workers; focusing on an ergonomic layout, fast results and minimising clicks. It is available now in the App store for iOS, with the Android version expected to be released later this year. In case you would like to be invited to use the app and create an account, or have any questions, please contact us here at the Library Lab or through the BioDex website. As an alternative to using the app, it is also possible to integrate BioDex into existing workflows by using the classification API which allows for the predicted species to be returned programmatically. Allowing the potential Collections’ existing digitization software to interface with a standalone classification service.
1. January 2020 – 30. September 2020
Collection Manager, ETH Zurich
Michael is head of the Entomological Collection of ETH Zurich. He is the originator of the idea behind BioDex and supported this project with his domain knowledge.
We use cookies to help us give you the best possible user experience on our website. By continuing to browse the site you are agreeing to the use of cookies. More information about privacy can be found here.
Accept
