Researchers have developed the BirdNet app that makes it easy for people to participate in bird research and conservation. Credit: Ashqur Rahman, Yang Center/Cornell Lab of Ornithology (CC-BY 4.0, Creativecommons.org/licenses/by/4.0/)
The BirdNet app, a free machine learning-based tool that can identify more than 3,000 birds by sound alone, generates reliable scientific data and makes it easy for people to contribute citizen science data about birds simply by recording sounds.
An article published June 28 in the open-access journal PLOS Biology by Conor Wood and colleagues at the Lisa Yang Center for Conservation Bioacoustics, Cornell Lab of Ornithology, USA suggests that the BirdNet app breaks the barrier for citizen science lowers as it does not require bird-recognition skills to participate. Users simply listen to the birds and tap the app to record them. BirdNet uses artificial intelligence to automatically identify species by sound and capture records for research use.
“Our guiding design principles were that we needed a precise algorithm and a simple user interface,” said Stephen Kahl, study co-author from Cornell Lab’s Yang Center, who led the technology development. “Otherwise, users won’t return to the app.” The results exceeded expectations: since launch in 2018, more than 2.2 million people have contributed data.
To test whether the app can generate reliable scientific data, the authors selected four test cases where conventional research had already provided strong answers. Their results show that the BirdNet app data successfully replicated known songbird patterns in North American and European songbirds, accurately mapping a bird migration across both continents.
People can easily get involved in bird research and conservation through the recently developed BirdNet app. Credit: Stephen Kahl, Yang Center/Cornell Lab of Ornithology (CC-BY 4.0, creativecommons.org/licenses/by/4.0/)
Validating the reliability of the app’s data for research purposes was the first step in a hopefully long-term, global research effort – not just for birds, but ultimately for all wildlife and even sounds as a whole. The data used in the four test cases is publicly available, and the authors are working to open the full data set.
“The most exciting thing about this work is how easy it is for people to get involved in bird research and conservation,” says Wood. “You don’t need to know anything about birds, all you need is a smartphone and the BirdNet app can provide both you and the research team with a prediction of which bird you’ve heard. There was tremendous turnout, resulting in an incredible wealth of data. It really is a testament to the passion for birds that unites people from all walks of life.”
The BirdNet app is part of Cornell Lab’s suite of tools for ornithology, which includes the educational app Merlin Bird ID and the citizen science apps eBird, Nestwatch and Project FeederWatch, which together collect more than 1 billion bird observations, sounds and generated photos. By participants around the world for use in science and conservation.
Bird call app downloaded millions of times worldwide – now available for iOS devices
More information:
Machine Learning-Based BirdNet App Breaks Down Barriers to Global Avian Research by Enabling Citizen Science Partnership, PLOS Biology (2022). DOI: 10.1371/journal.pbio.3001670 Provided by the Public Library of Science
Citation: Identification Bird Species by Sound, an App Opens New Avenues for Citizen Science (2022, June 28) Retrieved June 29, 2022
This document is protected by copyright. No part may be reproduced without written permission except for fair use for purposes of personal study or research. The content is for informational purposes only.
source
