The BirdNET app, a free machine-learning-powered application that can recognize over 3,000 different birds by sound alone, produces accurate scientific data and makes it simpler for users to contribute citizen-science data on birds by merely recording noises.
The BirdNET app lowers the barrier to citizen science because it doesn’t require bird-identification expertise to participate, according to a study by Connor Wood and colleagues from the K. Lisa Yang Center for Conservation Bioacoustics at the Cornell Lab of Ornithology, U.S., published on June 28 in the open access journal PLOS Biology.
Simply keep an ear out for birds, then tap the app to capture them. BirdNET employs artificial intelligence to recognize the species automatically based on sound, documenting the identification for later use in study.
“Our guiding design principles were that we needed an accurate algorithm and a simple user interface,” said study co-author Stefan Kahl in the Yang Center at the Cornell Lab, who led the technical development.
“Otherwise, users would not return to the app.” The results exceeded expectations: Since its launch in 2018, more than 2.2 million people have contributed data.”
The authors chose four test instances in which conventional research had already produced solid results in order to determine whether the app could produce trustworthy scientific data.
Their findings demonstrate that the BirdNET app data accurately traced a bird migration on both continents and successfully recreated known patterns of song dialects in North American and European songbirds.
The first step in what they hope would be a long-term, global study effort on not only birds but ultimately all wildlife and even entire soundscapes was validating the trustworthiness of the app data for research purposes.
Our guiding design principles were that we needed an accurate algorithm and a simple user interface. Otherwise, users would not return to the app.The results exceeded expectations: Since its launch in 2018, more than 2.2 million people have contributed data.
Stefan Kahl
The authors are trying to make the complete dataset open, and the data used in the four test scenarios is already available to the general public.
“The most exciting part of this work is how simple it is for people to participate in bird research and conservation,” Wood adds.
“You don’t need to know anything about birds, you just need a smartphone, and the BirdNET app can then provide both you and the research team with a prediction for what bird you’ve heard. This has led to tremendous participation worldwide, which translates to an incredible wealth of data. It’s really a testament to an enthusiasm for birds that unites people from all walks of life.”
The citizen-science apps eBird, NestWatch, and Project FeederWatch, which collectively have generated more than 1 billion bird observations, sounds, and photos from participants around the world for use in science and conservation, are also a part of the Cornell Lab of Ornithology’s toolkit. These include the educational Merlin Bird ID app.
