Researchers have developed a new application which can identify more than 3,000 birds just by sound. The app, called the BirdNET app, is a free machine-learning powered tool that can identify more than 3,000 birds by sounds alone, and generates reliable scientific data. This makes it easier for people to contribute citizen-science data on birds by simply recording sounds.
The study describing the findings was recently published June 28 journal Public Library of Science. The BirdNET app lowers the barrier to citizen science because it does not require bird-identification skills to participate, the study suggests. When people hear a bird chirp or sing, they can simply tap the app to record the sounds. The study was led by researchers at Cornell Lab of Ornithology, Cornell University.
How The BirdNET App Works
According to the study, the BirdNET app uses artificial intelligence to automatically identify the species by sound and captures the recording for use in research.
Since the launch of the app in 2018, more than 2.2 million people have contributed data. In order to test whether the app could generate reliable scientific data, the researchers selected four test cases in which conventional research had already provided robust answers. The study found that the BirdNET app data successfully replicated known patterns of song dialects in North American and European songbirds and accurately mapped a bird migration on both continents.
Validating the reliability of the app data for research purposes was the first step in what the researchers hope will be a long-term, global research effort. This research effort will be not just for birds, but ultimately for all wildlife and entire soundscapes.
In a statement released by Cornell University, Connor Wood, the lead author on the paper, said the most exciting part of the work is how simple it is for people to participate in bird research and conservation.
Wood added that one does not need to know anything about birds, they just need a smartphone, and the BirdNET app can then provide both them and the research team with a prediction for which bird they have heard. This has led to tremendous participation worldwide, which translates to an incredible wealth of data, and it is really a testament to an enthusiasm for birds that unites people from all walks of life, Wood further said.
Stefan Kahl, co-author on the paper, said the guiding design principles were that the researchers needed an accurate algorithm and a simple user interface because otherwise, users would not return to the app.
The study demonstrated that the BirdNET app data successfully replicated the known distribution pattern of song-types among white-throated sparrows, and the seasonal migratory ranges of the brown thrasher.
The app is available for both iOS and Android devices.