BirdNET: Free App Identifies Bird Species by Sound
By Science News Staff / Source
The BirdNET app is a free bird sound identification app for Android and iOS that includes over 3,000 bird species. Ornithologists hope this app will reduce barriers to citizen science and generate tens of millions of bird observations globally.
Wood et al. hope that the BirdNET app and similar projects will enable new opportunities for avian research and conservation. Image credit: Ashakur Rahaman / K. Lisa Yang Center for Conservation Bioacoustics, Cornell Lab of Ornithology.
“The ubiquity of smartphones combined with the power of new machine learning algorithms presents an opportunity to promote positive interactions between humans and birds and thus create new possibilities for avian research,” said lead author Dr. Connor Wood from the K. Lisa Yang Center for Conservation Bioacoustics at the Cornell Lab of Ornithology and his colleagues.
“We
present the BirdNET app, a free program capable of identifying over 3,000 bird
species by sound alone.”
BirdNET
uses artificial intelligence to automatically identify the species by sound.
It
allows users to record audio on a smartphone and transmit that audio and
metadata (date, time, and location) to the BirdNET server, and a bird species
identification is provided with a qualitative confidence score.
The
raw audio, quantitative confidence score, and metadata are saved on the server
for subsequent research usage. All observations are anonymized, and no user
data are stored.
“Our
guiding design principles were that we needed an accurate algorithm and a
simple user interface. Otherwise, users would not return to the app,” explained
co-author Dr. Stefan Kahl, also from the K. Lisa Yang Center for Conservation
Bioacoustics at the Cornell Lab of Ornithology and his colleagues.
To
test whether the app could generate reliable scientific data, the authors
selected four test cases in which conventional research had already provided
robust answers.
Their
results show that 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 they hope will be a long-term, global research effort — not just for
birds, but ultimately for all wildlife and indeed entire soundscapes.
Data
used in the four test cases is publicly available, and the authors are working
on making the entire dataset open.
“The
most exciting part of this work is how simple it is for people to participate
in bird research and conservation,” Dr. Wood said.
“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
team’s work appears in the journal PLoS Biology.
_____
C.M.
Wood et al. 2022. The machine learning-powered BirdNET App reduces
barriers to global bird research by enabling citizen science
participation. PLoS Biol 20 (6): e3001670; doi:
10.1371/journal.pbio.3001670