Home / News / Eavesdropping on the Arctic: What Migratory Birds Have to Say about Climate Change

Millions of songbirds flock to the far north each spring, lured by an abundance of food and a relative lack of predators. But spring has been coming earlier to the Arctic and so have some migratory birds, raising new questions about how these species are responding to changing climate. To develop a clearer picture of how climate change is transforming tundra life, Lamont researchers have implemented automated tools for tracking birds and other animals in remote places, giving them an earful of clues about how wildlife is adapting to generally warmer temperatures and more variable weather.

Over five breeding seasons, Lamont ecologist Natalie Boelman and her colleagues recorded birdsong from several remote outposts on Alaska’s North Slope. Her goal: to understand how songbird breeding habits are changing as the Arctic warms two to three times faster than the rest of the planet. Boelman initiated the study by developing a machine-learning-informed algorithm designed to sift out extraneous ambient noise. Later she and Columbia Engineering researcher Dan Ellis teamed up to garner a two-year $200,000 grant from the university’s Data Science Institute, intended to foster collaboration in the natural and computational sciences.

Far-flying and too small to tag with GPS receivers, songbirds are a challenge to study in the wild. With this novel approach, Boelman and her colleagues set out microphones to let the birds come to them. From the foothills of Alaska’s Brooks Range, four microphones recorded at regular intervals from early May through July, over five years, starting in 2010. From the 1.7 terabytes of data captured, the researchers sought to discern when the birds are arriving.

This year the team published a study with their findings, describing how, by applying the algorithm to the thousands of hours of recordings at the breeding grounds on Alaska’s North Slope, they were able to pick out birdsong from wind, trucks, and other noise, and estimate the amount of time the birds spent singing and calling each day, and when they arrived en masse.

The researchers also turned the algorithm loose on their data with no specific training to see if it could pick out birdsong on its own and approximate an arrival date. In both cases, the computer’s estimates closely matched what human observers had noted in the field. Their unsupervised machine learning method could potentially be extended to any dataset of animal vocalizations.

“Our methods could be retooled to detect the arrival of birds and other vocal animals in highly seasonal habitats,” said the study’s lead author, Lamont graduate student Ruth Oliver.

The team wanted to pin down when the birds were arriving and if the species mix would shift as plants favoring warmer temperatures expand their range. White-crowned sparrows prefer woody shrubs, but Lapland longspurs prefer open grasslands. With shrubs expected to dominate the area by 2050, sparrows could end up pushing out longspurs and other tundra-adapted birds.

“Ice is dynamic and complex, and we don’t have the data yet.”

The published work was a first step. In the next phase of their research, the team hopes to develop the tool further to distinguish between sparrows and longspurs, among other species, to spot population-level trends.

Species-specific identification from sound recordings is a complex problem that other researchers are also trying to crack. At Cornell University, Andrew Farnsworth and his colleagues are using deep learning tools in a project called BirdVox to classify recordings of migratory bird calls at night, when there’s less competing noise to filter out. Wildlife Acoustics, a company near Boston, is building low-cost field recorders and developing software to track the comings
and goings of birds, as well as frogs, bats, and whales, by the sounds they make. “We want to know what species are present when humans are not,” says Farnsworth. “We’re trying to teach the machine to classify sound the way the human brain does.”

The longer the data set, the greater chance that a climate change signal will become evident. For Boelman, five years proved too short in a region known for big year-to-year swings in weather and temperature, which appear to be growing more extreme with climate change. In a prior study based on eyewitness observations, the team reported that both sparrows and longspurs appeared to time their arrival and breeding to local conditions. When a late spring delayed snowmelt by 10 days in 2013, the birds arrived 3 to 6 days later than usual and hatched their young 4 to 10 days later. These findings suggest that Arctic-breeding birds may have the flexibility needed to adjust to the increasingly extreme and unpredictable environmental conditions. However, future generations may encounter conditions that exceed their current range of flexibility.

“It is still unclear how songbirds will cope if spring comes even earlier or later than it did during our study period,” said Boelman. “Species also time their migration and breeding with day length, which isn’t shifting with climate change. Species with a migratory response hard-wired to day length alone may not adapt as well to a changing environment.” Boelman recently received support from the National Science Foundation to continue and expand the work both in geographic and analytical scope. She will be deploying ~100 microphones in Canada and Alaska with the goal of understanding how environmental dynamics influence migration timing of waterfowl and songbirds.

Leave a Reply

Your email address will not be published. Required fields are marked *