'Drones for Ducks:' Federal grants fund research to use AI to count birds
(The Center Square) - How should researchers measure the populations of migratory birds? Researchers developed an idea around a campfire that was put to the test for the first time in Bosque Del Apache earlier this month, according to the University of New Mexico.
Each winter, wildlife managers must count migratory waterfowl as they fly down into refuges. However, this is a difficult task that involves scaring birds into the air by flying past them in airplanes.
Working with the U.S. Fish and Wildlife Service in the Department of the Interior, researchers at the University of New Mexico are working to make a machine-learning model prototype to count the birds using pictures taken by drones in a project called Drones for Ducks.
For the past three years, Christopher Lippitt, associate dean in the College of Arts and Sciences and professor in the Department of Geography and Environmental Studies, and Rowan Converse, a Ph.D. candidate in the Department of Geography & Environmental Studies, have worked to create an AI model that can tell different birds apart and count them by taking drone photos.
They plan to test the technology in a waterfowl survey this winter. They plan to compare the results to those collected by wildlife managers who use traditional methods.
The researchers plan to do this fieldwork in Bosque Del Apache and Texas Chenier Plain Refuge Complex.
“Ideally, it makes collecting the data more quick and efficient, it helps the biologists get the information they need more quickly by running it through the model, and they get an output that they can interpret in a timely manner,” Converse said. “We also hope that this is less disruptive for wildlife. A lot of the species seem to not react much to the drone going over, whereas some of the traditional methods involve flushing them out so they can be counted.”
Although the model is still being developed, early indications say it can detect birds with 95% accuracy, according to a report.
“The team hopes that the new system will make data collection more accurate and give wildlife managers faster access to information they use to make intervention decisions,” the University of New Mexico wrote. “Accurate counts of these migratory populations of birds are important because they help measure how populations have been impacted by climate change if wildlife managers need to put out additional food for the birds, and other information.”
Other schools are working to create models to count birds in snow or on water. However, UNM’s research is different because it explores detecting birds in more diverse landscapes like farm fields, flooded wetlands and river sandbars.
Doing this requires many volunteers.
To test and train the AI model’s accuracy, researchers use volunteers on Zooniverse.
It is a website anyone can sign up for and use to participate in research as a citizen scientist. “Citizen scientists look at the images taken by drones, mark what objects appear to be birds, and differentiate if each bird is a goose, duck, or crane. The task is more difficult than it may sound due to the diversity of the landscape and the unique bird’s-eye point of view.”
Volunteers submit the information, which researchers then review and filter.
The idea for this research first was established during a camping trip organized by the state’s chapter of the American Society for Photogrammetry and Remote Sensing. On the trip, Converse, Lippitt, and others discussed the challenges they face in their work.
Steven Sesnie, a spatial ecologist from the U.S. Fish and Wildlife Service, discussed the challenges associated with counting migratory bird populations. Lippitt proposed finding a way to use AI for the counts.
Since the program uses wildlife management and machine learning, Converse thought it was a good idea to explore in her Ph.D.
Now, Drones for Ducks, funded by the U.S. Fish and Wildlife Service, is on its third research award.
“We all work as a team— the folks at the Fish and Wildlife Service and us— so we’ve gone from the early days of, ‘let’s see if this is crazy,’ with an initial round of funding, to now starting to get down to surveying refuges to test out the potential for large-scale operations,” Lippitt said.