Using drones and artificial intelligence (AI) to monitor large colonies of seabirds could be as effective as traditional ground-based methods, while reducing costs, labor and the risk of human error, a new study finds.
Scientists from Duke University and the Wildlife Conservation Society (WCS) used a deep-learning algorithm — a form of AI — to analyze more than 10,000 drone images of mixed colonies of seabirds in the Malvinas/Falkland Islands off the coast of Argentina The Malvinas/Falklands are home to the world’s largest colonies of browed albatross and the second largest colonies of southern rock penguins.
Hundreds of thousands of birds breed on the islands in closely spaced groups. According to the researchers, the deep-learning algorithm correctly identified and counted the albatrosses with an accuracy of 97 percent and the penguins with 87 percent.
The automated counts were within 5 percent of the human counts, about 90 percent of the time. “Using drone surveys and deep learning provides us with an alternative that is remarkably accurate, less disruptive and significantly simpler,” said Madeline C Hayes, a remote-sensing analyst at the Duke University Marine Lab.
“One person, or a small team, can do it, and the equipment you need to do it isn’t that expensive or complicated.” Previously, teams of scientists have monitored the colonies, which are located on two rocky, uninhabited outer islands.
They count the number of each species they observe on any part of the islands and extrapolate those numbers to get population estimates for the entire colonies.
Because the colonies are large and densely spread, and the penguins are much smaller than the albatrosses (and thus easy to miss), counts must be repeated often. The presence of the scientists can also disrupt the breeding and nursing behavior of the birds.
To conduct the new studies, WCS scientists used a ready-made consumer drone to collect more than 10,000 individual photos. Hayes then converted this into a large-scale composite visual using image processing software.
She then analyzed the image using a convolutional neural network (CNN), a type of AI that uses a deep learning algorithm to analyze an image and distinguish and count the objects it “sees” in it — in this case. two different kinds of sea birds.
The team added these counts together to make comprehensive estimates of the total number of birds in the colonies.
“We loosely modeled a CNN after the human neural network, where it learns from experience,” said David W Johnston, director of the Duke Marine Robotics and Remote Sensing Lab.
“Essentially, the computer identifies various visual patterns, such as those created by browed albatrosses or southern rockhopper penguins in sample images, and over time learns to identify the objects that make up those patterns in other images, such as our composite photo.
” Johnston, who is also an associate professor of the practice of marine conservation ecology at Duke’s Nicholas School of the Environment, said the emerging drone- and CNN-enabled approach has broad applicability “and enhances our ability to measure the size and health of seabird colonies worldwide, and the health of the marine ecosystems they inhabit.
” Guillermo Harris, a senior conservationist at WCS, added: “Counting large seabird colonies of mixed species in remote locations is an ongoing challenge for conservationists.
This technology will contribute to regular population assessments of some species, allowing us to better understand whether conservation efforts are working.
” The two islands used for the pilot study, Grand Jason Island and Steeple Jason Island, are important for conservation and an important area of work for WCS.