Bird surveys can be labour extensive and often need willing volunteers who are not just prepared to sit it out for a few hours but are also skilled enough to recognise the birds or their bird songs. This means trying to keep and up to date record of local bird diversity and health can be time-consuming and expensive.
A team of researchers from Oregon State University (OSU) may have developed an automated solution to bird surveys which could lead to software that enables a near real-time monitoring of populations to happen. [pullquote]Now we can tell down to the second when a bird arrives, leaves, when and where it’s choosing to nest, that type of information. It’s just not practical to do that with human monitoring.[/pullquote]
Human ears can be confused by many different bird calls.
Human ears can be recognise different calls from birds if there are one or two calls being made simultaneously. But the more birds that are calling the more difficult it becomes. The OSU team have developed a piece of equipment that can distinguish individual calls from many different species of birds that are all singing at the same time.[like_to_read]
This system, the first of its type, should enable automated ecological monitoring of bird species in a given area.
“It’s difficult to hear and identify even one or two bird species at a time, and when you have many of them singing at once it’s even more difficult,” said Forrest Briggs, a doctoral student in computer science at OSU.
“Birds are important in themselves, but also an early warning system of larger changes taking place in the environment,” Briggs said. “Now we can tell down to the second when a bird arrives, leaves, when and where it’s choosing to nest, that type of information. It’s just not practical to do that with human monitoring.”
New acoustic monitor uses machine learning to recognise bird calls.
The system developed with funding from the National Science Foundation and the OSU College of Engineering uses a form of machine learning. Even in its early stages of development the equipment returns an error level that is as good as a human bird expert.
One of the big steps forward with the new system over other technologies is that it is omnidirectional so the microphones do not need to be pointed directly at the birds making the sounds. One day of its testing the system recorded 548 sounds from 13 different bird species.
“It would not be reasonable for a person to count birds once per minute, 24 hours a day, for three months, but we aim to obtain similar results with acoustic surveys,” the researchers wrote in a recent study published in the Journal of the Acoustical Society of America.
The new acoustic surveying technique still needs a little development doing to it. There’s currently interference from rainfall and the microphone can pick up non target sounds such as people having a party in the woods during one period of testing. There’s also issues of hardware as on one occasion a bear took a liking to one of the microphones.
Potential for real time ecological monitoring using sound.
There is high hopes for this method of ecological surveying and monitoring as it should be possible to extend the use to other species such as frogs, grasshoppers and marine mammals.
While it is always nice to spend a day in the field or in the garden watching the birds it’s not always practical for serious science. There will always be in the field surveys run by many groups because of it’s importance of involving the public with nature But for up to date monitoring this new type of acoustic remote sensing could lead to wildlife managers and conservationist getting much more useful up-to-date information on which to make decisions.
Oregon State University: Technology to monitor bird sounds, impacts of environmental change.