Clever computer software could soon be running a constant stocktake on New Zealand's birdlife, through cutting-edge technology trained to pick out their songs.
A new Massey University-led effort aims to achieve what conservationists have long struggled to for years - creating software that can identify bird species through their song alone.
The project, supported by an $880,000 Marsden Fund grant, holds the potential to detect, recognise, analyse, and ultimately infer bird populations from the estimated 20,000 acoustic recorders deployed around the country.
"If we are to have any chance of achieving goals like 100,000 kiwi by 2030, and Predator Free New Zealand 2050, we need measurement tools that are efficient and reliable enough to track the populations of our birds and tell us where our actions are best put," said Massey's Professor Isabel Castro, who is co-leading the project.
"The problem is that birds are hard to monitor – they move around, they live in the bush, and they are often well-camouflaged or nocturnal, so estimating how many there are is tough.
"Fortunately for us, birds are very talkative and by leaving audio recorders in spots, we can identify them through their song."
The current industry standard for measuring bird populations relies on people doing direct counts of birds in the field.
In New Zealand, researchers use five-minute call counts, where they count the presence or absence of a small number of birds in five-minute periods.
Recordings are analysed with the help of headset and a programme that allows the researchers to see the spectrogram - a visual representation of the sound - and count the calls of individual species in sections of these recordings.
"The human ear is a powerful recognition tool, but this kind of analysis is subjective, error prone, and slow with only a fraction of the data actually used," Castro said.
"When you add in the varied quality of recordings, differences in calls from day to night and locations or competing sounds from the environment – you see the problem.
"We scientists don't like uncertainty and we look for better ways."
That didn't mean teaching computers to recognise bird songs as well as we do - but teaching them how to do it better.
The solution was specially designed software dubbed AviaNZ, which combines experts in technology and bird ecology to solve the problem that neither side could alone.
"We've got the scope of expertise," Castro said.
"We have mathematics, computer science, signal processing, but we also have expertise about the birds and their behaviour - by combining the technical and ecological work we believe that we are more likely to be successful where others have not by allowing people to see beyond the birds and beyond the sounds' characteristics."
The platform would be able to take audio recordings of varied qualities and have the capability for the researcher to search for specific birds at the touch of a button.
"In the beginning it might come back with four of the bird's calls at 100 per cent certainty and 10 that need to be manually checked, but as the system learns and we refine it, it will be more and more accurate."
To achieve this, the software needed extra technological solutions and new knowledge of the behavioural ecology of our native species.
Field experiments will help the researchers to better understand other variables on vocalisations such as the relationship of sex, season and population density on the number of calls of individual birds.
"In just one project, we are going to adapt mini-microphone technology to learn about the vocal behaviour of kiwi in order to establish a baseline of average call per bird," Castro said.
"We will then feed the data into software to give population estimates on the amount of birds in any one given spot."
The data can be confirmed using the translocated populations of several species where the researchers know the exact or nearly exact numbers of individuals.
While this technology will be developed using New Zealand birds, it could ultimately also be useful to other countries with much larger populations of wildlife.