More than 1,000 little penguins have received their first dose of bird flu vaccine in Victoria, in what is believed to be the world’s largest vaccination program involving wild birds.
Catherine Basterfield, the chief executive of Phillip Island Nature Parks, said vaccinations began early last week and were ramping up.
Backyard bird feeding is one of our country’s most popular pastimes. Research reveals about half of Australian households feed wild birds, with many people doing so daily.
However, this practice could act as a superspreader event – where a disease infects an unusually high number of people or animals – of the H5N1 virus. This deadly strain of bird flu has already decimated wild bird and mammal populations worldwide. It is now spreading across Australia, most recently killing more than 1,000 crested terns and a long-nosed fur seal, the first detection in a mainland mammal.
Although many Australians feed wild birds, the practice is controversial. This is mainly due to concerns about people offering unsuitable foods and birds becoming dependent on humans.
So why is backyard bird feeding such a problem when it comes to bird flu? And can we do it safely?
Bird feeding can attract all kinds of avian visitors.Jaana Dielenberg, Biodiversity Council, CC BY
Not just a hobby
People feed wild birds for various reasons, including to provide food during tough times or simply enjoy their presence. Most care deeply about their avian companions and believe feeding them is helpful.
However, they may not realise the danger this creates for the birds they love.
Feeding wild birds heightens the risk of disease transmission at feeding locations. When we offer supplementary food, such as seeds or meat scraps, this attracts birds of many different species in a combination and number that would not happen in nature. They may carry deadly diseases, such as the H5N1 virus, and potentially spread them to other birds.
This can create a transmission hotspot right on our back deck. And catching bird flu can push our most threatened species, such as the orange-bellied parrot, to the brink of extinction.
The fatal effects of H5N1 are not only contained to birds. Scavenger animals such as possums, red foxes and crows can be exposed to the virus while devouring the carcasses of infected birds. Humans in close contact with infected wildlife, such as wildlife carers and veterinarians, can contract H5N1. However, human infection is rare and typically only causes mild symptoms.
Wild birds don’t necessarily need the food provided by backyard bird feeders.Jaana Dielenberg, Biodiversity Council, CC BY
Stopping the spread
Backyard bird feeding may seem like a harmless hobby. But given how many people do it, and the risks it poses to both birds and people, bird feeding activities could lead to many more wildlife deaths.
So if you feed birds in your backyard, how can you do so safely?
The most effective strategy is to stop feeding birds altogether. If you don’t offer food to wild birds, they will be less likely to congregate in your backyard or garden. And they will be fine without your help. Our previous research found most birds that visit feeders obtain most of their nutrition from natural sources, such as insects and worms. So the food we provide is a snack, not an essential meal.
But if you do continue feeding wild birds, here are three precautions to take:
Offer less food
Having feeders full of seeds and leftover meat will attract more birds. So to discourage them from congregating, simply provide less food. Much like COVID-era social distancing rules, this will lower the risk of H5N1 transmission by keeping birds separate.
Avoid hand-feeding
Having a bird swoop down to snatch food from your hand is one of the most intimate interactions we can have with wildlife. But in the era of bird flu, this must stop. While humans are unlikely to contract H5N1, close physical contact with birds through hand-feeding is simply not worth the risk.
Keep everything clean
If you keep feeding wild birds, it’s vital to regularly clean all feeding surfaces and equipment using domestic bleach. If you’re not prepared to do this, you shouldn’t be feeding them at all.
Backyard bird feeding could worsen Australia’s current H5N1 crisis. Indeed, your avian visitors may complain if you give them fewer tasty treats or stop feeding them altogether. But these measures will protect both you and them from this deadly disease.
Please do not touch sick or dead birds or marine mammals. Record the location, take photographs from a safe distance, keep pets away and report the sighting to the Emergency Animal Disease Hotline on 1800 675 888.
Darryl Jones does not work for, consult, own shares in or receive funding from any company or organisation that would benefit from this article, and has disclosed no relevant affiliations beyond their academic appointment.
Riverina Water is diluting water from two of its Wagga Wagga bores due to elevated levels of so-called “forever chemicals” being detected, but the source of contamination is a mystery.
But removing most possums from an area through predator control is only part of the challenge. Finding the last few survivors can be much harder.
Even a handful of remaining animals can eventually rebuild a population, making it essential that conservation workers have effective tools to detect them.
One promising solution lies in microphones that record sounds overnight, combined with artificial intelligence (AI) software capable of scanning thousands of hours of audio for possum calls.
Our new research shows this approach can work well – but only if the AI learns not to mistake other animals for possums.
When AI hears possums that aren’t there
AI is becoming increasingly useful for analysing wildlife recordings, allowing vast amounts of audio to be processed automatically rather than requiring volunteers or researchers to listen to every recording.
This is particularly valuable during the final “mop-up” stage of eradication, when only a handful of animals remain and locating them can be challenging.
Many AI models can also run directly on small, battery-powered recording devices in remote forests, avoiding the need to upload huge amounts of audio for processing.
But there is a problem. AI models designed to run on low-power devices often produce more false alarms, wrongly attributing the calls of other animals to possums.
For conservation teams, a false alarm can mean travelling to remote locations in search of an animal that isn’t there. To tackle this problem, we developed a new training approach called “cross-model confusion mapping”.
Rather than asking the AI directly which sounds were possums, we first used BirdNET – a widely used AI system trained to identify more than 6,000 bird species.
Although BirdNET has never been trained to recognise possums, that proved to be an advantage. Because it could only classify sounds as birds, every possum call was forced into the bird species it most closely resembled. That revealed which bird species were most likely to be confused with possums.
To human ears, these calls sound quite different. But AI doesn’t “hear” sound the way we do. It analyses visual representations of sound frequencies over time, known as spectrograms, where the patterns are more alike than they seem to us.
We then added recordings of those birds into our training data as what we call “hard negatives” – examples the AI found difficult to distinguish from possums but needed to learn were not possums. The idea is similar to teaching someone to distinguish between two similar-looking people by repeatedly showing them examples of both.
This prototype listening device uses on-board AI to identify possums and other forest calls automatically.Provided by author, CC BY-NC-ND
We then tested the retrained models using completely different recordings from native New Zealand forests, including natural forest sounds, bird calls, insects, rustling vegetation, wind, rain and possum vocalisations.
The results were encouraging.
Models trained using our approach produced far fewer false alarms while maintaining high detection accuracy.
By comparison, similar AI models trained without this targeted approach generated hundreds of false detections when analysing forest recordings that contained no possums at all.
Importantly, that difference only became apparent when the models were tested on recordings they had never encountered before. When evaluated using the same kinds of recordings they had been trained on, both approaches appeared to perform similarly.
Even more encouragingly, the approach also worked on forest recordings containing bird species the model had never encountered during training. This suggests it had learned to distinguish possum calls more generally rather than simply memorising a handful of confusing species.
A new tool for eradication?
That finding also highlights the importance of testing AI models on genuinely new, real-world data rather than only the examples they learned from.
While our work focused on possums, the same approach could potentially be adapted to detect stoats, rats and other invasive pest species that New Zealand is working to eliminate.
One notable omission was the ruru (morepork), New Zealand’s native owl. It wasn’t identified by BirdNET as one of the species most likely to be confused with possum calls, but understanding how the model performs around this important nocturnal species will be part of our future research.
Further field testing will be needed before the system can be widely deployed. But as bioacoustic monitoring becomes more common, AI could become an increasingly valuable conservation tool.
Finding the last remaining animals is often the hardest part of any eradication programme.
If AI can help conservation teams spend less time chasing false alarms and more time locating real pests, it could become another valuable tool supporting New Zealand’s Predator Free 2050 ambition.
Akbar Ghobakhlou does not work for, consult, own shares in or receive funding from any company or organisation that would benefit from this article, and has disclosed no relevant affiliations beyond their academic appointment.
