Just finished up a big few weeks with four talks at three conferences. Thanks for having me #Acoustics2025, #AOC2025 and #ESA2025.
So good to learn from so many brilliant people. Also managed to find some time to see some wild Numbats + a few other cool plants & animals. Now time for a nap 😴
thanks @ecologygrant.bsky.social! Sorry I missed this post, have been in the depths of PhD write up and neglected my Bluesky account.
I’m hoping to look at translation to other species soon. There are some tricky bits when dealing with overlapping calls and complex song types. I think that there are ways to get around that though, but how well it performs ultimately may vary depending on the species and region. 🤷
I guess at this stage I mostly mean that you can apply this to huge acoustic datasets and collect note annotations at very large ‘scales’ without requiring much more effort.
That being said, I think it will work well on other species with some tweaking!
This approach is highly scaleable, and can be used to rapidly 'harvest' individual note annotations from large acoustic datasets. This allows for further investigation of song structure, geographic call variation and potentially vocal individuality.
The clustering process is also very effective at searching 'underneath' a classifier threshold, removing false positives and finding vocalisations that may have been missed. The red circles in the figure show where the owl vocalisations have been split away from other sounds.
In this paper we use a multi-stage machine learning pipeling (combining supervised and unsupervised methods) to reduce almost 3000 hours of environmental recordings into 10,116 annotations, of which 93% were correctly annotated individual notes of the target species.
New paper out now in Ecological Informatics!
www.sciencedirect.com/science/arti...
#bioacoustics #machinelearning #acousticmonitoring
Wasn’t expecting to see this on my walk yesterday - Noisy Pitta in suburban Brisbane!
They’re usually rainforest birds but migrate at this time of year and can show up in weird places.
Haven’t added any new species to my home patch list (now at 98) in ages, this will be hard to beat.
It's Qld Labor in Bonner. This is massive. This seat hasn't moved from Qld LNP since 2010. #ausvotes
Stoked to have a cover photo for @ecography.bsky.social! In our paper doi.org/10.1111/ecog... we included temporal dynamics into SSFs, resulting in daily patterns of movement and habitat selection.
Simulating gave us dynamic spatial predictions across the landscape.
Code! github.com/swforrest/dy...
Introducing Open Ecoacoustics: a platform for continental-scale ecological monitoring and research in Australia. As part of ARDC's Machine Observation Data Processing Infrastructure, we use ecoacoustic technologies to promote open science and conservation. #OpenScience #Ecoacoustics #bioacoustics
Excited to present our latest paper where we take a close look at what we know (and are yet to know) about biodiversity in Antarctica!
🔗 Check out a summary of the work: arcsaef.com/story/new-an...
🔗 Read the paper here: doi.org/10.1111/ddi....
Are you a scientist that analyses/creates models using data from cameras, acoustics, drones or satellites to understand biodiversity? Join the Biodiversity Monitoring starter pack. Point me to your research to be added. ECRs and PhDs welcome! 🧪🌏 #AI #conservation
go.bsky.app/eFMQQX
Thank you! Cool feature, would be keen to be on the contributors list!
The pre-print is still a bit rough, so very open to any feedback during the review process! The next step is to try this on other species and calls. It may be a bit trickier with diurnal species or those with more complex vocalisations.
Anyone who works in bioacoustics knows that tagging individual notes is extremely time consuming, so I think this is a really good way to 'harvest' note annotations from noisy environmental data. You can then use these annotations to compare geographic call variation or even vocal individuality.
We then found that applying iterative unsupervised clustering (using UMAP and HDBSCAN) to the acoustic features was useful for separating false-positive and true detections, and in the end you are also left with individual note annotations that have essentially been automatically tagged!
In this paper (currently in review) we apply a hybrid approach to automated detection of a cryptic threatened owl, the Powerful Owl (Ninox strenua).
Step one is a neural network to classify the vocalisations, after which we segment the output and extract acoustic features.
New pre-print! 🎙️🦉
Automated Note Annotation after Bioacoustic Classification: Unsupervised Clustering of Extracted Acoustic Features Improves Detection of a Cryptic Owl
papers.ssrn.com/sol3/papers....
#bioacoustics #machinelearning #conservation
First time birding in NZ. Cannot believe how many exotics there are everywhere. House sparrow chatter definitely most common noise of the day (Blackbird song close second).
Loved the Gannet colony!
Thanks so much for watching!
@callanalexander.bsky.social on birds in vineyards - heaps of native birds present, and using a cool combination of supervised and unsupervised machine learning models to overcome false positive issues in AI detection of bird calls
#ESAus2024
Good morning, #ESAus2024! Lots of people joined the starter pack yesterday. Take a(nother) look for other austral ecologists to follow and check out the hashtag for interesting talks coming up today.
go.bsky.app/5YmZLNm
Will be there, list is a great idea!
Excited for #ESAus2024 this week! I'm speaking about birds, wine & machine learning on Thursday afternoon.
Would like to be added if possible please! I work on AI + threatened species monitoring in Australia. :)
Would love to be added please! Great list.
Hello Bioacousticians,
Turns out there wasn't a bioacoustics starter pack.
Just realised I myself am following the bare minimum number required to make a starter pack.
Please share & nominate yourself!
Hoping to see this pack grow.
go.bsky.app/2Qmjek6
