Hi! I would be interested to learn more about your project. Would you send me your contact email? Mine is melisa.simic@nuveen.com - We are infrastructure investors globally working with both clean energy and diversified infra assets. 

Thanks, Melisa

Hi Nikita,

 If you haven't already, I'd recommend reaching out to the folks at the Cornell Ornithology lab. They're really glued into all things bird. In particular, I remember seeing a presentation years ago about their project birdcasting, which was measuring bird migration via radar. One of their next steps was to connect small scale behavior to large scale movement data, and it sounds like your drone project could help fill that gap. 

Cheers,

Brandon

I love the emails that lead me here.

Hi ,

We have been working on creating custom classifiers for frogs in India and have moderate success in this effort. Our workflow is simple - created around 100 3s snippets for each species class (tip: make sure you include only species specific calls obtained from the same PAM data and ensure a decent mix of good and medium quality sound files) in Raven Pro and ran the custom classifier in BirdNET GUI with the default settings. This gives out decent output - although the 'cocktail party problem' is a big issue in species rich regions like the tropics. Species that tend to call in chorus along with many other frog species are hard to be trained. We are currently looking out for solutions to address this. Would like to know how others are dealing with this issue as well.

Thanks

Hi, ya'll!  Yes, we've found that building custom classifiers on top of bird classifier embeddings (including BirdNET) often works very well!

We originally reported good performance on (frequency shifted) bats, anurans, and marine mammals. We've repeatedly seen good performance on real-world passive acoustic data, as well.

Alade Allen-Ankins recently has a paper applying birdnet embeddings to Australian anurans.

Kath, et al also recently used transfer learning from BirdNet embeddings to obtain a large improvement on Anuraset's baseline score. (F1-macro score improved from 0.378 in the original paper to 0.588 using transfer from bird embeddings.)

Our group should also have a new paper up shortly with practical suggestions for improving transfer learning even further. At the very least, transfer learning should provide a much faster way to collect and curate training data than direct human annotation. I highly recommend it as a first step on new problems: You will likely get a good-enough classifier for your needs very quickly, and if not, you'll produce a very useful dataset for further work much more quickly than direct annotation would allow.

Hi Danielle, 

A friend of mine was having a fellowship at K Lisa Yang Center and she successfully built a classifier for Javan Slow Loris. So far I only heard she only made one for sonic call, not sure if it is possible for ultrasonics.

Hi Nigel 

I am interested! I am using it on free-ranging dogs and need units ASAP. It would be nice to have 120B or the version you're working on. A friend is in the US now and he could bring them to me in Brazil.

Thank you!

Hi all! Just wanted to add in that @gracieermi and I maintain a conservation tech directory that includes all the tracking/telemetry companies we've come across so far - conservationtech.directory. 

Currently listed doing a search of the directory - 

Cellular Tracking Technologies - https://celltracktech.com/ 

Advanced Telemetry Systems (ATS) - ​​https://atstrack.com/index.html

Ecotone Telemetry - http://www.ecotone-telemetry.com/index.php/en/oferta/obroze-telemetryczne

GPS Collars - https://www.gps-collars.com/ 

Lotek - https://www.lotek.com/

Microwave Telemetry - https://www.microwavetelemetry.com/

Milsar - https://milsar.com/

Technosmart Europe - https://www.technosmart.eu/

Telemetry Solutions - https://www.telemetrysolutions.com/

Telenax - https://telenax.com/

Telonics - https://www.telonics.com/index.php

Tigrinus - https://www.tigrinus.com.br/

Titley Scientific - https://www.titley-scientific.com/us/products/wildlife-tracking

Wildlife Computers - https://wildlifecomputers.com/

Xerius Tracking - http://www.xeriustracking.fr/

North Star - http://www.northstarst.com/

Migrate Tech - http://www.migratetech.co.uk/ 

e-obs GmbH - https://e-obs.de/

Africa Wildlife Tracking - https://awt.co.za/ 

Holohil - https://www.holohil.com/

Wildlife Materials - https://wildlifematerials.com/

Vectronic Aerospace/Vectronics - https://www.vectronic-aerospace.com/

Kiwi Track - https://kiwitrack.weebly.com/

Hello 

I’m planning to buy new device for turtle dove to study migration patterns in middle east 

So i need your help for the best device for this research 

Thanks 

Hey Cortney, this is such a good question! 

First off - I'd be very careful about interpreting the number of BirdNET detections of a species as a vocalization index for that species. For example, let's say a recorder captures a lot of Species A, which sounds like Species B,  but Species B isn't present at that site. You will often find that BirdNET (or any other sound ID model) reports many detections for Species B and Species A, making it seem like both species are present. So, the number of detections of a species at a site isn't necessarily a more reliable indicator of species presence at that site.

One alternative to consider would be to verify species presence at each site and each day, then use the number of days that species was present as a threshold for habitat use. What threshold to use depends on the species - we've used three consecutive days of presence for some songbirds, for instance.

You could also remove dates when the species is expected solely to be migratory. However, this can get tricky... For example, I've observed that Cerulean Warblers that breed at a particular site will arrive there a week or two before migrants pass through at nearby non-breeding migration hotspots.

Doing a day-by-day analysis of presence enables you to more easily check machine learning detections than if you were checking for the number of detections for each species. You can verify the presence of the species at each site and day by listening to the highest-scoring clips for each day for each species. 

If you have 18 days of recording * 12 sites and you listen to the top 5 highest-scoring clips per species and day, that's a maximum of 1,000 five-second clips per species. In my experience, reviewing that amount of clips takes me only a few hours using a Jupyter notebook like this one:

Read "bioacoustics-cookbook/tdl-notebook at main · kitzeslab/bioacoustics-cookbook · GitHub" on GitHub

bioacoustics-cookbook/tdl-notebook at main · kitzeslab/bioacoustics-cookbook · GitHub

Jupyter Notebooks for interactive review and annotation of audio files - bioacoustics-cookbook/tdl-notebook at main · kitzeslab/bioacoustics-cookbook

GitHub

Hallo. Maybe this software can help you? It is also executable on RPi. I used it some time ago for the same reason and it worked well. Greetings Karl

Read "OpenWebRX web-based software defined radio | Homepage" on

OpenWebRX web-based software defined radio | Homepage

OpenWebRX web-based software defined radio receiver, remote HF spectrum monitoring with a wide variety of demodulators.