WILDLABS logoWildlabs.net : The conservation technology network

WILDLABS logoWildlabs.net : The conservation technology network

Group

AI for Conservation / Feed

Artificial intelligence is increasingly being used in the field to analyse information collected by wildlife conservationists, from camera trap and satellite images to audio recordings. AI can learn how to identify which photos out of thousands contain rare species; or pinpoint an animal call out of hours of field recordings - hugely reducing the manual labour required to collect vital conservation data.

discussion

What is your favourite social media these days?

Eugene Galaxy

29 January 2025 7:27am

Hey everyone, I would like to understand more about the wildlife community consensus (if there is such?) on social medias.With recent BlueSky rise and X platform owner's...

10 1
Beni Beeri Issembert

4 March 2025 8:36am

Linkedin mainly. 

iNaturalist and eBird ofc but these are more communities than real social networks. 

But, and this is a real advice, a good RSS feed reader with all your trusted sources and then you don't need any other social network. 

:O) 

See full post
discussion

Career Move: Defence AI to Conservation AI

Luke Swaby

19 February 2025 12:01pm

Hi All,I'm looking for advice regarding a career move into Conservation AI, and figured I’d throw my case out to the wisdom of the crowd.I'm currently a Data Research Scientist at...

9 2
Luke Swaby

22 February 2025 2:21pm

Hey Margaux,

Thanks so much for such an informative response, really appreciate it. I’ll be look into every avenue you’ve suggested!

And congratulations on the job, your company honestly looks like the dream. Well done for sticking it out for the right opportunity.

Re. your point on software integration, I’m a Data Scientist primarily but much of my current work revolves around integrating off-the-shelf models (e.g. vision-language models) into existing systems/pipelines, and I think this aligns well with the state of the conservation tech field at the moment. With new state-of-the-art models emerging from the tech giants on an almost monthly basis I doubt small conservation NGO’s will be reinventing the wheel in-house…

I just want to collaborate with likeminded people and devote my knowledge/skills/creativity to a cause I really believe in, and am happy to wait as long as it takes to find the right opportunity :)

Just making notes on what you’ve said now. Will be reaching out to all these companies you’ve mentioned, probably including yours haha

Thanks again!

Luke

Luke Swaby

28 February 2025 1:05pm

Hi Maureen, thanks a lot for this. Seemed more or less perfect so I applied :)

Also didn't realise there was a slack community so I'll be scanning that too...

 

See full post
discussion

The 100KB Challenge!

Dan

7 February 2025 11:47am

If you could send/receive 100KB of data from anywhere on the planet via satellite; what would you send?I work for a company called Ground Control, we design, build and manufacture...

11 3
Dan

20 February 2025 9:13am

Nice one - what kind of thing would you use this for? 

~500mA peak current, it has a similar power profile as the current RockBLOCK product, in that it needs lots of juice for a for a small period of time (to undertake the transmission) we include onboard circuitry to help smooth this over. I'll be able to share more details on this once the product is officially launched!

 

Dan

20 February 2025 9:13am

~500mA peak current, it has a similar power profile as the current RockBLOCK product, in that it needs lots of juice for a for a small period of time (to undertake the transmission) we include onboard circuitry to help smooth this over. I'll be able to share more details on this once the product is officially launched!

 

Nuno Cesar de Sa

20 February 2025 9:31am

Hi Dan, 

Not right now but I can envision many uses. A key problem in RS is data streams for validation and training of ML models, its really not yet a solved problem. Any kind of system that is about deploying and "forgetting" as it collects data and streams it is a good opportunity. 

 

If you want we can have a talk so you tell me about what you developed and I'll see if it fits future projects.

 

All the best

 

See full post
discussion

Switch to Conservation IT

Soumya Bhattacharyya

10 June 2022 1:47am

Friends,Very excited to be a new member of the community!I have spent my 30 years career in mainstream traditional IT. But always loved and longed to do something meaningful in...

5 3
Soumya Bhattacharyya

25 February 2025 2:16am

Some of you may have seen this post of mine from back in 2022. With the hope that it will help me put my foot through the door, I have now completed my Masters in AI and ML. Purely to work in preferably research and dev oriented opportunities in conservation and wild life. 

If anyone can advice/ assist/ wants to network, please drop a note. 

Eugene Galaxy

25 February 2025 6:42am

Hey @soumyabhatta, welcome in! I had a similar career switch as you, but less experience, and coming from Robotics background. :)



What helped our startup to get a "tech introduction" in to the world of Wildlife & Conservation was going through Dan Morris' blog where he showcases all of the relevant tech he knows about.



I cannot recommend you enough to get a read on it: 

See full post
discussion

Building the perfect camera trap (Guide)

Hugo Markoff

17 February 2025 8:06am

I know there are several people and teams going through the journey of building their own trail cameras – so I decided to make the guide I wish I had when we were still building...

3 3
Lars Holst Hansen

18 February 2025 4:15pm

If you are the least interested in camera traps, you should definately go and check out Hugo's interesting article!

Cheers,

Lars

Robert (Bob) Zak

21 February 2025 4:22pm

Great Article! (and thanks for the ping re: "PIR Sensors" )

I like the idea of a simple magnetic trigger.  As an alternative, I've often wondered about an ultra-low-power "wake on Radio" receiver that could be connected wirelessly to a range of different trigger devices.  

Also, there is an interesting tradeoff between battery life and trigger speed you didn't cover.  Namely, all the commercial trail cameras I know of  turn themselves almost completely off between triggers to save power.  An ultra low power "boot controller" monitors the PIR sensor, and when triggered, initiates the boot sequence for the main SoC.  I've found that the boot process (rather than PIR bandwdith, configuring the image sensor, shutter speed, etc. ) dominates the "trigger time".  It is remarkable that this all happens in less than 400 ms for the newer trail cameras.  There are some hacks to help this along, for example, locating the time-critical code early in the EEPROM boot image so that the firmware can start executing before all the firmware is loaded (ask me how I discovered this). 

For those interested in the inner workings of a typical commercial trail camera, check out my series of articles documenting reverse engineering (and hacking) a few Browning models.  

   

Hugo Markoff

23 February 2025 8:11am

Hey Bob, thanks for the kind words! Your articles on Winterberry Wildlife have really been a big inspiration for me! There are extremely limited numbers of articles on trial cameras, and you have some nice in-depth hardware level which I have been reading 😊 

You are completely right about the battery life and trigger speed tradeoff. If I remember right, there are a few cameras which offered “real time” images but in return the battery was drained in a few days and people started to complain on forums. In early stages of development there is also much about limiting the services at boot, as you mention putting the camera function as early in the boot sequence as possible, creating your own camera configs and so on. 

See full post
discussion

Free tool to generate your spirit animal

Eugene Galaxy

19 February 2025 7:58am

Hey everyone!This is not for conservation, but I still wanted to share it with the community! :)To promote awareness of different animal species, I made a simple app that...

4 0
Hugo Markoff

19 February 2025 2:10pm

Just tried it again :D 

See full post
Link

GhostNetZero.ai

Alex Rood

13 February 2025 5:40pm

Using advanced AI technology, GhostNetZero.ai analyzes the collected sonar data to identify specific locations where ghost nets are likely to be found. This enables the recovery of these abandoned nets and helps to rid our oceans of hazardous waste.

3
discussion

AddaxAI - Free AI models for camera traps photos identification

Peter van Lunteren

3 April 2024 7:16am

AddaxAI is an application designed to streamline the work of ecologists dealing with camera trap images. It’s an AI platform that allows you to analyse images on your...

15 17
Peter van Lunteren

12 February 2025 2:47pm

Hi Caroline @Karuu ,

The model is still in development. Unfortunately, I'm not sure how long it will take as it is not my top priority at the moment. However, you can still use EcoAssist to filter out the empty images, which is generally already a huge help. 

Would that work for the time being? 

 

See full post
discussion

Camera Trap Data Visualization Open Question

Arthur

4 February 2025 3:00pm

Hi there,I would like to get some feedback, insight into how practitioners manage and visualize their camera trap data.We realized that there exists already many web based...

6 0
Arthur

12 February 2025 12:31pm

Hey Ed! 

Great to see you here and thanks a lot for your thorough answer.
We will be checking out Trapper for sure - cc @Jeremy_ ! A standardized data exchange format like Camtrap DP makes a lot of sense and we have it in mind to build the first prototypes.
 

Our main requirements are the following:

  • Integrate with the camtrap ecosystem (via standardized data formats)
  • Make it easy to run for non technical users (most likely an Electron application that can work cross OSes).
  • Make it useful to explore camtrap data and generate reports

 

In the first prototyping stage, it is useful for us to keep it lean while keeping in mind the interface (data exchange format) so that we can move fast.


Regards,
Arthur

Kim Hendrikse

12 February 2025 1:36pm

Quick question on this topic to take advantage of those that know a lot about it already. So once you have extracted all your camera data and are going through the AI object detection phase which identifies the animal types. What file formation that contains all of the time + location + labels in the photos data do the most people consider the most useful ? I'm imagining that it's some format that is used by the most expressive visualization software around I suppose. Is this correct ?

A quick look at the trapper format suggested to me that it's meta data from the camera traps and thus perform the AI matching phase. But it was a quick look, maybe it's something else ? Is the trapper format also for holding the labelled results ? (I might actually the asking the same question as the person that started this thread but in different words).

Kim Hendrikse

12 February 2025 2:04pm

Another question. Right now pretty  much all camera traps trigger on either PIR sensors or small AI models. Small AI models would tend to have a limitation that they would only accurately detect animal types and recognise them at close distances where the animal is very large and I have question marks as to whether small models even in these circumstances are not going to make a lot of classification errors (I expect that they do and they are simply sorted out back at the office so to speak). PIR sensors would typically only see animals within say 6m - 10m distance. Maybe an elephant could be detected a bit further. Small animals only even closer.

But what about when camera traps can reliably see and recognise objects across a whole field, perhaps hundreds of meters?

Then in principle you don't have to deploy as many traps for a start. But I would expect you would need a different approach to how you want to report this and then visualize it as the co-ordinates of the trap itself is not going to give you much  information. We would be in a situation to potentially have much more accurate and rich biodiversity information.

Maybe it's even possible to determine to a greater degree of accuracy where several different animals from the same camera trap image are spatially located, by knowing the 3D layout of what the camera can see and the location and size of the animal.

I expect that current camera trap data formats may fall short of being able to express that information in a sufficiently useful way, considering the in principle more information available and it could be multiple co-ordinates per species for each image that needs to be registered.

I'm likely going to be confronted with this soon as the systems I build use state of the art large number of parameter models that can see species types over much greater distances. I showed in a recent discussion here, detection of a polar bear at a distance between 130-150m.

Right now I would say it's an unknown as to how much more information about species we will be able to gather with this approach as the images were not being triggered in this manner till now. Maybe it's far greater than we would expect ? We have no idea right now.

See full post
discussion

Low-power acoustics systems

Sebastian MARZETTI

27 January 2025 1:44pm

Hello,I am a researcher specializing in acoustics, electronics, and artificial intelligence. Together with my team, we develop terrestrial and underwater acoustic systems with...

6 1
Sebastian MARZETTI

10 February 2025 10:42am

Hello, we do not have a website yet. We are exploring where our technology can provide the most significant value compared to existing products. We would be very interested in discussing this with you.
Sebastian MARZETTI

10 February 2025 10:49am

Hi Julia,

Thank you for your reply. Your work on connected acoustic recorders sounds very interesting, and we’d love to learn more about your application and the enhancements to Bugg. We’ll contact you soon to arrange a discussion.

Looking forward to it!

Thank you,

Best regards,

Sebastian

See full post
Link

Training Educators in Nigeria how to save the Earth with Empathy & Computational thinking; use AI robotics #hummingbirdbit to make a bee waggle! 🐝

Gabriel Onifade A.

10 February 2025 1:48am

Teaching Children about Empathy for the Endangered Species and for Nature Conservation In celebration of the Earth Conservation Day, @veracityhouse in collaboration with the Nature Conservation Foundation trained Teachers on how students can save earth with computational...

1
discussion

AI for Bird and Bat Recognition

Lorenzo Girotti

7 February 2025 11:57am

Hi everyone,I'm working on a project involving the automatic recognition of bats and birds from their audio recordings in Italy, with a possibile evolution also in other european...

1 1
Carly Batist

7 February 2025 5:06pm

Hi Lorenzo,

I highly recommend the OpenSoundscapes package (developed by the Kitzes Lab at U Pittsburgh) - there are workflows to build your own CNNs there, the documentation is really thorough, and the team are very responsive to inquiries. They also have a bioacoustics 'model zoo' that lists relevant models. The Perch model from Google would be good to look into as well.

Some recent papers I've seen that might also be worth checking out -

Hope that helps a bit!

See full post
Link

acoupi: An Open-Source Python Framework for Deploying Bioacoustic AI Models on Edge Devices

Carly Batist

7 February 2025 1:39am

New paper - "acoupi integrates audio recording, AI-based data processing, data management, and real-time wireless messaging into a unified and configurable framework. We demonstrate the flexibility of acoupi by integrating two bioacoustic classifiers...BirdNET and BatDetect2"

3
discussion

Machine learning for bird pollination syndromes

Craig

25 November 2024 7:30am

I am a PhD student working on bird pollination syndromes in South Africa and looking specifically at urbanizations effect on sunbirds and sugarbirds. By drawing from a large...

2 2
Lance Legel

3 January 2025 3:55am

Hi @craigg, my background is machine learning and deep neural networks, and I'm also actively involved with developing global geospatial ecological models, which I believe could be very useful for your PhD studies.  

First of all to your direct challenges, I think there will be many different approaches, which could serve more or less of your interests.

As one idea that came up, I think it will be possible in the coming months, through a collaboration, to "fine-tune" a general purpose "foundation model" for ecology that I'm developing with University of Florida and Stanford University researchers.  More here.

You may also find the 1+ million plant trait inferences searchable by native plant habitats at Ecodash.ai to be useful.  A collaborator at Stanford actually is from South Africa, and I was just about to send him this e.g. https://ecodash.ai/geo/za/06/johannesburg

I'm happy to chat about this, just reach out!  I think there could also be a big publication in Nature (or something nice) by mid-2025, with dozens of researchers demonstrating a large number of applications of the general AI techniques I linked to above.

See full post
discussion

AI in Ornithology

Dr Yvette Ehlers Smith

1 November 2024 1:10pm

Any researchers out there that are using AI tech specifically linked to birds (in Africa)? I would be very interested to hear from you. We are putting together a special issue in...

2 4
Adrien Pajot

4 November 2024 6:00am

Thanks for flagging! We might be interested to submit our work on acoustic monitoring system.

See full post