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.


Needing help from the community: Bioacoustics survey

I'm reaching out because I'm currently conducting a research project titled "UX-Driven Exploration of Unsupervised Deep-Learning in Marine Mammals Bioacoustic Conservation" for my...

1 0

Was great to chat with you Sofia and I would encourage others in the Acoustics community to help provide input for Sofia's study!

See full post

Labelled Terrestrial Acoustic Datasets

Hello all,I'm working with a team to develop an on-animal acoustic monitoring collar. To save power and memory, it will have an on board machine learning detector and classifier...

6 0

Hi Jesse,

It is great to hear about another team working to improve this area of research.

Are you sure that you can get significant energy savings by processing onboard? In my (admittedly limited) experience, that processing has underlying energy costs. Also the sounds you might want to detect can have a massive range of qualities and as @Lars_Holst_Hansen has suggested, you may not even know exactly what it is you will want to have recorded.

I investigated using a smart recorder (µMoth) v a 'dumb' recorder (Lab2 S17e) for my koala project. The µMoth used about 3.5-4 times more juice than the simple S17e which is a big deficit to overcome before you even ask the recorder to do something "smart". Higher power requirements also limit the battery tech that will work efficiently for you. 

After you have your neatly separated recordings, you may still be asking yourself 'what did I miss?'.

I would happily share my labelled data with you if it was from your area of interest. Apologies for not being able to help with your core request. I assume that you have already raided the repository of: 


It is not too useful for terrestrial mammals yet but has some good labelled sounds for birds and soundscapes.

Please tell us more about your project, particularly the hardware side.

See full post

Pytorch-Wildlife: A Collaborative Deep Learning Framework for Conservation (v1.0)

Welcome to Pytorch-Wildlife v1.0At the core of our mission is the desire to create a harmonious space where conservation scientists from all over the globe can unite, share, and...

6 2

Yeah it would be great to exchange experiences. I’ll contact you.

I started with yolov3 on Jetson (and rtx 2080ti) in 2019 and from then till now added yolov4, scaled yolov4, Yolor, yolov7, yolov6.  With each improvement in model I’ve empirically experienced a real world improvement. And around two days ago a new one, yolov9 came out :-)

I’ve ported my software to the nano, the NX, the AGX, recently the Jetson nano Orin, Orin NX and Orin AGX :-)

I’m looking to see if I can generate some custom high end models for integration into the system wildlife purposes.

Is there any plan for upcoming workshop or training for PyTorch-Wildlife for non coder? I was trying to use MDv5 via PyTorch Wildlife but stop after stuck with the unfamiliarity of interface. Thanks! 

See full post

Tools for automating image augmentation 

Does anyone know of tools to automate image augmentation and manipulation. I wish to train ML image recognition models with images in which the target animal (and false targets)...

11 0

Hi @arky !

Thanks for your reply.

I am running into pytorch/torchvision incompatibility issues when trying to run your script.

Which versions are you using?

Best regards,



@Lars_Holst_Hansen  Here is the information you requested. Also run Yolov8 in multiple remote environments without any issues.  Perhaps you'll need to use a virtual environment (venv et al) or conda to remedy incompatibility issues. 

$ yolo checks
Ultralytics YOLOv8.1.4 🚀 Python-3.10.12 torch-1.13.1+cu117 CUDA:0 (Quadro T2000, 3904MiB)
Setup complete ✅ (16 CPUs, 62.5 GB RAM, 465.0/467.9 GB disk)

OS                  Linux-6.5.0-17-generic-x86_64-with-glibc2.35
Environment         Linux
Python              3.10.12
Install             pip
RAM                 62.54 GB
CPU                 Intel Core(TM) i7-10875H 2.30GHz
CUDA                11.7

matplotlib          ✅ 3.5.1>=3.3.0
numpy               ✅ 1.26.3>=1.22.2
opencv-python       ✅>=4.6.0
pillow              ✅ 10.2.0>=7.1.2
pyyaml              ✅ 6.0.1>=5.3.1
requests            ✅ 2.31.0>=2.23.0
scipy               ✅ 1.11.4>=1.4.1
torch               ✅ 1.13.1>=1.8.0
torchvision         ✅ 0.14.1>=0.9.0
tqdm                ✅ 4.66.1>=4.64.0
psutil              ✅ 5.9.8
py-cpuinfo          ✅ 9.0.0
thop                ✅ 0.1.1-2209072238>=0.1.1
pandas              ✅ 1.5.3>=1.1.4
seaborn             ✅ 0.12.2>=0.11.0
See full post

Mass Detection of Wildlife Snares Using Airborne Synthetic Radar

Mass Detection of Wildlife Snares Using Airborne Synthetic RadarFor the last year my colleauges Prof. Mike Inggs (Radar - Electrical Engineering, Unviversity of Cape Town) and...

9 1

Operating at 2GHz the radar penetrates vegetation so could see through canopy, but not through trunks of trees. However snares are typically set in groups, so one could maximise chance of locating all snares by carrying out a circular/spiral flight path after detection of a potential snare to locate others

Hi David,

I assume this will only work with wire (metal) snares? We often see snares made of nylon rope (used for lucern bales) in the field, which I assume will be missed by the radar?



Hi David, would love to collaborate with you on this topic. A few years ago Dr. Nick van Doormaal did his PhD on snaring with us and we ran a number of experiments on the detection of snares in a real world scenario using trained anti-poaching teams. I think it would be quite simple to replicate the study and then look at the efficacy of remote sensing vs human detection. Let me know if you are interested in chatting further!

See full post

ChatGPT for conservation

Hi, I've been wondering what this community's thoughts are on ChatGPT? I was just having a play with it and asked:"could you write me a script in python that loads photos and...

40 9

The greatest issue with ChatGPT is GIGO (Garbage in, garbage out). It doesn't matter how good the machine learning algorithm is, if it gets fed bad information (data) it will regurgitate bad information. One obvious problem is that it does not reference its information sources. So some of it might be established beyond any doubt, but then it includes something it made up out of thin air with an equally authoritative tone. Because at bottom, ChatGPT is still a dumb machine (or collection of machines) that has to be told what to do by its programmers. It can be useful, but for conservation issues that can have far-reaching implications, I will not trust it. It could be really useful with the addition of two measures (maybe one has already been implemented?):

  1. The option to show the references for all sources (for each statement that it makes; and if it makes its own logical deduction, show that explicitly).
  2. Either weighing or restricting its input to sources that has been checked (e.g. peer-reviewed articles) for at least its scientific output (maybe/hopefully Google is already doing this).

I think with the addition of these two functions it will really become useful to conservation. But we are not there yet. In the meantime it is similar to Wikipedia, maybe a good a starting point for further research.

Just so you know, I uploaded both a photo without a cat and one with a cat in the picture and ask if there was a cat in the picture it got it correct both times.


Uploading pictures to wildlabs doesn't seem to work at this time, so I can't show you the response, but the second answer with the cat in the picture it answered with:

"Yes, there is a cat in this picture. It appears to be in the middle of the driveway."

You can already achieve both of them with your prompt. 
Or, if you're not using ChatGPT specifically but another LLM that you can fine tune, you can use RAG or fine tuning to extra train the algorithm on the data you want it to extract information from.
With ChatGPT you can create your custom GPT now.

See full post

Apply Now: UW Data Science for Social Good Projects

Sign up for Data Science for Social Good 2024! This summer program is a great opportunity to get dedicated data science support on a conservation (tech) project or to get rich experience as a student in the field. More info in the link - student apps due 2/12, projects due 2/20.


Conservation Technology for Human-Wildlife Conflict in Non-Protected Areas: Advice on Generating Evidence

Hello,I am interested in human-dominated landscapes around protected areas. In my case study, the local community does not get compensation because they are unable to provide...

2 0

This is an area where my system would do very well in:



Also, as you mention areas dominated by humans, there is a high likelyhood that there will be enough power there to support this system, which provides very high performance and flexibility but it comes with a power and somewhat a cost cost.

Additionally, it's life blood comes with generating alerts and making security and evidence gathering practical and manageable, with it's flexible state management system.

Ping me offline if you would like to have a look at the system.

Hi Amit,

The most important thing is that the livestock owners contact you as soon as possible after finding the carcass. We commonly do two things if they contact us on the same day or just after the livestock was killed:

  1. Use CyberTracker (or similar software) on an Android smart phone to record all tracks, bite marks, feeding pattern and any other relevant signs of the reason for the loss with pictures and GPS coordinates. [BTW, Compensation is a big issue -- What do you do if the livestock was stolen? What do you do if a domestic animal killed the livestock? What if it died from disease or natural causes and was scavenged upon by carnivores afterwards?]
  2. In the case of most cats, they would hide the prey (or just mark it by covering it with grass or branches and urinating in the area). In this case you can put up a camera trap on the carcass to capture the animal when it returns to its kill (Reconyx is good if you can afford it - we use mostly Cuddeback with white flash). This will normally only work if the carcass is fresh (so other predators would not be able to smell it and not know where it is yet), so the camera only has to be up for 3-5 days max.

This is not really high-tech, but can be very useful to not only establish which predator was responsible (or if a predator was responsible), but also to record all the evidence for that.

See full post

AI volunteer work

Hello All, I have recently joined this group and going through the current feeds and discussions i already feel that its the right group i'm search for sometime.I'm a software...

See full post

Passionate engineer offering funding and tech solutions pro-bono.

My name is Krasi Georgiev and I run an initiative focused on providing funding and tech solutions for stories with a real-world impact. The main reason is that I am passionate...

2 1

Hi Krasi! Greetings from Brazil!

That's a cool journey you've started! Congratulations. And I felt like theSearchLife resonates with the work I'm involved round here. In a nutshell, I live at the heart of the largest remaining of Atlantic forest in the planet - one of the most biodiverse biomes that exist. The subregion where I live is named after and bathed by the "Rio Sagrado" (Sacred River), a magnificent water body with a very rich cultural significance to the region (it has served as a safe zone for fleeing slaves). Well, the river and the entire bioregion is currently under the threat of a truly devastating railroad project which, to say the least is planned to cut through over 100 water springs! 

In face of that the local community (myself included) has been mobilizing to raise awareness of the issue and hopefully stop this madness (fueled by strong international forces). One of the ways we've been fighting this is through the seeking of the recognition of the sacred river as an entity of legal rights, who can manifest itself in court, against such threats. And to illustrate what this would look like, I've been developing this AI (LLM) powered avatar for the river, which could maybe serve as its human-relatable voice. An existing prototype of such avatar is available here. It has been fine-tuned with over 20 scientific papers on the Sacred River watershed.

And right now myself and other are mobilizing to manifest the conditions/resources to develop a next version of the avatar, which would include remote sensing capacities so the avatar is directly connected to the river and can possibly write full scientific reports on its physical properties (i.e. water quality) and the surrounding biodiversity. In fact, myself and 3 other members of the WildLabs community have just applied to the WildLabs Grant program in order to accomplish that. Hopefully the results are positive.

Finally, it's worth mentioning that our mobilization around providing an expression medium for the river has been multimodal, including the creation of a shortfilm based on theatrical mobilizations we did during a fest dedicated to the river and its surrounding more-than-human communities. You can check that out here:


Let's chat if any of that catches your interest!


Hi Danilo. you seem very passionate about this initiative which is a good start.
It is an interesting coincidence that I am starting another project for the coral reefs in the Philipines which also requires water analytics so I can probably work on both projects at the same time.

Let's that have a call and discuss, will send you a pm with my contact details

There is a tech glitch and I don't get email notifications from here.

See full post

Jupyter Notebook: Aquatic Computer Vision

Dive Into Underwater Computer Vision Exploration OceanLabs Seychelles is excited to share a Jupyter notebook tailored for those intrigued by the...

3 0

This is quite interesting. Would love to see if we could improve this code using custom models and alternative ways of processing the video stream. 

This definitely seems like the community to do it. I was looking at the thread about wolf detection and it seems like people here are no strangers to image classification. A little overwhelming to be quite honest 😂

While it would be incredible to have a powerful model that was capable of auto-classifying everything right away and storing all the detected creatures & correlated sensor data straight into a database - I wonder if in remote cases where power (and therefore cpu bandwidth), data storage, and network connectivity is at a premium if it would be more valuable to just be able to highlight moments of interest for lab analysis later? OR if you do you have cellular connection, you could download just those moments of interest and not hours and hours of footage? 

Am working on similar AI challenge at the moment. Hoping to translate my workflow to wolves in future if needed. 

We all are little overstretched but it there is no pressing deadlines, it should be possible to explore building efficient model for object detection and looking at suitable hardware for running these model on the edge. 



See full post

New paper - An integrated passive acoustic monitoring and deep learning pipeline for black-and-white ruffed lemurs in Ranomafana National Park, Madagascar

We demonstrate the power of using passive acoustic monitoring & machine learning to survey species, using ruffed lemurs in southeastern Madagascar as an example.

2 0
What an awesome paper! Loved learning about such a promising research tool in PAM combined with a CNNs, and that lemur vocalizations are termed as "roar-shrieks" :)
See full post

Monitoring setup  in the forest based on the wifi with 2.4 GHz frequency.

I am planning to setup the network using the wireless with frequency 2.4GHz. Can I get the the data for this signal distortion in the forest area?Is there any any special...

5 0

Hi Dilip,

I do not have data about signal distortion in a forest area and with the signal you are intended to use.

However, in a savannah environment, when I put a tour on the highest point of the park, Lora signal (avg 900MHz) is less distorted than WiFi signal (2.4GHz). This is normal as a physics law: the frequency determines the wave length, and the less the length (obviously the less the frequency), the less obstructed the signal.

So, without interfering with your design, I would say that in a forest configuration, WiFi will need more access points deployed and may be more costly, and in your context, even when using LoRa, you will need more gateways than I have in a savannah.

To design the approximate number of gateways, you may need to use terrain Visibility analysis.

To design the cameras deployment, you will need to comply with the sampling methods defined in your research. However, if it is on for surveillance reasons, you may need to rely on terrain visibility analysis also.

Best regards.

I've got quite a lot of experience with wireless in forested areas and over long(ish) ranges.

Using a wifi mesh is totally possible, and it will work.  You will likely not get great range between units.  You will likely need to have your mesh be fairly adaptable as conditions change.

Wireless and forests interact in somewhat unpredictable ways it turns out.  Generally, wireless is attenuated by water in the line-of-sight between stations.  From the Wifi perspective, a tree is just a lot of water up in the air.  Denser forest = more water = worse communications. LoRa @ 900Mhz is less prone to this issue than Wifi @ 2.4Ghz and way less prone than Wifi @ 5Ghz.  But LoRa is also fairly low data rate.  Streaming video via LoRa is possible with a lot of work, but video streaming is not at all what LoRa was build to do, and it does it quite poorly at best.

The real issue I see here is to do with power levels.  CCTV, audio streaming, etc are high data rate activities.  You may need quite a lot of power to run these systems effectively both for the initial data collection and then for the communications.

If you are planning to run mains power to each of these units, you may be better off running an ethernet cable as well.  Alternatively, you can run "power line" networking, which has remarkably good bandwidth and gets you back down to a single twisted pair for power and communications.

If you are planning to run off batteries and/or solar, you may need a somewhat large power system to support your application?


I would recommend going with Ubiquity 2.4Ghz devices which have performed relatively well in dense foliage of the California Redwood forests. It took a lot of tweaking to find paths through the dense tree cover as mentioned in the previous posts. 


See full post

Using "motion extraction" for animal identification

Hi all, I am no expert in the underlying machine learning models, algorithms, and AI-things used to identify animals in the various computer-vision tools out there (...

6 0

Hi Dhanu,

Our group moved to Wildlife Insights a few years back (for a few reasons but mostly ease of data upload/annotation by multiple users) so I haven't tried EcoAssist. This being said, I will look into it as a pre-WildlifeInsights filter to analyze the tens of thousands of images that get recorded when camera traps start to fail, or get confused with sun spots (which can be common at one of our sites, a south-facing slope with sparse canopy cover).

Thanks for sharing!


See full post

Wildlife Conservation for "Dummies"

Hello WILDLBAS community,For individuals newly venturing into the realm of Wildlife Conservation, especially Software Developers, Computer Vision researchers, or...

3 4

Maybe this is obvious, but maybe it's so obvious that you could easily forget to include this in your list of recommendations: encourage them to hang out here on WILDLABS!  I say that in all seriousness: if you get some great responses here and compile them into a list, it would be easy to forget the fact that you came to WILDLABS to get those responses.

I get questions like this frequently, and my recommended entry points are always (1) attend the WILDLABS Variety Hour series, (2) lurk on, and (3) if they express a specific interest in AI, lurk on the AI for Conservation Slack.

I usually also recommend that folks visit the Work on Climate Slack and - if they live in a major city - to attend one of the in-person Work on Climate events.  You'll see relatively little conservation talk there, but conservation tech is just a small subset of sustainability tech, and for a new person in the field, if they're interested in environmental sustainability, even if they're a bit more interested in conservation than in other aspects of sustainability, the sheer number of opportunities in non-conservation-related climate tech may help them get their hands dirty more quickly than in conservation specifically, especially if they're looking to make a full-time career transition.  But of course, I'd rather have everyone working on conservation!

Some good overview papers I'd recommend include: 

I'd also encourage you to follow the #tech4wildlife hashtags on social media! 



I'm also here for this. This is my first comment... I've been lurking for a while.

I have 20 years of professional knowledge in design, with the bulk of that being software design. I also have a keen interest in wildlife. I've never really combined the two; and I'm starting to feel like that is a waste. I have a lot to contribute. The loss of biodiversity is terrifying me. So I’m making a plan that in 2024 I’m going to combine both.

However, if I’m honest with you – I struggle with where to start. There are such vast amounts of information out there I find myself jumping all over the place. A lot of it is highly scientific, which is great – but I do not have a science background.

As suggested by the post title.. a “Wildlife Conservation for Dummies” would be exactly what I am looking for. Because in this case I’m happy to admit I am a complete dummy.

See full post

Successfully integrated deepfaune into video alerting system

Hi all, I've successfully integrated deepfaune into my Video alerting full-features security system StalkedByTheState. The yellow box around the image represents the zone of...

7 0

So my vision about using my StalkedByTheState software to deter the wolves away from the sheep can be represented something along the lines of this:

Wolf deterrant
I'm pretty sure this is how Rob Appleby described it to me. But I think all the sheep should be inside the fence.

And here's how I would explain it to the government officials in a power point. I'm making the point that the wolves have been shooed away.

Sheep safe now 

Big thanks to @kimhendrikse for guiding me through StalkedByTheState. His expertise and willingness to help newcomers like me are vital for our community. His patience and clear explanations have not only helped me understand the intricacies of the tool but have also made my learning experience enjoyable. Grateful for the collaborative spirit that makes Wildlabs thrive!

See full post

Tranforming Conservation Together: Highlights from the 2023 EarthRanger User Conference

Here are a few key insights from this year's event that we're carrying into 2024.

4 1
Hi @hjayanto !No participants from Indonesia, but we did have some from the Philippines, Cambodia, and Bhutan. Happy to help facilitate your adoption. Can you email me at...
Thank you Jordan! We have a plan on the adoption of earth as one of the activity in our WILDLABS awards application. I will try to reach you when we through with the support and/...
Sounds good, thanks @hjayanto !
See full post