Super interesting! I'm currently developing sensor accelerometers for fence perimeters in wildlife conservation centres. I think this is a really cool application of accelerometers; I would love to know how the sensor which you developed for part 3 looked like, or what type of software/machine learning methods you've used? Currently my design is a cased raspberry pi pico, combined with an accelerometer and ml decision trees in order to create a low-cost design. Perhaps there is something to be learnt from this project as well :)

Really appreciate this discussion and the collective interest in humane, non-lethal deterrent solutions.

We at Katidhan, based in India, have been working on a similar innovation called Parabraksh — a solar-powered smart deterrent that uses randomized light patterns to simulate the presence of a threat (like eye contact or motion). It’s specifically designed for deterring elephants, wild boars, leopards, tigers, and other wild animals that cause crop loss or endanger human settlements.

Inspired by the efforts of Lion Lights and Foxlights, we focused on building a solution that’s cost-effective, rugged, and adaptable to diverse geographies. Parabraksh is certified by a government agri-university and has been deployed in over 5,000 installations across India, including projects with state forest departments.

We understand the concerns around animal habituation, and Parabraksh addresses this with a dynamic light logic that changes patterns and behavior unpredictably. When combined with smart field practices and periodic repositioning, the deterrent effect has remained effective across long deployment cycles.

If anyone is interested in trying or procuring the system, feel free to reach out to me directly at previn@katidhan.com. We’re happy to collaborate or share insights.

Warm regards,
Previn Jacob
Katidhan | www.katidhan.com

Aloha, this is a great project. Thanks for sharing. I have been looking for ideas to integrate machine learning with some of the conservation work we are engaed in here on Kauai. Thank you

Hi, I'm really interested in your project. If you're open to it, I’d be happy to build and send you a couple of data logger units — free of charge — to help monitor temperature, humidity, pressure, and possibly hive weight using a load cell. I’m also considering adding a simple bee traffic sensor to track how often bees enter and leave the hive. This could help reveal patterns related to foraging behavior or colony stress. 

 It would also be an interesting use case for using LoRaWAN to send node data to a central gateway. The data could be exported in line protocol format so you can easily import it into InfluxDB or another dashboarding tool if you'd like to visualize it.

 I’m quite busy with other projects, but I’d be happy to throw something together to get you started, and I’ll include the source code in case you'd like to modify or expand it in the future. Let me know if this sounds helpful — I'd love to support your work.

 Best regards, Travis

Hi Sean! I love that you are naturally curious and are pursuing really cool projects in your free time. I know absolutely nothing about cape dune mole rats (in fact, never heard of them prior to this post, but I will confess I was interested in the concept of a mole-rat mystery), but I did have some thoughts about where you might find more information-

It seems like the types of questions you are asking are pretty specific and niche. My first thought on how to find someone with expertise in these specific rodents was to go to their iNat page- there you can see the top observer and top identifier. Both individuals are active researchers, so I think reaching out to them on iNat or finding their e-mails from their respective organizations' sites might be a good way to get in touch.

• https://doi.org/10.1080/15627020.2012.11407557

I also did a quick search in Google Scholar in which I typed in only the scientific name and hit go. The two publications linked above caught my eye as potentially helpful in your search- particularly the first one. They excavated burrows and noted things like home range size, that males have more burrows than females, etc. I didn't go much beyond the abstracts but these seem like they might get you on the right tracks!

Happy ratting!

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'm looking forward to the cool Margo TV we are going to see when we get some AI bear monitoring going in Canada with Margo supplies :) That's going to be awesome.

Here is an image of a bear from last night in the Scandinavian zoo in Denmark. The system triggered on the bear even though it is very dark and this is a digital zoom on a wide angle fixed camera. Despite being very fuzzy we are able to get triggers on these ones due to the use of multiple mitigation techniques so we get long distance, high sensitivity and low false positives. This one for example was checked with multiple successive frames and multiple AI models before calling it a bear.

This is without thermal. But with added thermal and models trained on thermal images the heat signature will effectively be taken up in the model I'm expecting. This would mean that in effect you can tolerate a lower confidence level but it would after all be a living thing as well.



This trigger event for this event was even less clear, but you can still just make out two eyes, and bear in mind (excuse the pun), the actual view from this camera is even wider and the bear further away in a sense as this is a dynamic zoom.