Hi Johnathan, 



There is a Canadian company more or less doing that. They have their own endurance drone and optical/thermal cameras. Very much keyed into surveys and they may have success given the number of helicopter accidents we have had in Western Canada. Not sure if the AI part is there yet. 



I know they've done surveys with at least one department here but not much beyond that. I talked to one of the developers their just as a point of interest. The current leadership today looks different than I remember though. 



 

Read "Superwake" on Superwake

Superwake

" /> <link rel=

Superwake

Hi all, I'm the founder of a company in Texas that provides thermal drone surveying for private game ranches. Right now, we're doing everything completely manually in terms of counting during both the initial flight as well as the review. Automating our process with an AI program would be great, but there are multiple limitations I'd imagine:

1.) Thermal imaging has pretty poor resolution even when you're only 100 feet or so above the ground. We'll often need to bring the drone down even closer to identify a buck vs doe. I'd imagine an AI model would be even more limited by this poor resolution

2.) Using a visible zoom camera in tandem with the thermal can help with this issue, but then you are very limited. Thermal works great at night, but requires cool, cloudy days if you're wanting to fly in the daylight to use the optical camera. In Texas, these are few and far between.

3.) Even if you were to figure out everything else, there are often animals that rewuire a pilot to move the drone off its path in order to identify (for example if they're bedded down behind a tree we will often need to swing around to the other side. 

If anyone is interested, we do record all of our surveys, so I have 1000+ hours of thermal footage of animals from whitetail deer to nilgai to zebra. I'd be happy to share this with someone who's interested in potentially building a model if they think they can solve the limitations.

The Futures Wild team will be there :)

Yep see you on friday 

Hi Sam, I  did my master's on hatchling turtle vocalisations and their role in nest emergence behaviours (currently under review for publication). I recorded nest emergence behaviour in-situ using microphones and camera traps. I worked with snapping turtles, but the methods could be quite useful. I would be happy to share my thesis if that would be helpful.

there are a few sea turtle papers that describe hatchling vocalisations but not many experiments testing hypotheses for these vocalisations. 

here are some papers that could help you get you started:

• Maeda et al 2024
• McKenna et al 2019
• Lacroix et al 2022
• Nishizawa et al 2021

Shoot me a message if interested in chatting more :)

Hello Sam ...great work, would like to see the paper when it comes online. I would like to know about the device....Bests Zahir

Open source technologies are a game-changer for biodiversity conservation. They give us the freedom to use, study, modify, and share vital tools and knowledge that help advance research in meaningful ways. For conservationists, this means we can adapt technologies to meet local needs, improve existing tools, and make new innovations available to everyone—creating a more collaborative and sustainable future for our planet.

It’s exciting to see the impact of open source in conservation already, with tools like Mothbox, Fieldkit, and OpenCTD helping to drive progress. I'm curious—how do the formal definitions of open source resonate with you? How do they shape the way we approach conservation?

Also, if you're interested in how open source AI can support conservation efforts, check out this article: Open Source AI Agents: How to Use Them and Best Examples.

Can’t wait to hear your thoughts! Let's keep the conversation going.

Sorry to be a stickler on syntax when there is a richer discussion about community here - but I believe a true "open source" project is a functionally complete reference design that anyone can build upon with no strings attached. If the community isn’t provided with enough information to fully build and iterate on the design independently, then the project doesn’t truly meet the spirit of open source. 

As a developer and engineer, I’ve observed that sometimes projects crowdsource free engineering work under the guise of being "open source." While this can have benefits, it can feel like asking for a free lunch from clients and customers. 

Advanced features—like enterprise-level data management or tools for large-scale deployments—can reasonably remain proprietary to sustain the project financially. Transparency is critical here. If the foundational components aren’t fully open, it would be more accurate to describe the project as "community-driven" or "partially open." And as an engineer/developer I wouldn't be angry when I went to explore the project marked "open source" only to find that I have been lied to.

Just my two cents, and I really appreciate the thoughtful discussion here. The open source community has been a massive influence on me. Everything I do at work would not be possible without it.  In many ways, "open source" or "public domain" projects represents the true know-how of our society.