WILDLABS logo

WILDLABS logo

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.

Link

Celebrating World Oceans Day: Revitalizing the marine ecosystem with technology-driven engineered reefs to accelerate CO2 capture

Esther Githinji

9 June 2023 10:14am

As we celebrate World Oceans Day this month, we are reminded that addressing climate change will take more than any one organization. It will require companies, governments, NGOs and communities, all working together, with the aid of technology, to improve the efficiencies of our activities and operations and to reduce costs, waste and emissions. Such an example is IBM and The Reef Company recently joining forces signing a joint initiative agreement aimed at bolstering their ocean conservation endeavors.

0
discussion

ISO Speakers for Emerging Technologies class.

Flor Sangermano

31 May 2023 4:29pm

Hi Everyone, Apologies for posting across multiple groups.  I'm teaching a new course @ Clark University next semester on emerging technologies for conservation. The course...

2 0
Carly Batist

31 May 2023 10:21pm

Definitely interested! I'm in the ecoacoustics/acoustic monitoring space, working at Rainforest Connection and Arbimon.

See full post
article

Happywhale: AI-Powered Whale Identification

Happywhale

16 May 2023 10:00am

In this Conservation Tech Showcase case study from Happywhale, you’ll learn about how AI tools are helping researchers and citizen scientists identify and protect humpback whales. 

1
See full post
article

AI for Conservation Office Hours: 2023 Review

Jake Burton

11 May 2023 10:00am

We've now wrapped our 2023 AI for Conservation Office Hours, where we helped conservationists connect with AI experts to get tailored expert advice on AI and ML problems in their projects

3
See full post
discussion

Crowdsourcing individual ID for pop dyn?

Than Hitt

1 May 2023 5:36pm

Hi! I'm trying to estimate abundance and survival in freshwater fish populations (trout and salmon) using AI for individual recognition from crowdsourced data: https://www.usgs....

1 0
Phil Mitchell

5 May 2023 6:15pm

That sounds like a really neat project! Do fish get re-caught often enough that individual ID is useful? Is sample bias (more data from popular spots) an issue?

See full post
Link

Using computer vision to understand bee vision

Ellie Warren

5 May 2023 1:10am

Here's an innovative project from the Harvey Mudd College Bee Lab that could help us understand how bees view their environments, and thus better protect bee habitat. This project uses computer vision and drone imagery to replicate "bee vision" of flowers and how it differs from a human's view of the same habitat.

0
event

EarthRanger User Conference

Jordan Steward

27 April 2023 5:52am

Back for its 8th year, don't miss this year's premier global annual event where conservation practitioners from around the world convene to discuss important challenges and solutions

2
See full post
discussion

Looking to contribute

Dannii

27 April 2023 2:41am

Hi everybody 👋🏽,I'm a UX designer, and I design interfaces and improve user experiences/flows. I would love to contribute to conservation tech / climate tech, especially saving...

3
See full post
Link

Artificial Intelligence and Conservation with Lily Xu

Ellie Warren

26 April 2023 8:41pm

WWF's recent Fuller Seminar Series on Artificial Intelligence and Conservation featured some familiar faces from the WILDLABS community, including our past Tech Tutor Lily Xu! Check out her presentation talking about AI-based causal reasoning and how it can be applied to conservation challenges.

1
discussion

AI Animal Identification Models

David Hunter

30 March 2023 5:01am

Hi Everyone,I've recently joined WILDLABS and I'm getting to know the different groups. I hope I've selected the right ones for this discussion...I am interested in AI to identify...

12 3
David Hunter

20 April 2023 12:53am

Thanks Dan, that is very helpful. No zebras here but I did see four deer wandering through the streets this morning. Quite wild at times here!

I am totally willing to try an image classifier if it reports multiple objects it identifies in a scene. I will give this a go.

I think 1 fps would be quite acceptable actually, and in some perspective actually advantageous in reducing how much data is getting logged.

I tried upgrading my existing object detector model to YOLOv8 following the links you sent, but I don't think it is possible to upgrade the model on the framework I'm using (ml5js) so I think I will have to try a different framework.

Thank you.

Bas Michielsen

25 April 2023 2:08pm

Hi David

It appears that you have been looking for existing models, however, most existing models are trained on either COCO or some other very generic dataset. So, if you want to identify just animals, you may be better off training your own model. It seems no one in this thread mentioned yet that it is possible to do transfer learning on existing models, which keeps most of the "visual part" of the model as is, but just changes the classification part so it can identify other things. This way you can take an existing model trained on COCO and in a fraction of the time it takes to train a full model, just retrain that for your animals.

Also have a look at your requirements for the inferencing stage. Some models take long in training but are superfast in inference and others are slow in both cases but very accurate, etc. If you want semi-realtime inferencing, you are probably looking at single shot detectors (SSD), and not RCNNs.

See full post
Link

Feathered forecast: Tech tools comb weather data for bird migrations

Stephanie O'Donnell

26 April 2023 2:50pm

Since its launch in 1999, the BirdCast project has used weather radar data to track and forecast bird migrations across the U.S. In recent years, technology such as cloud computing and machine learning have helped make the work of researchers in the project easier and more automated. The BirdCast project is now working on integrating radar data with human observations and bioacoustics to help identify the bird species traversing the skies.

0
discussion

Congo Basin activity?

Chris Nicholas

30 March 2023 9:14pm

greetings - I am helping coordinate a visit by the incoming director of national parks for the Democratic Republic of the Congo (DRC) in mid-late June. He is very interested to...

1 0
chris anderson

25 April 2023 5:08pm

greetings!

 

i sent you a PM regarding this, feel free to contact me however is most convenient for you -

 

regards,

chris 

See full post