From Pixels to Populations

"From Pixels to Populations" is an interactive website and activity for students (and also for AI & Ecology enthusiasts!) that explores how mathematics and AI are applied in wildlife monitoring and conservation.

Using real field data, the users can follow the full research pipeline: capturing photographs, using AI to recognise individual sea turtles, and applying statistical ecology models to infer population size. Through this hands-on platform, one can explore key mathematical concepts underpinning AI and statistical modelling, including probability, uncertainty, and bias (and have fun as well!).

Everyone is welcome to use this platform in their educational activities and contact one of us for help. 

News

We are planning more events, so watch this space! We are also happy to visit schools Please contact our outreach team by email (maths-outreach@qmul.ac.uk) for further information and to arrange a visit.  

Would you like to learn more?

If you are interested in exploring further, here are a few useful references and resources:

  • Learn more about our Statistical Ecology research within the Centre for Probability, Statistics and Data Science at QMUL. 
  • Learn more about Kostas Papafitsoros’ research relating to AI and sea turtles.
  • The Zakynthos Turtles interactive platform  
    A unique interactive web-platform Zakynthos Turtles, which actively engages visitors and tour operators with responsible sea turtle conservation on Zakynthos Island, Greece and helps towards an adoption of turtle-friendly attitude in ecotouristic activities. Through this platform, visitors upload images of unique turtles that they have observed for individual photo-identification and receive information about them in real time e.g., including their behaviours, interesting stories, and quantification of the human pressure that their observed turtle is subject to (as simplified dissemination of my research). 
  • The TurtleTurtle wildlife photo-ID game  
    The task is to match turtles using photo-identification (photo-ID) and one can play endlessly trying to match sea turtle faces and in the same time learn facts about their lives! 

Acknowledgements

The platform was created by the staff of the School of Mathematical Sciences, Queen Mary University of London, Kostas Papafitsoros, Eleni Matechou, Silvia Liverani, Linus Wunderlich in partnership with Deep-C Vision.  

The project was funded by an EPSRC Additional Skills Funding Scheme Summer 2025. We thank the following people who contributed to the project: Thanos Polychronou, Nico Hernandez, Arthur Guillaumin, Huda Alsulami. The 3D loggerhead sea turtle model used in this platform was downloaded from DigitalLife3D.