Baltic Seabird AI/UX Hackathon
The Guillemots (“Sillgrisslor”) of Stora Karlsö outside Gotland return in the spring every year to the same ledge. They mate, lay their eggs and raise their chicks. Every day, they leave the ledge to dive for fish outside the colony. They grow very old (some over 45 years) and live their whole life in the Baltic Sea. Science on the guillemots helps to bring knowledge about the delicate ecosystem of the Baltic Sea. With their position high up in the food chain, these fascinating seabirds can tell us a lot about the state of the fish and the rest of the Baltic Sea ecosystem.
Gathering and annotating data is a heavy task for the scientists of the Baltic Seabird Project. In last year’s trial, huge leaps were made with the help of citizen science. The live stream hosted by WWF produced some 1300+ comments and insights.
With the use of AI, recognition of individuals and frequent events could be automated, leaving the extra-ordinary and rarer observations to researchers and citizen science.
Choose from three hackathon tasks
- Video recognition of adult individuals, eggs, and chicks. Behaviour classification from individual movements, etc.
- Improved UX for citizen science, feedback, and rewards
- Open application task building on result from task 1 and data from SMHI and Space Data Lab
- Prize pot money SEK 20 000
- Trip to Stora Karlsö with scientists from SLU and WWF
Application and team formation
- Deadline for team (2-5 ppl) application: November 7, 2019
- Webinars and walk-through: November 8, 2019, 10am
- Pitch your team idea November 15. Ten best teams will be shortlisted and free travel and accomodation to the hackathon (however, all participating teams are welcome during the hackathon)
- Hackathon: November 21-22, 2019
Resources at your disposal
- Data (raw and annotated video)
- Experienced coaching on methods, UX and infrastructure
- Scientific knowledge on guillemots and the eco-system of the Baltic Sea
- State of the art infrastructure (AI Innovation of Sweden Data Factory)
- Seminars on machine learning in video
- A citizen science project with a massive turnout