AI for Coral Reefs Challenge
Automating coral analysis - detecting and classifying coral reef to aid conservation and research of life under water.
Premium participation: Get 1-on-1 Mentoring & Guidance
Try a free mentoring sessionTackling the manual analysis of hours of data recorded during dives surveying the reefs
Challenge completed. Watch the recording of the AI for Coral Reefs final results presentations to discover that the teams came up with:
About the Challenge
Rising temperatures combined with an increasing concentration of CO2 in the ocean cause the water to be more acidic. This change in temperature and acidity harms animals that build shells, such as corals. Occupying less than 1% of the ocean floor, coral reefs are home to more than 30% of marine life. Apart from the importance of biodiversity, coral reefs provide food, income, and protection for half a billion people on earth. Predictions are that if the ocean’s temperature rises by 2 degrees, the earth will lose all its coral reefs.
That’s why the FruitPunch AI community decided to collaborate with ReefSupport to set up a challenge to make a difference! ReefSupport is building a platform through which researchers can automatically analyze their ocean surveys. Coral reef surveyors collect benthic images about their marine ecosystem and must store, process, and eventually share this information. Organizations that do regular surveys of their reef tend to take ~100 pictures per survey. When they return to the office, they analyze the captured photographs to infer the health and growth of their reefs, as well as to count and identify fish and substrates and other features important for a holistic and thriving marine ecosystem. The analysis consumes more time than dive - it takes 5 days of analysis for every 4 hour dive.
Info session
Our challenge partner
GOAL: Creating a ML model for coral detection and classification
A typical reef analysis follows the following steps:
- Step 1: Color correction
- Step 2: Image segmentation of corals (boundary detection)
- Step 3: Identify the coral cover and length of corals (Ruler detection and measurement)
- Step 4: Color & bleaching detection
The goal of this challenge is to automate the first 2 steps by:
- Image segmentation of coral
- Supervised & semi-supervised learning
- Creating a ML pipeline for scientists in the field
Who are we looking for?
AI engineers and data scientists! Experience with image segmentation is a pro! You can apply at any level of experience above basic (theoretical) coding & data science skills. If you are just starting out, join the platform & turn on email notifications because we will be releasing an AI Bootcamp soon! In the selection of the team we look for a combination of rookies looking to learn, hardened professionals and life-long learners switching it up.
You can join as a contributor (12 hours per week commitment for 10 weeks), coach (2-4 hours per week, only for experienced ML professionals) and teacher (give one relevant ML / domain masterclass).
During this challenge they will receive masterclasses from:
- Raditya Andrean Saputra, Founder & Director of Indonesia Biru Foundation ▶️ Coral Reef Surveying and Monitoring
- Camillo Pachmann, Founder of MLReef ▶️ Using ML Reef to build an ML pipeline
- Yohan Runhaar, CTO of Reef Support ▶️ Benthic photographic understanding and exploratory data analysis
Did you know
🪸 Great Barrier Reef has lost half of its corals since 1995 due to warmer seas driven by climate change
🌡 90% of coral reef will die off if ocean temperature rises by another 0.5 degree
🐋 1 billion people and 30% of marine life depends on coral reefs
🤿 For every 4 hours of diving, the analysis of recorded material takes 5 days!
Timeline
Application Deadline: 30 September 2021
Challenge Kick-off: 4 October 2021
Midterm Presentations: 3 November 2021
Final Presentations: 1 December 2021