Data Study Group Final Report: Centre for Environment, Fisheries and Aquaculture Science (Cefas) - Detecting marine slicks from shipwrecks using satellite observation data

Data Study Groups are week-long events at The Alan Turing Institute bringing together some of the country’s top talent from data science, artificial intelligence, and wider fields, to analyse real-world data science challenges.

Thousands of shipwrecks around the world still contain oil and fuel from past conflicts and maritime accidents, slowly releasing hydrocarbons into the sea as their hulls corrode. These wrecks pose a long-term hazard to marine ecosystems and coastal communities, threatening fisheries, food security, and biodiversity. Globally, it is estimated that between 2.5 and 20 million tonnes of petroleum products remain trapped in submerged vessels. Detecting and monitoring these leaks is essential for environmental protection, yet it remains difficult at scale. Most satellite-based monitoring relies on visual interpretation or single-image classifiers that struggle under variable lighting, sea states, and weather conditions. Developing automated, reliable detection methods that can operate under these real-world constraints is critical for enabling continuous, large-scale observation of shipwreck pollution.

Data Study Group - September 2025 | The Alan Turing Institute