AI dives into a sea of data, from plankton to pollution

Scientists are turning to AI to analyse millions of images and sensor readings, spotting changes in oceans and rivers faster than ever before.

 Underwater cameras and environmental sensors mean modern monitoring of oceans, rivers and lakes now generates far more data than researchers can realistically analyse by hand. Making sense of that flood of information was the goal of iMagine, an EU-funded research collaboration between aquatic scientists and digital experts from 11 European countries.  Running from 2022 to 2025, the project developed AI tools to help researchers process and analyse large volumes of aquatic data faster and on a much larger scale. Coordinating the effort was Gergely Sipos, an expert in research computing and digital infrastructure at the EGI Foundation, a not-for-profit organisation that connects researchers across Europe with computing, data and other digital services. “This is about the health of the ocean, rivers and lakes that people depend on for food, climate, tourism and drinking water,” said Sipos. “Faster and cheaper monitoring means problems like plankton decline, litter accumulation, oil spills and coral degradation can be picked up and acted on sooner.”  Although iMagine ended in 2025, the tools and data developed by the researchers have been made available for other scientists to use and adapt to their own work. That includes the datasets used to train AI models to recognise everything from fish species to floating litter. Making them available means other researchers can build on what has already been learned, rather than starting from scratch. “Anyone can access our work,” said Sipos. “We continue to support scientists. We offer training material, and even jump on video calls if needed.”