A subject hotly debated since its arrival on the world’s stage, artificial intelligence isn’t short of critics with fears being raised over the future it could spell for those in the job market. But it’s a technology that, undeniably, has its uses, too. And when it comes to matters of conservation, it’s a tool that could prove to be transformational for what can be achieved and the timeframe in which it is done so.

For proof, we need look no further than the environmental NGO, WWF Germany which has, in recent weeks, embarked on a project to deploy AI in the murkiest depths of the ocean with one mission: to track down ghosts.

Every year, 20% of all fishing gear in the world’s oceans is lost and an estimated 50,000 tons of lost fishing nets or ‘ghost nets’ end up in the oceans, posing a danger to a variety of marine wildlife. Lost fishing gear makes up around 30% of marine plastic waste, decomposing into smaller pieces and fibres over centuries and exacerbating microplastic pollution in the oceans. The ownerless nets can fish endlessly, making them deadly traps for fish, seabirds, turtles and marine mammals. 

To help tackle this problem, WWF Germany is now expanding its search for ghost nets by collaborating with the Microsoft AI for Good Lab and Accenture. Together, they have launched an initiative to address this threat with the AI-supported platform ghostnetzero.ai.

By using AI, the platform makes it possible to efficiently analyse already existing sonar images specifically for ghost nets. For example, these sonar images are collected worldwide to secure shipping traffic or to explore locations for offshore wind turbines. As the high-resolution sonar data is automatically analysed by the AI technology, the locations where ghost nets are likely to be found are then marked on the platform.

To help advance the new technology, WWF Germany is now calling for cooperation from research institutes, authorities or offshore wind power companies who are urged to donate suitable recordings via the new online platform.

“Ghost nets endanger marine animals and ecosystems and make up a significant proportion of plastic waste in the ocean, but they are invisible under the water surface and their detection is complex. The combination of sonar search and AI-supported detection enables a quantum leap: the seabed is mapped all over the world and there is a huge amount of data. If we can specifically check existing image data from heavily fished marine zones, this is a real game-changer in the search for ghost nets. We hope that research institutes, authorities and companies will take part in the collaboration,” says Gabriele Dederer, research diver and project manager ghost nets at WWF Germany. AI-support also enables WWF to extend its own search to larger sea areas.

According to WWF Germany, the AI technology is already 90% accurate, but once a new area has been identified by the platform, a team of environmentalists checks the marked areas for validation with a trained eye. Depending on the nature of the seabed, it is often difficult to tell whether a suspicious structure is a sanded-in net or a cable. The AI is currently trained to reliably detect these subtle differences in sonar images from different systems. This will make it possible to evaluate existing data sets in a targeted manner. 

“GhostNetZero is a powerful example of how AI can transform how we tackle environmental challenges,” said Thomas Knüwer, chief creative officer at Accenture Song ASG.

“By replacing manual searches with an AI-driven, scalable process, we’re making ghost net detection faster and more effective than ever. This initiative doesn’t just enhance efficiency – it turns scattered data into actionable insights, driving global collaboration to protect marine ecosystems. Leveraging our expertise in user interface design and strategic brand positioning, we aim to help GhostNetZero become a lasting force for ocean conservation.”

“We are excited to work with WWF Germany and Accenture on this project to help address ocean plastic pollution and protect marine ecosystems,” said Juan Lavista Ferres, corporate vice president and chief data scientist of the AI for Good Lab at Microsoft. “The Microsoft AI for Good Lab developed a model that allows GhostNetZero to analyze sonar data to identify and remove ghost nets with the accuracy and efficiency that is only possible with AI.” 

So far, WWF Germany has manually sifted through images captured by a side-scan sonar and recovered a total of 26 tons of nets from the Baltic Sea.

Click here for more from the Oceanographic Newsroom.