We are excited to learn about the incredible work done by researchers from Global Fishing Watch, led by Fernando Paolo, who have used neural networks to analyze satellite and radar images to uncover insights into global maritime activities! This ground-breaking study, published in Nature, revealed that three-quarters of the world’s large fishing vessels and a quarter of transport and energy ships operate as “dark vessels,” not sharing their locations publicly.
Fernando Paolo was thrilled to explain their findings, “Historically, vessel activity has been poorly documented, limiting our understanding of how the world’s largest public resource—the ocean—is being used. We had an idea that we were missing a big chunk of the activity happening in the ocean, but we didn’t know how much. And we found that it’s a lot more than we imagined.”
From 2017 to 2021, the team examined imagery of coastal areas where major fishing and industrial operations are concentrated, synthesizing GPS, satellite, and radar images. They then trained multiple neural networks to spot and classify boats and offshore structures within these images. Their findings showed that the majority of the approximately 63,000 vessels tracked did not use automated identification systems, raising questions about illegal activities such as unregulated fishing.
The researchers trained one AI to differentiate fishing vessels based on their travel patterns and locations, noting that 42 to 49% of the vessels were classified as fishing boats. Co-author Jennifer Raynor, assistant professor of natural resource economics at the University of Wisconsin-Madison, enthused, “By revealing dark vessels, we have created the most comprehensive public picture of global industrial fishing available.”
Furthermore, the study identified 28,000 offshore structures, including those involved in wind power and oil production, with a noteworthy rise in offshore wind turbines. The number of oil structures saw a 16% increase during the study period, but even more impressively, the count of wind turbines more than doubled, surpassing oil platforms by 2021. This growth in offshore wind energy was especially pronounced in China, which experienced a ninefold increase from 2017 to 2021.
The team went into detail about the process of their study. After gathering a huge amount of data, including 2 petabytes of satellite imagery, vessel GPS data, and deep-learning models, they developed three deep convolutional neural networks. These networks were designed to identify objects, estimate their lengths, classify offshore infrastructure, and distinguish between fishing and non-fishing vessels. By analyzing satellite imagery and vessel GPS data, they were able to map vessel activities and offshore energy infrastructure. This enabled them to detect potential hotspots for illegal fishing and quantify the scale of vessel activities, including the rapid growth of offshore wind infrastructure.
The researchers hope this map can now help in managing and understanding future human activities in the ocean. Co-author Patrick Halpin, professor of marine geospatial ecology at Duke University, expressed, “The footprint of the Anthropocene is no longer limited to terra firma,” meaning human activity in this current epoch has penetrated every corner of the planet.
We are elated by this incredible work from Global Fishing Watch and their endeavor to uncover the mysteries of the ocean and its activities. We hope this research allows us to better understand and protect the world’s largest public resource, the ocean, in the future!
