New research leverages AI and satellite imagery to reveal the growing footprint of human activity at sea

A new study published today in the journal Nature offers an unprecedented view of the previously unmapped industrial use of the ocean and its evolution.

The study, led by Global Fishing Watch, uses machine learning and satellite imagery to create the first global map of large vessel traffic and offshore infrastructure, revealing a remarkable amount of activity that was previously “dark” to public surveillance systems.

The analysis reveals that around 75% of the world’s industrial fishing vessels are not publicly tracked, and that much of this fishing takes place around Africa and South Asia. More than 25% of transport and energy vessel activity is also missing from public tracking systems.

“A new industrial revolution is emerging in our seas, undetected until now,” said David Kroodsma, director of research and innovation at Global Fishing Watch and co-lead author of the study. “On land, we have detailed maps of almost every road and building on the planet. In contrast, the growth of our oceans has been largely hidden from public view. This study helps eliminate blind spots and to highlight the scale and intensity of human activities. activity at sea.”

Researchers from Global Fishing Watch, University of Wisconsin-Madison, Duke University, UC Santa Barbara and SkyTruth analyzed 2 million gigabytes of satellite imagery spanning 2017-2021 to detect ships and offshore infrastructure in the coastal waters of six or more continents. four quarters of industrial activity is concentrated.

By synthesizing GPS data with five years of radar and optical imagery, researchers were able to identify ships that had failed to broadcast their positions. Using machine learning, they then determined which of these vessels were likely engaged in fishing activities.

“Historically, vessel activity has been poorly documented, limiting our understanding of how the world’s largest public resource, the ocean, is used,” said co-lead author Fernando Paolo, senior engineer. in machine learning at Global Fishing Watch. “By combining space technology with cutting-edge machine learning, we have mapped undisclosed industrial activity at sea on a scale never before achieved.”

Although not all boats are legally required to broadcast their locations, vessels missing from public monitoring systems, often referred to as “dark fleets,” pose major challenges to the protection and management of natural resources. Researchers found numerous dark fishing vessels in many marine protected areas and a high concentration of vessels in the waters of many countries that previously showed little or no vessel activity by public monitoring systems.

“Publicly available data wrongly suggests that Asia and Europe have similar amounts of fishing within their borders, but our mapping reveals that Asia dominates: for every ten fishing vessels we found on the water, seven were in Asia and only one in Europe.” said co-author Jennifer Raynor, assistant professor of natural resource economics at the University of Wisconsin-Madison.

“By revealing dark vessels, we have created the most comprehensive public picture available of global industrial fishing.”

The study also shows how human activity in the ocean is changing. Coinciding with the COVID-19 pandemic, fishing activity fell by around 12% globally, with an 8% drop in China and 14% elsewhere. On the other hand, the activity of transport and energy vessels remained stable.

Offshore energy development exploded during the study period. Oil structures increased by 16%, while wind turbines more than doubled. By 2021, turbines would outnumber oil platforms. Chinese offshore wind power has seen the most striking growth, increasing ninefold between 2017 and 2021.

“The Anthropocene footprint is no longer limited to land,” said co-author Patrick Halpin, a professor of marine geospatial ecology at Duke University.

“Having a more comprehensive view of ocean industrialization allows us to see new growth in offshore wind energy, aquaculture and mining that is rapidly adding to established activities of industrial fishing, transportation maritime, oil and gas Our work reveals that the global ocean is a busy, crowded and complex industrial workspace of the growing blue economy.

The study highlights the potential of this new technology to fight climate change. Mapping all maritime traffic will improve estimates of offshore greenhouse gas emissions, while infrastructure maps can inform wind development or help track marine degradation caused by oil exploration.

“Identifying offshore infrastructure is essential for understanding the impacts and trends of offshore energy development and is crucial data for our work to detect marine pollution events and hold responsible parties to account,” said co -author Christian Thomas, geospatial engineer at SkyTruth.

The open data and technology used in the study can help governments, researchers and civil society identify hotspots of potentially illegal activities, determine where industrial fishing vessels may encroach on artisanal fishing areas, or simply to better understand maritime traffic in their waters.

“Previously, this type of satellite monitoring was only available to those who could afford it. Today it is available free of charge to all countries,” Kroodsma concluded. “This study marks the start of a new era in ocean management and transparency.”