Powered by

Advertisment
Home Environment Stories

AI and satellite imagery unveil growing human influence on oceanic activities

A new study in the journal Nature has given us a never-before-seen look at how humans use the ocean, and it’s changing a lot. The study was led by Global Fishing Watch

By Ground report
New Update
AI and satellite imagery unveil growing human influence on oceanic activities

A new study in the journal Nature has given us a never-before-seen look at how humans use the ocean, and it’s changing a lot. The study was led by Global Fishing Watch. They used machine learning and satellite images to make the first-ever global map of large ship traffic and offshore structures. They found a lot of activity that wasn’t being tracked publicly before.

Advertisment

The study shows that about 75% of the world’s big fishing boats aren’t tracked publicly. A lot of this fishing happens around Africa and South Asia. Also, more than 25% of shipping and energy boat activity isn’t tracked publicly.

AI map reveals sea’s human activity

David Kroodsma, the director of research and innovation at Global Fishing Watch and one of the lead authors of the study, said that there’s been a new industrial revolution happening in our oceans that we didn’t know about until now. He said that while we have detailed maps of almost every road and building on land, we don’t know as much about what’s happening in the ocean. This study helps us see more of what’s happening at sea.

Researchers from Global Fishing Watch, the University of Wisconsin-Madison, Duke University, UC Santa Barbara, and SkyTruth looked at 2 million gigabytes of satellite images from 2017 to 2021. They were looking for ships and offshore structures in coastal waters across six continents where most of the industrial activity is.

The researchers combined GPS data with five years of radar and optical images. This let them find ships that weren’t broadcasting their locations. Then they used machine learning to figure out which of those ships were probably fishing.

"Historically, we have poorly documented vessel activity, limiting our understanding of the usage of the world's largest public resource - the ocean," said co-lead author Fernando Paolo, senior machine learning engineer at Global Fishing Watch. "We combined space technology with state-of-the-art machine learning to map undisclosed industrial activity at sea on a scale never done before."

"Historically, vessel activity has been poorly documented, limiting our understanding of how the world's largest public resource, the ocean, is used," said Fernando Paolo, an engineer at Global Fishing Watch and co-author of the study. "We map undisclosed industrial activity at sea on a scale never seen before."

Map shows all human maritime machinery

The report published this week in Nature highlights that more than 1 billion people depend on the ocean as their main source of food. Additionally, it points out that the ocean ships about 80% of all traded goods and offshore fields produce nearly 30% of the world's oil.

Artificial intelligence created the new map of human activity at sea, allowing the identification of everything from suspicious fishing operations to an explosion in marine energy development. Research indicated that wind turbines outnumbered oil structures at the end of 2020. In fact, turbines accounted for 48% of all ocean infrastructure in 2021, while oil structures made up 38%.

publive-image
AI and satellites map ocean activity. Credit: 2023 Global Fishing Watch

The so-called "blue economy", which moves between 1.5 and 2.5 trillion dollars a year, relies on all this industrial machinery. It grows faster than the overall global economy, but also causes rapid environmental deterioration.

"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 while only one was 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 of global industrial fishing available."

The study also indicates changes in human activity in the ocean. The COVID-19 pandemic coincided with a global decrease in fishing activity by approximately 12%, including an 8% decline in China and a 14% reduction elsewhere. Meanwhile, the activity of transport and energy vessels remained stable.

Exposed environmental risk

Experts estimate that humans exploit one third of fish stocks beyond biologically sustainable levels. Moreover, human industrialization has led to the loss of between 30% and 50% of critical marine habitats.

"Global Fishing Watch detected numerous fishing vessels hidden within many marine protected areas. The new map of human activity at sea highlighted this revelation. They issued a statement saying, 'Dark fleets', often vessels without public monitoring systems, pose significant challenges to the protection and management of natural resources."

They also discovered a high concentration of ships in the waters of countries that showed little or no previous activity. Wrongly, publicly available data suggests Asia and Europe have similar amounts of fishing within their maritime boundaries. However, new mapping shows that fishing is much larger in Asia.

"We found seven out of every ten fishing boats in the water in Asia, while we found only one in Europe," explained Jennifer Raynor, another of the study's authors. "We created the most complete public picture available of global industrial fishing by revealing the dark ships."

Global Fishing Watch and other organizations have until now relied on the maritime Automatic Identification System (AIS) to see what was happening at sea. The system tracks vessels carrying a box that sends radio signals, but requirements for carrying AIS vary by country and vessel type. Vessels involved in illicit activities often turn off their AIS radars or manipulate the locations they transmit.

Keep Reading

Part 1: Cloudburst  in Ganderbal's Padabal village & unfulfilled promises

India braces for intense 2024 monsoon amid recent deadly weather trends

Support us to keep independent environmental journalism alive in India.

Follow Ground Report on X, Instagram and Facebook for environmental and underreported stories from the margins. Give us feedback on our email id [email protected]

Don't forget to Subscribe to our weekly newsletter, Join our community on WhatsApp, and Follow our YouTube Channel for video stories.