Dec 21, 2020 - Science

Space data can be used to spot possible human rights abuses at sea

Earth's blue water with dappled clouds against the blackness of space.
Photo: NASA

Suspicious behaviors from ships that may subject their crews to forced labor can be seen from space, according to a new study.

Why it matters: Forced labor is a known issue in the international fishing industry, but the scale and scope of it is difficult to quantify. The study could be the start of developing tools to better enforce laws to end these human rights abuses.

What they found: The authors of the new study, published Monday in the journal Proceedings of the National Academy of Sciences, used machine learning and satellite data collected between 2012 and 2018 to analyze about 16,000 longline, squid jigger and trawler vessels, including 22 ships with known human rights abuses.

  • The team, which included human rights experts, found 27 high-risk behaviors that could indicate forced labor and can be seen using satellite data compiled by Global Fishing Watch.
  • Traveling farther from port, more daily fishing hours, longer amounts of time spent at sea and fewer fishing excursions per year are indicators of vessels at high-risk of subjecting their crews to forced labor, according to the study.
  • The study discovered about 4,200 potentially high-risk ships.
  • "High-risk vessels visited ports predominantly in Africa, Asia and South America, although exceptions include Canada, New Zealand, the United States, and several European countries," a press release from Global Fishing Watch says.

Yes, but: The researchers behind the study emphasized this new work is a proof of concept that isn't ready to be used as a predictive tool to stop forced labor in real time.

  • "We are not accusing any specific vessels here of force labor," co-author of the study David Kroodsma, of Global Fishing Watch, told Axios. "We are simply showing that there's a high risk of it across the fleet, based on their behavior. And the next step is to get more information."
Go deeper