New study reveals previously untracked industrial activity in the oceans: A team of researchers from Global Fishing Watch and other institutions has published a new study that uses satellite imagery and machine learning to map the previously unseen industrial use of the ocean. The study, published in the journal Nature, shows the extent and intensity of human activity at sea, such as fishing, shipping, and offshore infrastructure including offshore wind farms. "By combining space technology with state-of-the-art machine learning, we mapped undisclosed industrial activity at sea on a scale never done before," said co-lead author Fernando Paolo, senior machine learning engineer at Global Fishing Watch.

The findings: The researchers analyzed 2 mn gigabytes of satellite data from 2017 to 2021, covering coastal waters across six continents where more than three-quarters of industrial activity is concentrated. They were able to detect vessels and structures that failed to broadcast their positions, revealing numerous "dark fleets" and "dark infrastructure." The map also reveals that about 75% of the world's industrial fishing vessels are not publicly tracked.

Why is this important? The study highlights the potential of this new tech to tackle climate change, improve estimates of greenhouse gas emissions at sea, and inform sustainable ocean development. The open data and tech used can pave the way for governments, researchers, and civil society to monitor and protect the ocean.

And reveals historical changes: The study also reveals how ocean industrialization is changing over time. While fishing activity dropped globally by about 12% during the COVID-19 pandemic, transport and energy activity remained stable. Offshore wind energy also showed the most growth, with turbines increasing ninefold in China and surpassing oil platforms in number by 2021.

Tags: