3 January 2024 | Fernando S. Paolo, David Kroodsma, Jennifer Raynor, Tim Hochberg, Pete Davis, Jesse Cleary, Luca Marsaglia, Sara Orofino, Christian Thomas, Patrick Halpin
The study combines satellite imagery, vessel GPS data, and deep-learning models to map industrial vessel activities and offshore energy infrastructure across the world's coastal waters from 2017 to 2021. Key findings include:
1. **Industrial Fishing Vessels**: 72-76% of industrial fishing vessels are not publicly tracked, with significant activity around South Asia, Southeast Asia, and Africa.
2. **Transport and Energy Vessels**: 21-30% of transport and energy vessel activity is missing from public tracking systems.
3. **COVID-19 Impact**: Fishing activity decreased by 12 ± 1% at the onset of the pandemic in 2020 and had not recovered by 2021, while transport and energy activities remained relatively stable.
4. **Offshore Wind Energy**: Offshore wind energy is growing rapidly, surpassing the number of oil structures by 2021.
5. **Global Observational Data Limitations**: Lack of global observational data limits understanding of the expansion of the blue economy and its impact on developing nations and coastal communities.
6. **Deep Learning and Satellite Imagery**: Deep convolutional neural networks were used to identify and classify objects, estimate lengths, and classify vessels and infrastructure with high accuracy.
7. **Fixed Infrastructure**: By 2021, there were around 28,000 offshore structures, with wind turbines and oil structures constituting 48% and 38% of all ocean infrastructure, respectively.
8. **Vessel Traffic and Infrastructure Interactions**: Trawlers avoid areas near oil structures, while wind turbines may attract fish, though they are less likely to affect industrial fishing.
9. **Conclusion**: The study reveals the extent of major industrial activities at sea, highlighting the need for accurate mapping to understand and manage future human activities in the ocean.The study combines satellite imagery, vessel GPS data, and deep-learning models to map industrial vessel activities and offshore energy infrastructure across the world's coastal waters from 2017 to 2021. Key findings include:
1. **Industrial Fishing Vessels**: 72-76% of industrial fishing vessels are not publicly tracked, with significant activity around South Asia, Southeast Asia, and Africa.
2. **Transport and Energy Vessels**: 21-30% of transport and energy vessel activity is missing from public tracking systems.
3. **COVID-19 Impact**: Fishing activity decreased by 12 ± 1% at the onset of the pandemic in 2020 and had not recovered by 2021, while transport and energy activities remained relatively stable.
4. **Offshore Wind Energy**: Offshore wind energy is growing rapidly, surpassing the number of oil structures by 2021.
5. **Global Observational Data Limitations**: Lack of global observational data limits understanding of the expansion of the blue economy and its impact on developing nations and coastal communities.
6. **Deep Learning and Satellite Imagery**: Deep convolutional neural networks were used to identify and classify objects, estimate lengths, and classify vessels and infrastructure with high accuracy.
7. **Fixed Infrastructure**: By 2021, there were around 28,000 offshore structures, with wind turbines and oil structures constituting 48% and 38% of all ocean infrastructure, respectively.
8. **Vessel Traffic and Infrastructure Interactions**: Trawlers avoid areas near oil structures, while wind turbines may attract fish, though they are less likely to affect industrial fishing.
9. **Conclusion**: The study reveals the extent of major industrial activities at sea, highlighting the need for accurate mapping to understand and manage future human activities in the ocean.