In a novel study that bridges marine biology and technology, researchers have taken a data-driven approach to understand the impact of ship noise on gilthead sea bream, a commercially important fish species. The study, led by Roee Diamant from the Hatter Department of Marine Technologies at the University of Haifa in Israel, and the Faculty of Electrical Engineering and Computing at the University of Zagreb in Croatia, was recently published in the journal ‘Ecological Informatics’, which translates to ‘Ecological Information Science’.
The research team exposed one group of gilthead sea bream to playback ship noise while observing a control group in a separate tank. Over the course of a month, they collected and analyzed millions of fish trajectories using a combination of MobileNetV2 and DeepSORT algorithms. This advanced technology allowed them to track and compare the behavior of the fish in both groups.
Diamant and his team found that the noise-exposed group exhibited changes in their movement patterns, such as speed, acceleration, and movement curvature. These behavioral changes were accompanied by physiological alterations, including a trend of reduced weight gain and shifts in beneficial and potentially harmful metabolites. However, the growth rates between the two groups were not significantly different.
“The results represent preliminary evidence of potential stress responses rather than conclusive proof of physiological stress,” Diamant explained. “This study should be viewed as a proof-of-concept demonstration of a multimodal approach that integrates behavioral and physiological indicators.”
The findings have significant implications for the maritime industry, particularly in the context of underwater radiated noise and its potential impact on marine life. As shipping traffic continues to increase, so does the level of noise pollution in our oceans. Understanding how this noise affects commercially important species like gilthead sea bream can help inform regulations and mitigation strategies.
For maritime professionals, this research underscores the importance of considering the environmental impact of underwater noise. It also highlights the potential for advanced technologies, such as machine learning and computer vision, to monitor and analyze marine life behavior. This could open up new opportunities for innovative solutions in marine conservation and sustainable fishing practices.
Moreover, the study’s multimodal approach, which combines behavioral and physiological indicators, could be applied to other species and environments, providing a more comprehensive understanding of the impacts of human activities on marine ecosystems.
In the words of Diamant, “This is just the beginning. We hope that our work will inspire further research and collaboration between marine biologists, technologists, and the maritime industry to address the challenges posed by underwater noise pollution.”