Sea lions help scientists map southern Australia’s seafloor
News

Sea lions help scientists map southern Australia’s seafloor

In southern Australia, scientists have enlisted an unexpected team of helpers to map the ocean floor – and the sea lions have done their job well. Six different marine habitats were captured – including algal meadows and reefs – that make up southern Australia’s seabed, researchers report in a recently published study.

Our understanding of seabed habitats is limited, but video data from remotely operated vehicles and underwater cameras is starting to fill the gaps. However, these vessel-based surveys are time-consuming, expensive and challenging, especially in remote or deep-sea areas. To tackle this, an Australian research team devised an innovative solution that exceeded expectations. The researchers fitted small, lightweight video cameras and movement trackers on eight adult female Australian sea lions. The team had two goals: to understand the habitats and food critical for the endangered species, and to map the little-known seafloor off southern Australia’s coast.

Real-time position monitoring

In this fascinating study, high-definition colour video was captured by sea lions as they swam in the ocean, diving to depths greater than five metres during daylight hours. These cameras, attached to the sea lions, had batteries that allowed for 12–13 hours of total filming, spread over two to three days. This footage provided scientists with valuable insights into underwater habitats.

To track the sea lions’ movements, satellite-linked GPS loggers were used. These devices recorded the sea lions’ locations every two minutes when they surfaced, by capturing quick snapshots of satellite signals. If a dive lasted longer than two minutes, the location was recorded when the sea lion resurfaced. Only accurate data from five or more satellites was used, and any unrealistic data, such as that showing speeds over six metres per second, was filtered out.

The GPS data, transmitted via Argos systems on polar-orbiting satellites, allowed researchers to monitor the sea lions’ positions in real time. Additionally, time-depth recorders attached to the sea lions measured their diving depth every second, providing a detailed picture of their underwater behaviour.

Combining sea lion-captured data with AI

Using 89 hours of recordings taken by the sea lions, the researchers identified six seabed habitats covering 5,000 square kilometres of seabed in southern Australia. The researchers then used AI models to predict large habitat areas across the continental shelf of southern Australia, combining the data collected by the sea lions with other data gathered over 21 years.

While the sea lions were undeniably the stars of this project, the study also underscores the effectiveness of AI models – particularly random forest algorithms, a widely-used machine learning technique that combines the outputs of multiple decision trees to achieve a single prediction – in identifying diverse benthic habitats across the continental shelf. These models were validated using data from animal-borne video and other sources, revealing the potential to repurpose such data for broader marine research. This innovative approach not only advanced habitat mapping but also showcased the untapped value of data collected by marine animals.

To learn more about the findings of this study, read the scientific paper here.

Researchers equipped Australian sea lions with small, lightweight video cameras and movement trackers to assist in mapping the seabed. (Image courtesy: Rich Carey/Shutterstock)
Hydrography Newsletter

Value staying current with hydrography?

Stay on the map with our expertly curated newsletters.

We provide educational insights, industry updates, and inspiring stories from the world of hydrography to help you learn, grow, and navigate your field with confidence. Don't miss out - subscribe today and ensure you're always informed, educated, and inspired by the latest in hydrographic technology and research.

Choose your newsletter(s)