The polar regions are among the most inaccessible places on our planet. Discovering where different seal species reside in this rapidly changing environment is challenging. Researchers from the Royal Netherlands Institute for Marine Research (NIOZ), Wageningen University & Research (WUR) and Aeria visited the waters around Svalbard, Norway, to make high-resolution drone images of different types of seals. After comparing these drone images with satellite images, algorithms can be developed to automate the detection of seals in satellite images. To the researchers’ surprise, these satellite images revealed not only the location of the breathing holes, but also the traces of polar bears. These images from space are a very valuable conservation tool for Arctic marine mammals, which rely heavily on sea ice, which is rapidly dwindling due to global warming.
This summer, researchers were able to collect stunning drone images of ringed seals and walruses. In one fjord, St. Johnsfjorden, twelve ringed seals were found scattered throughout the fjord, resting on fast ice. However, getting close to and identifying these individuals is a major challenge. Since polar bears hunt ringed seals, any mammal—whether it walks on all fours or two feet—will be avoided at all costs.
“Using a drone, we were able to take high-resolution images of ringed seals on ice resting next to their breathing holes. Based on these images, the species can be easily identified. Arctic Seal Project. For this specific area, the researchers also obtained Maxar satellite images. Since the ice is landlocked and does not move, the locations of the breathing holes are practically fixed. Therefore, researchers can match individual seals on the drone’s image directly to the breathing holes visible in satellite images. “Although we were aware of the potential of these satellite imagery in observing mammals from space, we were shocked to notice white streaks across the ice shield connecting the seals’ breathing holes. In this remote and hostile environment, this can only mean one thing, trails Polar bear “.
Machine learning to count arthropod mammals
The resolution of satellite images has improved greatly in the past decade. These satellites, which orbit the Earth at an altitude of more than 600 km, can image anywhere on the Earth’s surface with a resolution of 30 x 30 cm. By downsizing high-quality drone images to a resolution of 30 x 30 cm, researchers can create an image that simulates satellite images taken from space. Ultimately, these images can then be fed to a machine learning algorithm and used to train a file neural network‘,” says Jeroen Hoekendijk, PhD candidate, who was part of the research team and is working together. EPFL to further develop these technologies. By applying this trained network to satellite imagery, the researchers hope to be able to automatically detect seals in these remote and hostile areas.
Arctic seal species use ice differently
Seals and walruses are especially abundant in the Arctic regions. Each of these species has its own unique characteristics and relationship to sea ice.
Ringed seals, for example, make breathing holes in sea ice installed on the coast. These breathing tubes can be several meters long and connect the sea water under the ice with the air above. By using their claws on their front fins, they prevent these breathing holes from freezing. During the long, dark winter months, snow covers these breathing holes. These snow dens provide their young ones with some protection from the harsh conditions outside.
In contrast, harp seals rest and give birth on drifting ice. This ice pack covers most of the Arctic in winter, and connects all land masses in the polar region, but decreases in size during the summer months. Unlike fast ice, an ice pack drifts and can move several kilometers per day. Sudden changes in the direction of the current and the wind can quickly cause the birth platform of the harp seal to collapse. Walruses also benefit from an ice pack, but individuals can also be found resting on the ground. Also, during this summer’s Svalbard research expedition, researchers were able to collect drone images from Walruses that may help others To develop machine learning techniques similar to these types.
Change home quickly
Ultimately, the researchers hope to use these remote sensing techniques to locate seals in the Arctic. Because of climate change, their home is changing rapidly. This is especially the case for the North Barents Sea and the islands of Svalbard and Franz Josef Land. This region is the fastest warming place on Earth , where average temperatures rise by 2.7°C per decade, and up to 4°C per decade during the autumn months. Therefore, there is an urgent need to know the habitats that seals depend on to study the impact of climate change and the conservation of this species.
Disclaimer: AAAS and EurekAlert! is not responsible for the accuracy of newsletters sent on EurekAlert! Through the contributing institutions or for the use of any information through the EurekAlert system.