Search for: All records

Abstract Antarctic krill (Euphausia superba) are considered a keystone species for higher trophic level predators along the West Antarctic Peninsula (WAP) during the austral summer. The connectivity of krill may play a critical role in predator biogeography, especially for central-place foragers such as thePygoscelisspp. penguins that breed along the WAP during the austral summer. Antarctic krill are also heavily fished commercially; therefore, understanding population connectivity of krill is critical to effective management. Here, we used a physical ocean model to examine adult krill connectivity in this region using simulated krill with realistic diel vertical migration behaviors across four austral summers. Our results indicate that krill north and south of Low Island and the southern Bransfield Strait are nearly isolated from each other and that persistent current features play a role in this lack of inter-region connectivity. Transit and entrainment times were not correlated with penguin populations at the large spatial scales examined. However, long transit times and reduced entrainment correlate spatially with the areas where krill fishing is most intense, which heightens the risk that krill fishing may lead to limited krill availability for predators. 

Pack-ice seals are key indicator species in the Southern Ocean. Their large size (2–4 m) and continent-wide distribution make them ideal candidates for monitoring programs via very-high-resolution satellite imagery. The sheer volume of imagery required, however, hampers our ability to rely on manual annotation alone. Here, we present SealNet 2.0, a fully automated approach to seal detection that couples a sea ice segmentation model to find potential seal habitats with an ensemble of semantic segmentation convolutional neural network models for seal detection. Our best ensemble attains 0.806 precision and 0.640 recall on an out-of-sample test dataset, surpassing two trained human observers. Built upon the original SealNet, it outperforms its predecessor by using annotation datasets focused on sea ice only, a comprehensive hyperparameter study leveraging substantial high-performance computing resources, and post-processing through regression head outputs and segmentation head logits at predicted seal locations. Even with a simplified version of our ensemble model, using AI predictions as a guide dramatically boosted the precision and recall of two human experts, showing potential as a training device for novice seal annotators. Like human observers, the performance of our automated approach deteriorates with terrain ruggedness, highlighting the need for statistical treatment to draw global population estimates from AI output. 

Fine-scale sea ice conditions are key to our efforts to understand and model climate change. We propose the first deep learning pipeline to extract fine-scale sea ice layers from high-resolution satellite imagery (Worldview-3). Extracting sea ice from imagery is often challenging due to the potentially complex texture from older ice floes (i.e., floating chunks of sea ice) and surrounding slush ice, making ice floes less distinctive from the surrounding water. We propose a pipeline using a U-Net variant with a Resnet encoder to retrieve ice floe pixel masks from very-high-resolution multispectral satellite imagery. Even with a modest-sized hand-labeled training set and the most basic hyperparameter choices, our CNN-based approach attains an out-of-sample F1 score of 0.698–a nearly 60% improvement when compared to a watershed segmentation baseline. We then supplement our training set with a much larger sample of images weak-labeled by a watershed segmentation algorithm. To ensure watershed derived pack-ice masks were a good representation of the underlying images, we created a synthetic version for each weak-labeled image, where areas outside the mask are replaced by open water scenery. Adding our synthetic image dataset, obtained at minimal effort when compared with hand-labeling, further improves the out-of-sample F1 score to 0.734. Finally, we use an ensemble of four test metrics and evaluated after mosaicing outputs for entire scenes to mimic production setting during model selection, reaching an out-of-sample F1 score of 0.753. Our fully-automated pipeline is capable of detecting, monitoring, and segmenting ice floes at a very fine level of detail, and provides a roadmap for other use-cases where partial results can be obtained with threshold-based methods but a context-robust segmentation pipeline is desired. 

Antarctic terrestrial biodiversity faces multiple threats, from invasive species to climate change. Yet no large-scale assessments of threat management strategies exist. Applying a structured participatory approach, we demonstrate that existing conservation efforts are insufficient in a changing world, estimating that 65% (at best 37%, at worst 97%) of native terrestrial taxa and land-associated seabirds are likely to decline by 2100 under current trajectories. Emperor penguins are identified as the most vulnerable taxon, followed by other seabirds and dry soil nematodes. We find that implementing 10 key threat management strategies in parallel, at an estimated present-day equivalent annual cost of US$23 million, could benefit up to 84% of Antarctic taxa. Climate change is identified as the most pervasive threat to Antarctic biodiversity and influencing global policy to effectively limit climate change is the most beneficial conservation strategy. However, minimising impacts of human activities and improved planning and management of new infrastructure projects are cost-effective and will help to minimise regional threats. Simultaneous global and regional efforts are critical to secure Antarctic biodiversity for future generations.