Automated Quantification of Brittle Stars in Seabed Imagery Using Computer Vision Techniques

Underwater video surveys play a significant role in marine benthic research. Usually, surveys are filmed in transects, which are stitched into 2D mosaic maps for further analysis. Due to the massive amount of video data and time-consuming analysis, the need for automatic image segmentation and quantitative evaluation arises. This paper investigates such techniques on annotated mosaic maps containing hundreds of instances of brittle stars. By harnessing a deep convolutional neural network with pre-trained weights and post-processing results with a common blob detection technique, we investigate the effectiveness and potential of such segment-and-count approach by assessing the segmentation and counting success. Discs could be recommended instead of full shape masks for brittle stars due to faster annotation among marker variants tested. Underwater image enhancement techniques could not improve segmentation results noticeably, but some might be useful for augmentation purposes.

A fully-annotated imagery dataset of sublittoral benthic species in Svalbard, Arctic

Underwater imagery is widely used for a variety of applications in marine biology and environmental sciences, such as classification and mapping of seabed habitats, marine environment monitoring and impact assessment, biogeographic reconstructions in the context of climate change, etc. This approach is relatively simple and cost-effective, allowing the rapid collection of large amounts of data. However, due to the laborious and time-consuming manual analysis procedure, only a small part of the information stored in the archives of underwater images is retrieved. Emerging novel deep learning methods open up the opportunity for more effective, accurate and rapid analysis of seabed images than ever before. We present annotated images of the bottom macrofauna obtained from underwater video recorded in Spitsbergen island's European Arctic waters, Svalbard Archipelago. Our videos were filmed in both the photic and aphotic zones of polar waters, often influenced by melting glaciers. We used artificial lighting and shot close to the seabed (<1 m) to preserve natural colours and avoid the distorting effect of muddy water. The underwater video footage was captured using a remotely operated vehicle (ROV) and a drop-down camera. The footage was converted to 2D mosaic images of the seabed. 2D mosaics were manually annotated by several experts using the Labelbox tool and co-annotations were refined using the SurveyJS platform. A set of carefully annotated underwater images associated with the original videos can be used by marine biologists as a biological atlas, as well as practitioners in the fields of machine vision, pattern recognition, and deep learning as training materials for the development of various tools for automatic analysis of underwater imagery.

Cleaning up seas using blue growth initiatives: Mussel farming for eutrophication control in the Baltic Sea

Eutrophication is a serious threat to aquatic ecosystems globally with pronounced negative effects in the Baltic and other semi-enclosed estuaries and regional seas, where algal growth associated with excess nutrients causes widespread oxygen free "dead zones" and other threats to sustainability. Decades of policy initiatives to reduce external (land-based and atmospheric) nutrient loads have so far failed to control Baltic Sea eutrophication, which is compounded by significant internal release of legacy phosphorus (P) and biological nitrogen (N) fixation. Farming and harvesting of the native mussel species (Mytilus edulis/trossulus) is a promising internal measure for eutrophication control in the brackish Baltic Sea. Mussels from the more saline outer Baltic had higher N and P content than those from either the inner or central Baltic. Despite their relatively low nutrient content, harvesting farmed mussels from the central Baltic can be a cost-effective complement to land-based measures needed to reach eutrophication status targets and is an important contributor to circularity. Cost effectiveness of nutrient removal is more dependent on farm type than mussel nutrient content, suggesting the need for additional development of farm technology. Furthermore, current regulations are not sufficiently conducive to implementation of internal measures, and may constitute a bottleneck for reaching eutrophication status targets in the Baltic Sea and elsewhere.

A comparative analysis of metabarcoding and morphology-based identification of benthic communities across different regional seas

In a world of declining biodiversity, monitoring is becoming crucial. Molecular methods, such as metabarcoding, have the potential to rapidly expand our knowledge of biodiversity, supporting assessment, management, and conservation. In the marine environment, where hard substrata are more difficult to access than soft bottoms for quantitative ecological studies, Artificial Substrate Units (ASUs) allow for standardized sampling. We deployed ASUs within five regional seas (Baltic Sea, Northeast Atlantic Ocean, Mediterranean Sea, Black Sea, and Red Sea) for 12-26 months to measure the diversity and community composition of macroinvertebrates. We identified invertebrates using a traditional approach based on morphological characters, and by metabarcoding of the mitochondrial cytochrome oxidase I (COI) gene. We compared community composition and diversity metrics obtained using the two methods. Diversity was significantly correlated between data types. Metabarcoding of ASUs allowed for robust comparisons of community composition and diversity, but not all groups were successfully sequenced. All locations were significantly different in taxonomic composition as measured with both kinds of data. We recovered previously known regional biogeographical patterns in both datasets (e.g., low species diversity in the Black and Baltic Seas, affinity between the Bay of Biscay and the Mediterranean). We conclude that the two approaches provide complementary information and that metabarcoding shows great promise for marine monitoring. However, until its pitfalls are addressed, the use of metabarcoding in monitoring of rocky benthic assemblages should be used in addition to classical approaches rather than instead of them.