Vladimir N. Burkanov

Reliable demographic data are critical for seal population assessment and management, yet remain challenging to obtain from drone surveys without automated tools. Using data from harbor seal ( Phoca vitulina ) haulout surveys conducted in British Columbia, Canada, in 2023–2024, we developed and tested an automated pipeline that integrates detection, morphometric extraction, and size-class classification of seals into a single system. The pipeline combines cascaded DeepLabV3+ segmentation (water removal, colony-level seal detection, and individual body-contour refinement), principal component analysis (PCA)-based extraction of body length and maximum width, and three-class size-class determination based on body length (pups, juveniles, subadults/adults). We evaluated the pipeline on 2,483 manually annotated seals across four drone platforms (DJI Mavic 3 Thermal, Mavic 2 Pro, Mini 3 Pro and Mini 2), five substrate types, and two sensor modalities (RGB, thermal infrared). Aggregate detection F1 was 0.914. Orthomosaic geometric accuracy, quantified as the RMSE of calibration-rod length on the orthomosaic, ranged from 1.0 cm to 18.0 cm depending on the platform–altitude–substrate combination, a spread that aggregate metrics would mask. Relative to manual annotation on the same orthomosaics, automated RGB body lengths showed near-zero bias (−0.6 cm; RMSE = 12.5 cm), whereas automated thermal lengths were systematically shorter (bias −19.9 cm, RMSE = 24.1 cm), establishing the unsuitability of thermal imagery for automated quantitative pinniped morphometry. For RGB imagery, threshold classification by body length reached an overall accuracy (OA) of 78.7%; for individuals outside the uncertainty zones (defined as ±2 × the geometric RMSE on calibration rods around each class boundary), OA reached 90.9%. Within the RGB subset, OA was 78.9% at 20 m altitude, declining to 75.0% at 40 m where geometric error dominated. The pipeline enables automated demographic monitoring of pinniped haulouts with quantitatively characterized uncertainty across survey conditions.

The spotted seal (Phoca largha) population in the Bering Sea is likely influenced by sea-ice conditions that affect abundance, distribution, habitat use, mortality, and reproductive success. To assess their local abundance and distribution, we conducted drone-based surveys of coastal haulouts in Karaginsky Gulf, southwestern Bering Sea, from 21 to 29 July 2021. We surveyed 20 haulout sites with 64 drone flights, providing seal counts and group size composition estimates. Across all surveyed sites, we recorded a total of 4,057 individual seals. Age composition was inferred using historical size-age relationships from harvested seals. Drone imagery confirmed the presence of both young-of-the-year (YoY) and adults at haulouts. YoY made up 16% of seals at the end of July, consistent with historical reproductive and survival rates. Haulouts were categorized into two clusters based on YoY proportion: Cluster 1 averaged 33.3% YoY, and Cluster 2 averaged 11.7% YoY. These clusters differed in distribution: YoY seals were more common on haulouts surrounded by shallow waters. In contrast, the proportion of YoY was lower in the northern and eastern parts of the gulf, where deeper waters dominate near the continental shelf break. Our study confirms that historically used summer haulouts in Karaginsky Gulf remain active. These results highlight the importance of nearshore habitats for younger seals and suggest that depth-related habitat features (e.g., prey accessibility) influence haulout composition.

We assessed the potential of using a computer vision-based neural network to identify undigested parts of the diet in Steller sea lion feces samples. These samples were previously examined and identified by experts. We studied 19 types of bones and otoliths from 13 fish species found in the diet samples and accurately identified by expert morphologists. Each object was photographed against a black background in various projections using a microscope with a +10–15 magnification. This process resulted in 1513 photographs. To identify the undigested diet parts, we utilized the neural network model VGG 16, pre-trained on ImageNet data containing 1.4 million animal and plant images. The model was trained on 1469 photographs of diverse food residues using the R environment and the ‘keras’ package. The training accuracy over 60 epochs reached 99%. We tested the model on 44 images of Steller sea lion diet objects, not used during the training process. The model accurately identified fish remains with 100% accuracy. Computer vision enables quick and precise identification of food residues, reducing the analysis time and cost. It automates the identification process, eliminating human error. Our experiment involved a small data set and needs further research. To improve the feeding objects’ identification accuracy, a larger data set should be used, and the model should be validated on ad ditional test data. The main challenge of using computer vision to identify fish bones is obtaining sufficient photographs of different types of undigested food remains at different stages of digestion from all potential Steller sea lion prey items.

Freshwater populations of typically marine species present unique opportunities to investigate biodiversity, evolutionary divergence, and the adaptive potential and niche width of species. A few pinniped species have populations that reside solely in freshwater. The harbour seals inhabiting Iliamna Lake, Alaska constitute one such population. Their remoteness, however, has long hindered scientific inquiry. We used DNA from seal scat and tissue samples provided by Indigenous hunters to screen for mitochondrial DNA and microsatellite variation within Iliamna Lake and eight regions across the Pacific Ocean. The Iliamna seals (i) were substantially and significantly discrete from all other populations ( x ¯ F _st-mtDNA = 0.544, x ¯ Φ _{st - mtDNA} = 0.541, x ¯ F _{st-microsatellites} = 0.308), (ii) formed a discrete genetic cluster separate from all marine populations (modal ∆ k = 2, PC1 = 14.8%), had (iii) less genetic diversity (Hd, π , H _exp ), and (iv) higher inbreeding ( F ) than marine populations. These findings are both striking and unexpected revealing that Iliamna seals have likely been on a separate evolutionary trajectory for some time and may represent a unique evolutionary legacy for the species. Attention must now be given to the selective processes driving evolutionary divergence from harbour seals in marine habitats and to ensuring the future of the Iliamna seal.

Geographic differences in population growth trends are well-documented in Steller sea lions (Eumetopias jubatus), a species of North Pacific pinniped listed under the U.S. Endangered Species Act in 1990 following a marked decline in population abundance that began during the 1970s. As population growth is intrinsically linked to pup production and survival, examining factors related to pup physiological condition provides useful information to management authorities regarding potential drivers of regional differences. During dam foraging trips, pups predictably transition among three fasting phases, distinguished by the changes in the predominant metabolic byproduct. We used standardized ranges of two plasma metabolites (blood urea nitrogen and β–hydroxybutyrate) to assign pups to fasting categories (n = 1528, 1990–2016, 12 subpopulations): Recently Fed–Phase I (digestion/assimilation–expected hepatic/muscle glycogen usage), Phase II (expected lipid utilization), transitioning between Phases II–III (expected lipid utilization with increased protein reliance), or Phase III (expected protein catabolism). As anticipated, the majority of pups were classified as Recently Fed–Phase I (overall mean proportion = 0.72) and few pups as Phase III (overall mean proportion = 0.04). By further comparing pups in Short (Recently Fed–Phase II) and Long (all other pups) duration fasts, we identified three subpopulations with significantly (P < 0.03) greater proportions of pups dependent upon endogenous sources of energy for extended periods, during a life stage of somatic growth and development: the 1) central (0.27 ± 0.09) and 2) western (0.36 ± 0.13) Aleutian Island (declining population trend) and 3) southern Southeast Alaska (0.32 ± 0.06; increasing population trend) subpopulations had greater Long fast proportions than the eastern Aleutian Islands (0.10 ± 0.05; stabilized population). Due to contrasting population growth trends among these highlighted subpopulations over the past 50+ years, both density-independent and density-dependent factors likely influence the dam foraging trip duration, contributing to longer fasting durations for pups at some rookeries.

Cetacean species are highly mobile, most of them regularly travelling over long distances, thereby presenting complex obstacles to their conservation. Identification of their critical habitats, specifically those parts of a cetacean’s range that are essential for day‐to‐day survival and for maintaining a healthy population growth rate, is necessary for their effective protection. This study presents a summary of the data on cetacean sightings during surveys that covered substantial parts of the Russian Far East coastal waters from the Okhotsk Sea to Chukotka in order to determine important areas for particular cetacean species. Sixteen cetacean species were registered during the surveys, and for 12 of them with sufficient numbers of sightings, zones with maximum sighting rates were identified. Only 13% of all cetacean sightings and 22% of sightings of protected species occurred within marine protected areas (MPAs). The highest sighting rates for protected species were concentrated off north‐eastern Sakhalin Island, in the Shantar Area, in Anadyr Gulf, in Kresta Bay and in the waters off eastern Chukotka. The analysis of the distribution patterns of various cetacean species in Russian Far East seas provides a solid base for future conservation planning. Lack of specific MPAs for protection of cetaceans and associated biodiversity hinders marine conservation in Russian Far East seas. The study highlights the specific zones important for various cetacean species and suggests the extension of some existing MPAs and the creation of new MPAs for future spatial habitat protection measures.

Васюков Е.С., Кириллова А.Д., Бурканов В.Н.//2022

Recent findings that some gray whales that feed off Sakhalin Island (SI), Russia, in the western North Pacific (WNP) overwinter in the eastern North Pacific (ENP) indicate that population structure in this species is more complex than originally thought. We generated mitochondrial DNA (mtDNA) control region sequences and microsatellite genotypes (n = 12 loci) from 156 whales sampled off SI and compared them to available data from 106 ENP whales. Significant mitochondrial and nuclear genetic differentiation between the SI and ENP whales was found. Genetic cluster analysis identified two groups among the SI whales, one of which was genetically similar to ENP whales. Photographs collected from the biopsied SI whales showed that both groups comprised whales known to migrate to the ENP, suggesting that the clustering pattern was not reflective of some SI whales interbreeding while overwintering in the WNP. Instead, the genetic differentiation observed between the SI and ENP whales may be due to assortative mating of SI whales while west of eastern migratory routes. The rare but continued reports of gray whales off the coasts of Japan and China, however, confirm that some gray whales overwinter in the WNP and highlight the need to collect additional data from these whales.