Trine Hammer Jensen

Behavioral monitoring is central to welfare assessment but is difficult to conduct continuously. We used machine-learning-based video analysis to describe lion (Panthera leo) behavior across three zoo enclosures differing in available space, structural complexity and social composition. Interpretation of the Aalborg Zoo profile is additionally constrained by a major recent social change, as the enclosure’s adult male was euthanized five days before data collection began. Continuous recordings collected over 10 days were processed with LabGym, filtered for low-confidence predictions and likely static false detections, and summarized as behavioral durations. Because enclosure characteristics, pride size and cub presence varied only between three enclosures, enclosure was treated as the independent comparative unit; repeated hourly and daily observations were used to characterize within-enclosure temporal variation rather than to generate inferential replication. Analyses therefore focused on time budgets, daily and pooled activity, Shannon and Simpson diversity, within- and between-day behavioral instability, social interaction and pacing-like movement. The three enclosures showed distinct behavioral profiles. Diversity was lowest in Aalborg Zoo, social interaction did not increase consistently with pride size, and pacing-like movement was concentrated in Aalborg Zoo. However, the pacing-like measure should be interpreted as a screening indicator, as only 27.7% of manually annotated pacing-like lion-time was retained as pacing-like by the complete pipeline; it therefore cannot be interpreted as an estimate of true pacing prevalence. Activity was highest in Aalborg Zoo, but did not vary consistently with available space or structural complexity across the three enclosures. Automated quantification can support high-resolution exploratory welfare monitoring, but broader inference requires substantially more independently replicated enclosures.

Behavioral observation is central to animal welfare assessment in zoological institutions, but manual observation is time-consuming and difficult to apply continuously. We developed and applied a LabGym-based workflow for automated behavioral monitoring of captive lions (Panthera leo). Development footage from three Danish zoological institutions was used to train a lion detector and a seven-class behavior categorizer; video collected on 22–28 December 2025 was temporally held out from model development and used for applied validation. Detector performance was moderate (bounding-box AP 47.1%; segmentation AP 41.6%), while the internal categorizer validation reached 0.62 accuracy and weighted F1. In the held-out validation, 52.6% of manually annotated lion-time received a retained pipeline prediction. Fine-scale end-to-end accuracy was 0.231 and increased to 0.440 when calculated only on covered lion-time. Grouping behaviors as active, inactive/maintenance, and pacing-like locomotion increased these values to 0.317 and 0.602, respectively. Coverage varied substantially among institutions (33.8–59.8%) and was particularly low for cubs and nighttime footage. Although model macro-F1 exceeded simple majority-class baselines, end-to-end accuracy did not. The workflow demonstrates the potential of computer-vision approaches for scalable behavioral quantification and future welfare assessment in zoological settings, while highlighting the importance of accounting for prediction coverage and classification performance when interpreting automated behavioral data.

Determination of the causes of mortality in stranded marine mammals can contribute valuable information for conservation of wild populations, as well as contribute to risk assessments for different pathogens, hosts, and environmental conditions. This study examined necropsy reports for harbor (Phoca vitulina; n = 213) and gray (Halichoerus grypus; n = 40) seals stranded in Denmark in the period 2014 to 2021 to determine the causes of mortality where feasible. The likelihood that human interactions did or might have contributed to the mortality was also assessed. Infection with lungworms, heartworms, gastrointestinal roundworms, and influenza virus was tested for each seal in the data. Parasitic bronchopneumonia was the most common cause of death in both harbor (n = 68) and gray (n = 8) seals, and significantly more juveniles than adults died as a result of parasitic infections in the harbor seal cohort. Starvation was also a major cause of death in juvenile seals. Cause of death, death class (found dead, euthanized, or culled), and whether human interactions played a role in mortality did not vary significantly between the two species. Traumatic causes of death, resulting from confirmed or probable human interactions, were associated with adult and subadult seals of both species. Culling was the cause of death for 13.6% of harbor seals and 17.5% of gray seals.

This study investigates the possibility of using machine learning models created in DeepLabCut and Create ML to automate aspects of behavioral coding and aid in behavioral analysis. Two models with different capabilities and complexities were constructed and compared to a manually observed control period. The accuracy of the models was assessed by comparison with manually scoring, before being applied to seven nights of footage of the nocturnal behavior of two African elephants (Loxodonta africana). The resulting data were used to draw conclusions regarding behavioral differences between the two elephants and between individually observed nights, thus proving that such models can aid researchers in behavioral analysis. The models were capable of tracking simple behaviors with high accuracy, but had certain limitations regarding detection of complex behaviors, such as the stereotyped behavior sway, and displayed confusion when deciding between visually similar behaviors. Further expansion of such models may be desired to create a more capable aid with the possibility of automating behavioral coding.

This study investigates the possibility of using machine learning models created in DeepLabCut and Create ML to automate aspects of behavioral coding and aid in behavioral analysis. Two models with different capabilities and complexities were constructed and compared to a manually observed control period. The accuracy of the models was assessed before being applied to 7 nights of footage of the nocturnal behavior of two African elephants (Loxodonta africana). The resulting data was used to draw conclusions regarding behavioral differences between the two elephants and between individually observed nights, thus proving that such models can aid researchers in be-havioral analysis. The models were capable of tracking simple behaviors with high accuracy, but had certain limitations regarding detection of complex behaviors, such as the stereotyped behavior sway, and displayed confusion when deciding between visually similar behaviors. Further expansion of such models may be desired to create a more capable aid with the possibility of automating behavioral coding.

This article applies object detection to CCTV video material to investigate the potential of using machine learning to automate behavior tracking. This study includes video tapings of two captive Bornean orangutans and their behavior. From a 2 min training video containing the selected behaviors, 334 images were extracted and labeled using Rectlabel. The labeled training material was used to construct an object detection model using Create ML. The use of object detection was shown to have potential for automating tracking, especially of locomotion, whilst filtering out false positives. Potential improvements regarding this tool are addressed, and future implementation should take these into consideration. These improvements include using adequately diverse training material and limiting iterations to avoid overfitting the model.

The social- and self-directed behaviours of two golden lion tamarins (Leontopithecus rosalia) was investigated while having residence in the tropical house of Aalborg Zoo, Denmark. The behaviour of the female had been distinct from the male since 2018. Despite several diagnostic examinations and medicinal treatments, the cause of the aberrant and apparently stereotypical behavioural patterns remained undetermined, which initiated this study. The pair were recorded throughout a predetermined observation period and these recordings were analysed to illuminate the behaviours of the individuals. The results showed that there were differences in the type, frequency, and durations of both social- and self-directed behaviours between the sick female and the healthy male. The female expressed both social- and self-directed behaviours more frequently and for longer durations, while the male were more socially reserved and did not engage in social behaviours as frequently. Furthermore, subsequent necropsy of the female revealed uro-genital disease.

The white-beaked dolphin (Lagenorhynchus albirostris) is the second most frequently stranded cetacean species along the Danish coastline. The northern North Sea, the Skagerrak, the Kattegat and the Danish straits are part of the species distributional range. Here, we present eight incidents of breeding activity for the white-beaked dolphin in the inner Danish waters, reviewed from yearly reports made by the National Contingency Plan concerning strandings of marine mammals in Denmark from 2009 to 2023, Danish Wildlife Diseases Surveillance reports from 2014 to 2023 and the citizen science database Naturbasen in the period 2002 to 2023. Three pregnant females, three lactating females and one calf were found stranded in the inner Danish waters. Besides this, there have been live sightings of a female with a newborn calf. We conclude that the white-beaked dolphin is breeding in the inner Danish waters.

For the purpose of nature management and species conservation, European bison (Bison bonasus) are being increasingly reintroduced into nature reserves across Europe. The aim of this study was to investigate European bison’s adaptability to new areas through the study of their parasite-EPG (eggs per gram feces) and dietary diversity during twelve months after translocation. We compared the parasite-EPG from introduced European bison in Lille Vildmose, Denmark, with the parasite-EPG from populations from Bornholm, Denmark, and Białowieża Forest, Poland. From March 2021 to February 2022, fecal samples were collected from three populations. Samples from Lille Vildmose were examined through flotation, sedimentation, the Baermann technique, and nanopore sequencing. Fecal samples from Bornholm and Białowieża were examined through flotation and sedimentation. Nanopore sequencing of DNA from 63 European bison’s fecal samples collected during March–September in Lille Vildmose identified 8 species of nematodes within the digestive tract of the European bison, with Haemonchus contortus being the most frequently observed. In Lille Vildmose, a significantly higher excretion of nematode-EPG was observed during the summer period than in the spring, autumn, and winter. In addition, monthly differences in the excretion of nematode eggs were found, with this being significantly higher in June than in the months during autumn and winter (October–February). Significant differences in the nematode-EPG were only found between the excretion of nematode eggs in Białowieża Forest when compared to that of Lille Vildmose, with significantly higher excretion in Lille Vildmose (October–November). The results indicate that the development rates for nematodes may be affected by changes in temperature, with increasing temperatures speeding up their development time. Independent of this study design, wildlife vets together with the gamekeepers managing the herd found it necessary to treat the herd with antiparasitics for practical and animal welfare reasons in relation to translocation. Furthermore, 79 plant taxa were identified in the diet of the European bison. The broadest diet was observed in March suggesting that the European bison quickly adapted to their new habitat. The results suggest a seasonal shift in their diet, with this being most apparent from March to April.