Brown bear skin-borne secretions display evidence of individuality and age-sex variation.

Scent originates from excretions and secretions, and its chemical complexity in mammals translates into a diverse mode of signalling. Identifying how information is encoded can help to establish the mechanisms of olfactory communication and the use of odours as chemical signals. Building upon existing behavioural and histological literature, we examined the chemical profile of secretions used for scent marking by a solitary, non-territorial carnivore, the brown bear (Ursus arctos). We investigated the incidence, abundance, and uniqueness of volatile organic compounds (VOCs) from cutaneous glandular secretions of 12 wild brown bears collected during late and post-breeding season, and assessed whether age-sex class, body site, and individual identity explained profile variation. VOC profiles varied in the average number of compounds, compound incidence, and compound abundance by age-sex class and individual identity (when individuals were grouped by sex), but not by body site. Mature males differed from other age-sex classes, secreting fewer compounds on average with the least variance between individuals. Compound uniqueness varied by body site and age for both males and females and across individuals. Our results indicate that brown bear skin-borne secretions may facilitate age-sex class and individual recognition, which can contribute towards further understanding of mating systems and social behaviour.

Multispecies facial detection for individual identification of wildlife: a case study across ursids.

To address biodiversity decline in the era of big data, replicable methods of data processing are needed. Automated methods of individual identification (ID) via computer vision are valuable in conservation research and wildlife management. Rapid and systematic methods of image processing and analysis are fundamental to an ever-growing need for effective conservation research and practice. Bears (ursids) are an interesting test system for examining computer vision techniques for wildlife, as they have variable facial morphology, variable presence of individual markings, and are challenging to research and monitor. We leveraged existing imagery of bears living under human care to develop a multispecies bear face detector, a critical part of individual ID pipelines. We compared its performance across species and on a pre-existing wild brown bear Ursus arctos dataset (BearID), to examine the robustness of convolutional neural networks trained on animals under human care. Using the multispecies bear face detector and retrained sub-applications of BearID, we prototyped an end-to-end individual ID pipeline for the declining Andean bear Tremarctos ornatus. Our multispecies face detector had an average precision of 0.91-1.00 across all eight bear species, was transferable to images of wild brown bears (AP = 0.93), and correctly identified individual Andean bears in 86% of test images. These preliminary results indicate that a multispecies-trained network can detect faces of a single species sufficiently to achieve high-performance individual classification, which could speed-up the transferability and application of automated individual ID to a wider range of taxa. Supplementary Information: The online version contains supplementary material available at 10.1007/s42991-021-00168-5.

Automated facial recognition for wildlife that lack unique markings: A deep learning approach for brown bears.

Emerging technologies support a new era of applied wildlife research, generating data on scales from individuals to populations. Computer vision methods can process large datasets generated through image-based techniques by automating the detection and identification of species and individuals. With the exception of primates, however, there are no objective visual methods of individual identification for species that lack unique and consistent body markings. We apply deep learning approaches of facial recognition using object detection, landmark detection, a similarity comparison network, and an support vector machine-based classifier to identify individuals in a representative species, the brown bear Ursus arctos. Our open-source application, BearID, detects a bear's face in an image, rotates and extracts the face, creates an "embedding" for the face, and uses the embedding to classify the individual. We trained and tested the application using labeled images of 132 known individuals collected from British Columbia, Canada, and Alaska, USA. Based on 4,674 images, with an 80/20% split for training and testing, respectively, we achieved a facial detection (ability to find a face) average precision of 0.98 and an individual classification (ability to identify the individual) accuracy of 83.9%. BearID and its annotated source code provide a replicable methodology for applying deep learning methods of facial recognition applicable to many other species that lack distinguishing markings. Further analyses of performance should focus on the influence of certain parameters on recognition accuracy, such as age and body size. Combining BearID with camera trapping could facilitate fine-scale behavioral research such as individual spatiotemporal activity patterns, and a cost-effective method of population monitoring through mark-recapture studies, with implications for species and landscape conservation and management. Applications to practical conservation include identifying problem individuals in human-wildlife conflicts, and evaluating the intrapopulation variation in efficacy of conservation strategies, such as wildlife crossings.

A hypothetico-deductive approach to assessing the social function of chemical signalling in a non-territorial solitary carnivore.

The function of chemical signalling in non-territorial solitary carnivores is still relatively unclear. Studies on territorial solitary and social carnivores have highlighted odour capability and utility, however the social function of chemical signalling in wild carnivore populations operating dominance hierarchy social systems has received little attention. We monitored scent marking and investigatory behaviour of wild brown bears Ursus arctos, to test multiple hypotheses relating to the social function of chemical signalling. Camera traps were stationed facing bear 'marking trees' to document behaviour by different age sex classes in different seasons. We found evidence to support the hypothesis that adult males utilise chemical signalling to communicate dominance to other males throughout the non-denning period. Adult females did not appear to utilise marking trees to advertise oestrous state during the breeding season. The function of marking by subadult bears is somewhat unclear, but may be related to the behaviour of adult males. Subadults investigated trees more often than they scent marked during the breeding season, which could be a result of an increased risk from adult males. Females with young showed an increase in marking and investigation of trees outside of the breeding season. We propose the hypothesis that females engage their dependent young with marking trees from a young age, at a relatively 'safe' time of year. Memory, experience, and learning at a young age, may all contribute towards odour capabilities in adult bears.