No abstract

Summary The difficulty of obtaining reliable individual identification of animals has limited researcher's ability to obtain quantitative data to address important ecological, behavioral, and conservation questions. Traditional marking methods placed animals at undue risk. Machine learning approaches for identifying species through analysis of animal images has been proved to be successful. But for many questions, there needs a tool to identify not only species but also individuals. Here, we introduce a system developed specifically for automated face detection and individual identification with deep learning methods using both videos and still-framed images that can be reliably used for multiple species. The system was trained and tested with a dataset containing 102,399 images of 1,040 individuals across 41 primate species whose individual identity was known and 6,562 images of 91 individuals across four carnivore species. For primates, the system correctly identified individuals 94.1% of the time and could process 31 facial images per second.

Following significant developments in technology, alternative devices have been applied in fieldwork for animal and plant surveys. Thermal‐image acquisition cameras installed on unmanned aerial vehicles (UAVs) have been used in animal surveys in the wilderness. This article demonstrates an example of how UAVs can be used in high mountainous regions, presenting a case study on the Sichuan snub‐nosed monkey with a detection rate of 65.19% for positive individual identification. It also presents a model that can prospectively predict population size for a given animal species, which is based on combined initial work using UAVs and traditional surveys on the ground. A great potential advantage of UAVs is significantly shortening survey procedures, particularly for areas with high mountains and plateaus, such as the Himalayas, the Qinghai–Tibet Plateau, Hengduan Mountains, the Yunnan‐Gui Plateau and Qinling Mountains in China, where carrying out a traditional survey is extremely difficult, so that species and population surveys, particularly for critically endangered animals, are largely absent. This lack of data has impacted the management of endangered animals as well as the formulation and amendment of conservation strategies.

Microbiota of the wild blue sheep (Pseudois nayaur) presents a seasonal variation due to different dietary selection and feeding strategies from different ecological niches chosen by different sex in summer. To address those issues, we analyzed the variation of gut microbiota based on the material from the feces, with 16S rRNA and meta-genome aimed to explore seasonal and gender differences. The results indicate that seasonal dietary changes and gender differentiation, as expected, cause the variation in sheep's gut microbiota structure. The variation of the former is more significant than the latter. Dominant Firmicutes exists a significantly higher abundance in summer than that in winter. Subordinate Bacteroides expresses no seasonal difference between the two seasons. Compared with the winter group, the summer group is featured by abundant enzymes digesting cellulose and generating short-chain fatty acids (SCFAs), such as beta-glucosidase (EC: 3.2.1.21) for cellulose digestion, and butyrate kinase (EC:2.7.2.7) in butyrate metabolism, implying that the changes of the composition in intestinal flora allow the sheep to adapt to the seasonalized dietary selection through alternated microbial functions to reach the goal of facilitating the efficiency of energy harvesting. The results also show that the blue sheep expresses a prominent sexual dimorphism in the components of gut microbiota, indicating that the two sexes have different adaptations to the dietary selection, and demands for physical and psychological purposes. Thus, this study provides an example of demonstrating the principles and regulations of natural selection and environmental adaptation.

No abstract