Motion‐activated cameras (“camera traps”) are increasingly used in ecological and management studies for remotely observing wildlife and are amongst the most powerful tools for wildlife research. However, studies involving camera traps result in millions of images that need to be analysed, typically by visually observing each image, in order to extract data that can be used in ecological analyses. We trained machine learning models using convolutional neural networks with the ResNet‐18 architecture and 3,367,383 images to automatically classify wildlife species from camera trap images obtained from five states across the United States. We tested our model on an independent subset of images not seen during training from the United States and on an out‐of‐sample (or “out‐of‐distribution” in the machine learning literature) dataset of ungulate images from Canada. We also tested the ability of our model to distinguish empty images from those with animals in another out‐of‐sample dataset from Tanzania, containing a faunal community that was novel to the model. The trained model classified approximately 2,000 images per minute on a laptop computer with 16 gigabytes of RAM. The trained model achieved 98% accuracy at identifying species in the United States, the highest accuracy of such a model to date. Out‐of‐sample validation from Canada achieved 82% accuracy and correctly identified 94% of images containing an animal in the dataset from Tanzania. We provide an r package (Machine Learning for Wildlife Image Classification) that allows the users to (a) use the trained model presented here and (b) train their own model using classified images of wildlife from their studies. The use of machine learning to rapidly and accurately classify wildlife in camera trap images can facilitate non‐invasive sampling designs in ecological studies by reducing the burden of manually analysing images. Our r package makes these methods accessible to ecologists.

In the last half century, significant attention has been given to animal diseases; however, our understanding of disease processes and how to manage them at the livestock-wildlife interface remains limited. In this study, we conduct a systematic review of the scientific literature to evaluate the status of diseases at the livestock-wildlife interface in the United States. Specifically, the goals of the literature review were three fold: first to evaluate domestic animal diseases currently found in the United States where wildlife may play a role; second to identify critical issues faced in managing these diseases at the livestock-wildlife interface; and third to identify potential technical and policy strategies for addressing these issues. We found that of the 86 avian, ruminant, swine, poultry, and lagomorph diseases that are reportable to the World Organization for Animal Health (OIE), 53 are present in the United States; 42 (79%) of these have a putative wildlife component associated with the transmission, maintenance, or life cycle of the pathogen; and 21 (40%) are known to be zoonotic. At least six of these reportable diseases-bovine tuberculosis, paratuberculosis, brucellosis, avian influenza, rabies, and cattle fever tick (vector control)-have a wildlife reservoir that is a recognized impediment to eradication in domestic populations. The complex nature of these systems highlights the need to understand the role of wildlife in the epidemiology, transmission, and maintenance of infectious diseases of livestock. Successful management or eradication of these diseases will require the development of cross-discipline and institutional collaborations. Despite social and policy challenges, there remain opportunities to develop new collaborations and new technologies to mitigate the risks posed at the livestock-wildlife interface.

Cross-species disease transmission between wildlife, domestic animals and humans is an increasing threat to public and veterinary health. Wild pigs are increasingly a potential veterinary and public health threat. Here we investigate 84 pathogens and the host species most at risk for transmission with wild pigs using a network approach. We assess the risk to agricultural and human health by evaluating the status of these pathogens and the co-occurrence of wild pigs, agriculture and humans. We identified 34 (87%) OIE listed swine pathogens that cause clinical disease in livestock, poultry, wildlife, and humans. On average 73% of bacterial, 39% of viral, and 63% of parasitic pathogens caused clinical disease in other species. Non-porcine livestock in the familyBovidaeshared the most pathogens with swine (82%). Only 49% of currently listed OIE domestic swine diseases had published wild pig surveillance studies. The co-occurrence of wild pigs and farms increased annually at a rate of 1.2% with as much as 57% of all farms and 77% of all agricultural animals co-occurring with wild pigs. The increasing co-occurrence of wild pigs with livestock and humans along with the large number of pathogens shared is a growing risk for cross-species transmission.

Wild pigs (Sus scrofa), also known as wild swine, feral pigs, or feral hogs, are one of the most widespread and successful invasive species around the world. Wild pigs have been linked to extensive and costly agricultural damage and present a serious threat to plant and animal communities due to their rooting behavior and omnivorous diet. We modeled the current distribution of wild pigs in the United States to better understand the physiological and ecological factors that may determine their invasive potential and to guide future study and eradication efforts. Using national-scale wild pig occurrence data reported between 1982 and 2012 by wildlife management professionals, we estimated the probability of wild pig occurrence across the United States using a logistic discrimination function and environmental covariates hypothesized to influence the distribution of the species. Our results suggest the distribution of wild pigs in the U.S. was most strongly limited by cold temperatures and availability of water, and that they were most likely to occur where potential home ranges had higher habitat heterogeneity, providing access to multiple key resources including water, forage, and cover. High probability of occurrence was also associated with frequent high temperatures, up to a high threshold. However, this pattern is driven by pigs’ historic distribution in warm climates of the southern U.S. Further study of pigs’ ability to persist in cold northern climates is needed to better understand whether low temperatures actually limit their distribution. Our model highlights areas at risk of invasion as those with habitat conditions similar to those found in pigs’ current range that are also near current populations. This study provides a macro-scale approach to generalist species distribution modeling that is applicable to other generalist and invasive species.

The One Health initiative is a global effort fostering interdisciplinary collaborations to address challenges in human, animal, and environmental health. While One Health has received considerable press, its benefits remain unclear because its effects have not been quantitatively described. We systematically surveyed the published literature and used social network analysis to measure interdisciplinarity in One Health studies constructing dynamic pathogen transmission models. The number of publications fulfilling our search criteria increased by 14.6% per year, which is faster than growth rates for life sciences as a whole and for most biology subdisciplines. Surveyed publications clustered into three communities: one used by ecologists, one used by veterinarians, and a third diverse-authorship community used by population biologists, mathematicians, epidemiologists, and experts in human health. Overlap between these communities increased through time in terms of author number, diversity of co-author affiliations, and diversity of citations. However, communities continue to differ in the systems studied, questions asked, and methods employed. While the infectious disease research community has made significant progress toward integrating its participating disciplines, some segregation—especially along the veterinary/ecological research interface—remains. A cohesive reaction to emerging threats requires the efficient dissemination of knowledge and methodologies across multiple disciplinary boundaries. A “One Health” approach has been advocated to facilitate cross-disciplinary communication and research in responding to challenges in human, animal, and environmental health. We empirically describe collaboration networks surrounding one aspect of this One Health initiative: infectious disease transmission models. A systematic literature review and social network analysis showed that dynamic disease modelling grew faster than most biological and natural science disciplines over the last 25 y, yet the field remains somewhat compartmentalized. Many researchers contribute to a broad, cross-disciplinary group of journals, but publications from veterinarians and ecologists remain segregated into relatively discrete communities. While the veterinary and ecological communities regularly reference the broad, cross-disciplinary group, they only rarely cite each other; furthermore, the highest-tiered medical journals contributed very few papers to our search. Therefore, our results are somewhat mixed: while One Health may have precipitated a great deal of research interest in infectious disease, it has not fully overcome the barriers that segregate its contributing disciplines.