Having accurate, detailed, and up-to-date information about the location and behavior of animals in the wild would improve our ability to study and conserve ecosystems. We investigate the ability to ...automatically, accurately, and inexpensively collect such data, which could help catalyze the transformation of many fields of ecology, wildlife biology, zoology, conservation biology, and animal behavior into “big data” sciences. Motion-sensor “camera traps” enable collecting wildlife pictures inexpensively, unobtrusively, and frequently. However, extracting information from these pictures remains an expensive, time-consuming, manual task. We demonstrate that such information can be automatically extracted by deep learning, a cutting-edge type of artificial intelligence. We train deep convolutional neural networks to identify, count, and describe the behaviors of 48 species in the 3.2 million-image Snapshot Serengeti dataset. Our deep neural networks automatically identify animals with >93.8% accuracy, and we expect that number to improve rapidly in years to come. More importantly, if our system classifies only images it is confident about, our system can automate animal identification for 99.3% of the data while still performing at the same 96.6% accuracy as that of crowdsourced teams of human volunteers, saving >8.4 y (i.e., >17,000 h at 40 h/wk) of human labeling effort on this 3.2 million-image dataset. Those efficiency gains highlight the importance of using deep neural networks to automate data extraction from camera-trap images, reducing a roadblock for this widely used technology. Our results suggest that deep learning could enable the inexpensive, unobtrusive, high-volume, and even real-time collection of a wealth of information about vast numbers of animals in the wild.
Full text
Available for:
BFBNIB, NMLJ, NUK, PNG, SAZU, UL, UM, UPUK
Countries committed to implementing the Convention on Biological Diversity's 2011-2020 strategic plan need effective tools to monitor global trends in biodiversity. Remote cameras are a rapidly ...growing technology that has great potential to transform global monitoring for terrestrial biodiversity and can be an important contributor to the call for measuring Essential Biodiversity Variables. Recent advances in camera technology and methods enable researchers to estimate changes in abundance and distribution for entire communities of animals and to identify global drivers of biodiversity trends. We suggest that interconnected networks of remote cameras will soon monitor biodiversity at a global scale, help answer pressing ecological questions, and guide conservation policy. This global network will require greater collaboration among remote-camera studies and citizen scientists, including standardized metadata, shared protocols, and security measures to protect records about sensitive species. With modest investment in infrastructure, and continued innovation, synthesis, and collaboration, we envision a global network of remote cameras that not only provides real-time biodiversity data but also serves to connect people with nature.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NMLJ, NUK, OILJ, PNG, SAZU, SBCE, SBMB, UL, UM, UPUK
The conservation of large carnivores is a formidable challenge for biodiversity conservation. Using a data set on the past and current status of brown bears (Ursus arctos), Eurasian lynx (Lynx lynx), ...gray wolves (Canis lupus), and wolverines (Gulo gulo) in European countries, we show that roughly one-third of mainland Europe hosts at least one large carnivore species, with stable or increasing abundance in most cases in 21st-century records. The reasons for this overall conservation success include protective legislation, supportive public opinion, and a variety of practices making coexistence between large carnivores and people possible. The European situation reveals that large carnivores and people can share the same landscape.
Full text
Available for:
BFBNIB, NMLJ, NUK, PNG, SAZU, UL, UM, UPUK
Individually distinctive behavioral traits, or personalities, contribute to population-level processes and ecological interactions important in applied wildlife conservation research. ...Inter-individual variation in behavioral traits (personality) and correlation among behavioral traits (behavioral syndromes), can influence empirical estimates of population size and structure, models of resource selection and population dynamics, harvest and control in wildlife and fisheries populations, population response to disturbance and novel environments, and the success of reintroductions. Despite the important role that personality and behavioral syndromes play in the ecology and dynamics of wildlife populations, a disconnect between basic and applied research realms continues. While the concept of animal personalities and their role in ecology and evolution is increasingly embraced in the animal behavior, ecology, and evolutionary biology literature, it is less represented in applied wildlife management and conservation literature. We identify 10 research foci, often considered the domain of applied wildlife management and conservation, summarize examples of how these research domains may be influenced by personality and behavioral syndromes, and outline potential implications. We suggest that a focus on individuals in wildlife conservation study can bridge the gap between basic and applied research and incorporate knowledge from both realms towards more effective management, conservation, and recovery of populations.
•Animal personalities influence population parameters important for conservation.•We highlight 10 areas where personality influences wildlife research outcomes.•Areas include trapability, movement, disturbance, harvest, and reintroduction.•Accounting for personalities can reduce bias and improve conservation efforts.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
The onset of the COVID-19 pandemic brought an unusual decrease in human activity associated with partial and total lockdowns. Simultaneously, a series of wildlife sightings—mainly in urban areas—have ...been brought to public attention and often attributed to lockdown measures. Here we report on a series of wild carnivore records, including threatened species, obtained through camera traps set in urban forests, campuses, suburbs, and peri-urban areas of two cities in Chile, during partial lockdown measures. Our records are novel for Chile, a country where urban carnivore ecology is mostly unknown, and include the detection of four native carnivores, including the vulnerable güiña (Leopardus guigna) and the endangered southern river otter (Lontra provocax). These records also constitute a valuable baseline collected during partial lockdown measures in two cities of the Global South. We emphasize, however, that these findings cannot be used to argue for or against an effect of lockdown measures on wildlife. More generally, we call for caution in the interpretation of seemingly novel carnivore records during periods of lockdown and stress the value of international collaboration in evaluating the effects of the Anthropause on wildlife.
Display omitted
•Wildlife sightings during COVID-19-lockdowns have received considerable attention.•During partial lockdowns we recorded four native carnivores in Chilean cities.•None of the native species detected have been previously linked to urban areas.•It is difficult to determine if these records were influenced by partial lockdowns.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Great leaps forward in scientific understanding are often spurred by innovations in technology. The explosion of miniature sensors that are driving the boom in consumer electronics, such as smart ...phones, gaming platforms, and wearable fitness devices, are now becoming available to ecologists for remotely monitoring the activities of wild animals. While half a century ago researchers were attaching balloons to the backs of seals to measure their movement, today ecologists have access to an arsenal of sensors that can continuously measure most aspects of an animal's state (e.g., location, behavior, caloric expenditure, interactions with other animals) and external environment (e.g., temperature, salinity, depth). This technology is advancing our ability to study animal ecology by allowing researchers to (1) answer questions about the physiology, behavior, and ecology of wild animals in situ that would have previously been limited to tests on model organisms in highly controlled settings, (2) study cryptic or wide-ranging animals that have previously evaded investigation, and (3) develop and test entirely new theories. Here we explore how ecologists are using these tools to answer new questions about the physiological performance, energetics, foraging, migration, habitat selection, and sociality of wild animals, as well as collect data on the environments in which they live.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, INZLJ, KILJ, NLZOH, NMLJ, NUK, OILJ, PNG, SAZU, SBCE, SBMB, UL, UM, UPUK, ZRSKP
Anthropogenic noise is an important environmental stressor that is rapidly gaining attention among biologists, resource managers, and policy makers. Here we review a substantial literature detailing ...the impacts of noise on wildlife and provide a conceptual framework to guide future research. We discuss how several likely impacts of noise exposure have yet to be rigorously studied and outline how behavioral responses to noise are linked to the nature of the noise stimulus. Chronic and frequent noise interferes with animals' abilities to detect important sounds, whereas intermittent and unpredictable noise is often perceived as a threat. Importantly, these effects can lead to fitness costs, either directly or indirectly. Future research should consider the range of behavioral and physiological responses to this burgeoning pollutant and pair measured responses with metrics that appropriately characterize noise stimuli. This will provide a greater understanding of the mechanisms that govern wildlife responses to noise and help in identifying practical noise limits to inform policy and regulation.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NMLJ, NUK, OILJ, PNG, SAZU, SBCE, SBMB, UL, UM, UPUK
The last decade has seen a dramatic increase in the use of species distribution models (SDMs) to characterize patterns of species' occurrence and abundance. Efforts to parameterize SDMs often create ...a tension between the quality and quantity of data available to fit models. Estimation methods that integrate both standardized and non-standardized data types offer a potential solution to the tradeoff between data quality and quantity. Recently several authors have developed approaches for jointly modeling two sources of data (one of high quality and one of lesser quality). We extend their work by allowing for explicit spatial autocorrelation in occurrence and detection error using a Multivariate Conditional Autoregressive (MVCAR) model and develop three models that share information in a less direct manner resulting in more robust performance when the auxiliary data is of lesser quality. We describe these three new approaches ("Shared," "Correlation," "Covariates") for combining data sources and show their use in a case study of the Brown-headed Nuthatch in the Southeastern U.S. and through simulations. All three of the approaches which used the second data source improved out-of-sample predictions relative to a single data source ("Single"). When information in the second data source is of high quality, the Shared model performs the best, but the Correlation and Covariates model also perform well. When the information quality in the second data source is of lesser quality, the Correlation and Covariates model performed better suggesting they are robust alternatives when little is known about auxiliary data collected opportunistically or through citizen scientists. Methods that allow for both data types to be used will maximize the useful information available for estimating species distributions.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, INZLJ, KILJ, NLZOH, NMLJ, NUK, OILJ, PNG, SAZU, SBCE, SBMB, UL, UM, UPUK, ZRSKP
Quantifying animals' home ranges is a key problem in ecology and has important conservation and wildlife management applications. Kernel density estimation (KDE) is a workhorse technique for range ...delineation problems that is both statistically efficient and nonparametric. KDE assumes that the data are independent and identically distributed (IID). However, animal tracking data, which are routinely used as inputs to KDEs, are inherently autocorrelated and violate this key assumption. As we demonstrate, using realistically autocorrelated data in conventional KDEs results in grossly underestimated home ranges. We further show that the performance of conventional KDEs actually degrades as data quality improves, because autocorrelation strength increases as movement paths become more finely resolved. To remedy these flaws with the traditional KDE method, we derive an autocorrelated KDE (AKDE) from first principles to use autocorrelated data, making it perfectly suited for movement data sets. We illustrate the vastly improved performance of AKDE using analytical arguments, relocation data from Mongolian gazelles, and simulations based upon the gazelle's observed movement process. By yielding better minimum area estimates for threatened wildlife populations, we believe that future widespread use of AKDE will have significant impact on ecology and conservation biology.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, INZLJ, KILJ, NLZOH, NMLJ, NUK, OILJ, PNG, SAZU, SBCE, SBMB, UL, UM, UPUK, ZRSKP
Despite rapid growth in the field of reintroduction biology, results from scientific research are often not applied to translocations initiated when human land-use change conflicts with the continued ...persistence of a species' population at a particular site. Such mitigation-driven translocations outnumber and receive more funding than science-based conservation translocations, yet the conservation benefit of the former is unclear. Because mitigation releases are economically motivated, outcomes may be less successful than those of releases designed to serve the biological needs of species. Translocation as a regulatory tool may be ill-suited for biologically mitigating environmental damage caused by development. Evidence suggests that many mitigation-driven translocations fail, although the application of scientific principles and best practices would probably improve the success rate. Lack of transparency and failure to document outcomes also hinder efforts to understand the scope of the problem. If mitigation-driven translocations are to continue as part of the growing billion-dollar ecological consulting industry, it is imperative that the scale and effects of these releases be reported and evaluated.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NMLJ, NUK, OILJ, PNG, SAZU, SBCE, SBMB, UL, UM, UPUK