Search

Abstract Large herbivores in seasonal environments often experience mass variation due to temporal changes in the availability of critical resources like water and forage, as well as due to breeding events. Yet the documentation of mass variation in mammals of highly seasonal savanna habitats, which host the highest densities of grazing ungulates globally, has rarely been explored. Here, we showcase a method to evaluate seasonal mass variation in bovids. Our method used mineral‐baited scales and camera traps to enable us to track the body mass of three species through a period of wet and dry seasons in a South African savanna ecosystem. To illustrate one potential application of the method, we related body mass data to time, weather and resource availability. This showed that individuals altered their body masses markedly between seasons with, for example, female Kudu (Tragelaphus strepsiceros) gaining, on average, >21 kg over the 15‐week wet‐season period in 1 year. These changes were positively related to factors such as vegetation productivity (assessed using NDVI) and the frequency of rains. This method enables easy, non‐lethal and non‐invasive acquisition of mass data. The equipment is easy to deploy concurrently over large areas. Monitoring by this method has a variety of possible applications, potentially providing a useful early‐warning indicator of body condition to inform management, or providing information about ecological states, such as parturition or the reproductive effort of males. Given the longer and harsher dry seasons experienced in many arid systems in recent decades, and projected in future, this method may provide a straightforward means of monitoring long‐term body condition in animals as a result of environmental change.

Abstract Camera traps have great potential for generating wildlife insights by providing high resolution site‐specific data. Methods of data collection and analysis reliant on these tools for population density estimation can be relatively resource intensive, hindering their mainstream adoption. Here, we explore the potential of population density estimates derived from a distance sampling method based on optics theory, which greatly simplifies the process of setting up camera sites and analysing data. Specifically, we (1) tested the method on human subjects in an artificial environment, (2) compared it to another method relying on virtual grids on images using wild populations of black‐backed jackal (Canis mesomelas) and African civet (Civettictis civetta) in South Africa and (3) deployed it to estimate wild boar (Sus scrofa) population densities in Hungary. The initial human trials resulted in an estimate that was extremely close to true population density. When compared to the virtual grid method, results suggest that our distance sampling method can deliver accurate estimates with increased convenience and robustness against disruptions of the camera sites. The wild boar study resulted in a realistic density estimate, which can be used as a baseline when assessing future fluctuations in population density. As this new approach does not have special requirements for setting up camera sites, it is efficient and widely applicable across other density estimation methods requiring an estimate for effective detection distance. Additionally, the method can be applied in the retrospective analysis of existing datasets.

Climate change is shifting the transmission of parasites, which is determined by host density, ambient temperature and moisture. These shifts can lead to increased pressure from parasites, in wild and domestic animals, and can impact the effectiveness of parasite control strategies. Understanding the interactive effects of climate on host movement and parasite life histories will enable targeted parasite management, to ensure livestock productivity and avoid additional stress on wildlife populations. To assess complex outcomes under climate change, we applied a gastrointestinal nematode transmission model to a montane wildlife–livestock system, based on host movement and changes in abiotic factors due to elevation, comparing projected climate change scenarios with the historic climate. The wildlife host, Alpine ibex (Capra ibex ibex), undergoes seasonal elevational migration, and livestock are grazed during the summer for eight weeks. Total parasite infection pressure was more sensitive to host movement than to the direct effect of climatic conditions on parasite availability. Extended livestock grazing is predicted to increase parasite exposure for wildlife. These results demonstrate that movement of different host species should be considered when predicting the effects of climate change on parasite transmission, and can inform decisions to support wildlife and livestock health.

Abstract Camera traps are increasingly used in wildlife monitoring and citizen science to address an array of ecological questions on a wide variety of species. However, despite the ability of modern camera traps to capture high‐quality video, the majority of studies collect still images, in part because of concerns with video performance. We conducted a camera trap survey of a forested landscape in the UK, using a grid of paired camera traps, to quantify the impact of using video compared to photos on the outcomes of ecological research and for participation and engagement of citizen scientists. Ecological outputs showed no difference between photo and video datasets, but comparison between expert and citizen science classifications showed citizen scientists were able to classify videos more accurately (average accuracy of 95% for video, 86% for photo). Furthermore, citizen scientists were more likely to volunteer additional information on age (provided for 61% videos and 30% photos) and sex (provided for 63% videos and 45% photos) of animals in video footage. Concerns over slow trigger speeds for videos did not appear to affect our datasets or the inferences gained. When combined with citizen science, video datasets are likely to be of higher quality due to increased classification accuracy. Consequently, we encourage researchers to consider the use of video for future camera‐trapping projects.

Abstract Accurate and precise density estimates are crucial for effective species management and conservation. However, efficient monitoring of mammal densities over large spatial and temporal scales is challenging. In the United Kingdom, published density estimates for many mammals, including species considered to be common, are imprecise. Camera trap distance sampling (CTDS) can estimate densities of multiple species at a time and has been used successfully in a small number of studies. However, CTDS has typically been used over relatively homogeneous landscapes, often over large time scales, making monitoring changes (by repeating surveys) difficult. In this study, we deployed camera traps at 109 sites across an area of 2725 km2 of varied habitat in North‐East England, United Kingdom. The 4‐month survey generated 51 447 photos of wild mammal species. Data were sufficient for us to use CTDS to estimate the densities of eight mammal species across the whole‐survey area and within four specific habitats. Both survey‐wide and habitat‐specific density estimates largely fell within previously published density ranges and our estimates were amongst the most precise produced for these species to date. Lower precision for some species was typically due to animals being missed by the camera at certain distances, highlighting the need for careful consideration of practical and methodological decisions, such as how high to set cameras and where to left‐truncate data. Although CTDS is a promising methodology for determining densities of multiple species from one survey, species‐specific decisions are still required and these cannot always be generalized across species types and locations. Taking the United Kingdom as a case study, our study highlights the potential for CTDS to be used on a national scale, although the scale of the task suggests that it would need to be integrated with a citizen science approach.

Effective wildlife population management requires an understanding of the abundance of the target species. In the United Kingdom, the increase in numbers and range of the non-native invasive grey squirrel Sciurus carolinensis poses a substantial threat to the existence of the native red squirrel S. vulgaris, to tree health, and to the forestry industry. Reducing the number of grey squirrels, is crucial to mitigate their impacts. Camera traps are increasingly used to estimate animal abundance, and methods have been developed that do not require the identification of individual animals. Most of these methods have been focussed on medium to large mammal species with large range sizes and may be unsuitable for measuring local abundances of smaller mammals that have variable detection rates and hard to measure movement behaviour. The aim of this study was to develop a practical and cost-effective method, based on a camera trap index, that could be used by practitioners to estimate target densities of grey squirrels in woodlands to provide guidance on the numbers of traps or contraceptive feeders required for local grey squirrel control. Camera traps were deployed in ten independent woods of between 6 and 28 ha in size. An index, calculated from the number of grey squirrel photographs recorded per camera per day had a strong linear relationship (R2 = 0.90) with the densities of squirrels removed in trap and dispatch operations. From different time filters tested, a 5 min filter was applied, where photographs of squirrels recorded on the same camera within 5 min of a previous photograph were not counted. There were no significant differences between the number of squirrel photographs per camera recorded by three different models of camera, increasing the method’s practical application. This study demonstrated that a camera index could be used to inform the number of feeders or traps required for grey squirrel management through culling or contraception. Results could be obtained within 6 days without requiring expensive equipment or a high level of technical input. This method can easily be adapted to other rodent or small mammal species, making it widely applicable to other wildlife management interventions.

Abstract Mesocarnivores are of particular interest in wildlife management. Their adaptability makes them a focus of public attention globally, as negative interactions with people occur regularly, but their importance to wider ecosystem function is increasingly apparent. Robust methods for estimating mesocarnivore densities are essential for long‐term management strategies. Estimating densities of unmarked populations remains challenging, but new methods, based on camera trapping, have recently become available and require field testing. We conducted two camera trap surveys over two 200 km2 areas of commercial farmland in South Africa. One survey sampled 25 locations, while the second used a migrating grid to sample 59 locations; total sampling effort was similar across the two surveys. We applied distance sampling with camera traps (CTDS), developing a method to estimate animal distances by applying a distance measurement overlay grid to camera trap images. We aimed to establish meaningful density estimates of the mesocarnivore guild and evaluate CTDS's suitability for broader use with these types of species. We obtained density estimates for four carnivores, African civet Civettictis civetta, black‐backed jackal Canis mesomelas, brown hyena Hyaena brunnea and caracal Caracal caracal, providing valuable insight into their status in commercial farmland. Imprecision in the estimates was almost exclusively due to encounter rate variance, which was not reduced with the migrating camera grid. We explored the sensitivity of our results to assumptions determining the value of the ‘snapshot interval’, demonstrating that careful selection of this parameter is vital to ensuring reliable estimates when using rapid‐fire photo burst modes. CTDS can provide useful density estimates for mesocarnivores, but future studies should aim to maximize precision and reliability by increasing sampling locations. More studies are required in areas with known densities to promote confidence in accuracy.

Abstract The energy used by animals is influenced by intrinsic (e.g. physiological) and extrinsic (e.g. environmental) factors. Accelerometers within biologging devices have proven useful for assessing energy expenditures and their behavioural context in free-ranging animals. However, certain assumptions are frequently made when acceleration is used as a proxy for energy expenditure, with factors, such as environmental variation (e.g. ambient temperature or slope of terrain), seldom accounted for. To determine the possible interactions between behaviour, energy expenditure and the environment (ambient temperature and terrain slope), the rate of oxygen consumption ( $${\dot{\text{V}}\text{O}}_{2}$$ V ˙ O 2 ) was measured in pygmy goats (Capra hircus aegarus) using open-flow indirect calorimetry. The effect of temperature (9.7–31.5 °C) on resting energy expenditure was measured. The relationship between $${\dot{\text{V}}\text{O}}_{2}$$ V ˙ O 2 and dynamic body acceleration (DBA) was measured at different walking speeds (0.8–3.0 km h−1) and on different inclines (0, + 15°, − 15°). The daily behaviour of individuals was measured in two enclosures: enclosure A (level terrain during summer) and enclosure B (sloped terrain during winter) and per diem energy expenditures of behaviours estimated using behaviour, DBA, temperature, terrain slope and $${\dot{\text{V}}\text{O}}_{2}$$ V ˙ O 2 . During rest, energy expenditure increased below 22 °C and above 30.5 °C. $${\dot{\text{V}}\text{O}}_{2}$$ V ˙ O 2 (ml min−1) increased with DBA when walking on the level. Walking uphill (+ 15°) increased energetic costs three-fold, whereas walking downhill (− 15°) increased energetic costs by one third. Based on these results, although activity levels were higher in animals in enclosure A during summer, energy expenditure was found to be significantly higher in the sloped enclosure B in winter (means of enclosures A and B: 485.3 ± 103.6 kJ day−1 and 744.5 ± 132.4 kJ day−1). We show that it is essential to account for extrinsic factors when calculating animal energy budgets. Our estimates of the impacts of extrinsic factors should be applicable to other free ranging ungulates.

Abstract In light of global biodiversity loss, there is an increasing need for large‐scale wildlife monitoring. This is difficult for mammals, since they can be elusive and nocturnal. In the United Kingdom, there is a lack of systematic, widespread mammal monitoring, and a recognized deficiency of data. Innovative new approaches are required. We developed MammalWeb, a portal to enable UK‐wide camera trapping by a network of citizen scientists and partner organizations. MammalWeb citizen scientists contribute to both the collection and classification of camera trap data. Following trials in 2013–2017, MammalWeb has grown organically to increase its geographic reach (e.g. ∼2000 sites in Britain). It has so far provided the equivalent of over 340 camera trap‐years of wild mammal monitoring, and produced nearly 440,000 classified image sequences and videos, of which, over 180,000 are mammal detections. We describe MammalWeb, its background, its development and the novel approaches we have for participation. We consider the data collected by MammalWeb participants, especially in light of their relevance to the main goals of wildlife monitoring: to provide spatial data, abundance data and temporal behavioural data. MammalWeb can complement existing approaches to mammal monitoring. Explicit accounting for spatial and temporal patterns in animal activity enables accounting of bias relative to ad hoc observational data. Estimating abundance presents challenges, as for many camera‐trapping studies, but we discuss the potential of the data as they stand, and opportunities to advance their value for abundance estimation. Challenges remain to MammalWeb's central missions of enhancing engagement with and connection to nature, and delivering policy‐relevant data on Britain's wild mammals. We discuss these challenges and the opportunities they provide for advances in respect of engagement, science and financial security. Our approach reduces administrative burden and increases spatial coverage and, as such, MammalWeb provides a useful addition to existing case studies of citizen science camera‐trapping program design. We believe MammalWeb is an important step towards fulfilling calls for UK‐wide mammal monitoring and our description of challenges identifies an agenda for fulfilling that purpose.

Birds are important indicators for monitoring both biodiversity and habitat health; they also play a crucial role in ecosystem management. Declines in bird populations can result in reduced ecosystem services, including seed dispersal, pollination and pest control. Accurate and long-term monitoring of birds to identify species of concern while measuring the success of conservation interventions is essential for ecologists. However, monitoring is time-consuming, costly and often difficult to manage over long durations and at meaningfully large spatial scales. Technology such as camera traps, acoustic monitors and drones provide methods for non-invasive monitoring. There are two main problems with using camera traps for monitoring: (a) cameras generate many images, making it difficult to process and analyse the data in a timely manner; and (b) the high proportion of false positives hinders the processing and analysis for reporting. In this paper, we outline an approach for overcoming these issues by utilising deep learning for real-time classification of bird species and automated removal of false positives in camera trap data. Images are classified in real-time using a Faster-RCNN architecture. Images are transmitted over 3/4G cameras and processed using Graphical Processing Units (GPUs) to provide conservationists with key detection metrics, thereby removing the requirement for manual observations. Our models achieved an average sensitivity of 88.79%, a specificity of 98.16% and accuracy of 96.71%. This demonstrates the effectiveness of using deep learning for automatic bird monitoring.

Abstract Background Animal-attached devices can be used on cryptic species to measure their movement and behaviour, enabling unprecedented insights into fundamental aspects of animal ecology and behaviour. However, direct observations of subjects are often still necessary to translate biologging data accurately into meaningful behaviours. As many elusive species cannot easily be observed in the wild, captive or domestic surrogates are typically used to calibrate data from devices. However, the utility of this approach remains equivocal. Methods Here, we assess the validity of using captive conspecifics, and phylogenetically-similar domesticated counterparts (surrogate species) for calibrating behaviour classification. Tri-axial accelerometers and tri-axial magnetometers were used with behavioural observations to build random forest models to predict the behaviours. We applied these methods using captive Alpine ibex (Capra ibex) and a domestic counterpart, pygmy goats (Capra aegagrus hircus), to predict the behaviour including terrain slope for locomotion behaviours of captive Alpine ibex. Results Behavioural classification of captive Alpine ibex and domestic pygmy goats was highly accurate (> 98%). Model performance was reduced when using data split per individual, i.e., classifying behaviour of individuals not used to train models (mean ± sd = 56.1 ± 11%). Behavioural classifications using domestic counterparts, i.e., pygmy goat observations to predict ibex behaviour, however, were not sufficient to predict all behaviours of a phylogenetically similar species accurately (> 55%). Conclusions We demonstrate methods to refine the use of random forest models to classify behaviours of both captive and free-living animal species. We suggest there are two main reasons for reduced accuracy when using a domestic counterpart to predict the behaviour of a wild species in captivity; domestication leading to morphological differences and the terrain of the environment in which the animals were observed. We also identify limitations when behaviour is predicted in individuals that are not used to train models. Our results demonstrate that biologging device calibration needs to be conducted using: (i) with similar conspecifics, and (ii) in an area where they can perform behaviours on terrain that reflects that of species in the wild.

Abstract Background Tri-axial accelerometers are frequently deployed on terrestrial quadrupedal mammals using collars, because they are easy to fit and are thought to have minimal impact on the subject. Collar-attached devices are not fixed to the body and can move independently of the body. This may result in inaccurate measures of acceleration, reducing the accuracy of measured body movement. We determined the effect of collar size and collar weight on acceleration measured by a collar-mounted accelerometer on a quadruped mammal. The aim was to suggest best practice for sizes and weights of collars on which to deploy tri-axial accelerometers. Using pygmy goats, Capra aegagrus hircus, which were trained to walk at different speeds (0.8–3.0 km/h) on a treadmill, we measured body acceleration using a collar-mounted tri-axial accelerometer, with different collar sizes (individual neck circumference + 1 cm to + 9 cm) and collar weight (0.4% to 1.2% of individual weight). Results There was a significant effect of collar size, collar weight and walking speed on measured acceleration. Measured acceleration was less accurate and more variable when collars were looser and heavier. To measure body acceleration more accurately, we found that collar size should be within 5 cm or 16% of an individual’s neck circumference when it was heavy (up to 1.2% of animal’s body weight) or within 7 cm (33%) of neck circumference if the collar was light (up to 0.6% of animal body weight). Conclusion We suggest that not only reporting collar size and weight for welfare purposes, but it is also important to consider these aspects for scientific rigour, to ensure data are collected as accurately as possible. We provide guidelines for researchers fitting collar-attached devices to ensure a higher degree of accuracy of recorded body acceleration.

Understanding to what extent geographic patterns in threatened species diversity are driven by environmental features or human activities could aid conservation. Here, Howard et al. investigate broad scale patterns in species richness of threatened vertebrates and test the role of environmental and anthropogenic drivers.

Citizen science schemes enable ecological data collection over very large spatial and temporal scales, producing datasets of high value for both pure and applied research. However, the accuracy of citizen science data is often questioned, owing to issues surrounding data quality and verification, the process by which records are checked after submission for correctness. Verification is a critical process for ensuring data quality and for increasing trust in such datasets, but verification approaches vary considerably between schemes. Here, we systematically review approaches to verification across ecological citizen science schemes that feature in published research, aiming to identify the options available for verification, and to examine factors that influence the approaches used. We reviewed 259 schemes and were able to locate verification information for 142 of those. Expert verification was most widely used, especially among longer-running schemes, followed by community consensus and automated approaches. Expert verification has been the default approach for schemes in the past, but as the volume of data collected through citizen science schemes grows and the potential of automated approaches develops, many schemes might be able to implement approaches that verify data more efficiently. We present an idealised system for data verification, identifying schemes where this system could be applied and the requirements for implementation. We propose a hierarchical approach in which the bulk of records are verified by automation or community consensus, and any flagged records can then undergo additional levels of verification by experts.

Abstract Rodents and other small mammals cause an increasing number of negative economic and environmental impacts worldwide. In the UK, the non‐native grey squirrel has a significant impact on the forestry industry and has caused the decline of the native red squirrel. Baits are used to deliver biocides and contraceptives to reduce overabundant wildlife populations and as vehicles for vaccines to control disease outbreaks. Bait‐delivered contraceptives are also being developed to manage grey squirrel populations in the UK. The effectiveness of bait‐delivered drugs on wildlife populations depends on the amount of bait consumed by individuals over time; therefore, it is important to understand individual level bait uptake in order to optimize delivery methods. Passive integrated transponder (PIT) tags are increasingly used to mark and monitor animal behaviour as they are cost‐effective, have minimal negative welfare impacts and have a lower tag loss rate than external tags, particularly in small animals. The aim of this study was to design and test a novel bait hopper equipped with a PIT‐tag reader and bait‐weighing device, to record bait uptake by individual grey squirrels for optimizing the delivery of a contraceptive bait. The hopper was designed to overcome some of the limitations of traditional PIT‐tag systems, by improving battery life and the quality and quantity of data collected in the field. In captive trials, the hopper proved to be highly effective at recording feeding visits by squirrels, as 95% of the visits could be attributed to a PIT‐tag record. The hoppers measured the amount of bait removed per feeding visit to an accuracy of 0.1 g, with 97% of the bait taken from six hoppers attributed to a PIT‐tag ID. In a field trial, the hoppers were effective at recording the feeding visits by grey squirrels in two woods, with 47 of the 51 PIT‐tagged grey squirrels entering the hoppers. The adaptability of the hopper design means that it has wider applications for wildlife management; in particular, efficacy studies for bait‐delivered substances in the context of wildlife disease control and/or population reduction.

Assessments of conservation status are typically based on short-term extinction risk, but the value of indicators that compare the current state of species (e.g., abundance or distribution) to potential baselines is increasingly recognised. The use of baselines in conservation legislation is hindered by ambiguity in how baselines should be determined and interpreted, leading to inconsistent application. Here, we explored the use of species’ potential ranges as a consistent means of quantifying baselines for assessing species’ distributions, a key component of conservation status. Using breeding birds of Great Britain (GB) as a case study, we simulated where bird species would be expected to occur today in a modelled world without human land use. We calculated indices that contrasted these potential human-free ranges with realised ranges. Our analyses revealed that 42% of GB birds have wider realised than potential ranges and 28% have narrower realised than potential ranges. These indices could lead to reassessments of current conservation priorities. Eighteen species assigned ‘least concern’ status by the GB regional IUCN Red List had much narrower realised than potential ranges, suggesting that their ranges are in a more degraded state than currently recognised by Red List criteria. Some of these species are not under active conservation management and could be candidates for higher prioritisation. Our approach provides a systematic means of quantifying range baselines that is not reliant on variable historic data or expert opinion and, thereby, provides a step forward in resolving a major contemporary problem in conservation assessment: how to set baselines in conservation consistently. The insights produced are also of wider scientific and cultural relevance, revealing where species would likely exist today in the absence of historic human impacts. This could be used to identify areas where targeted restoration actions might lead to the return of historically extirpated species, or even to novel colonists.

The capital and income breeding concept links energy resources used during reproduction to the timing of their acquisition. During reproduction, capital breeders rely on resources gained previously and accumulated for reproductive investment. By contrast, income breeders use mainly resources collected during the period of reproductive activity. Most commonly, this concept is applied to females; relatively few studies have considered males. Moreover, there has been little attention to the link between the capital-income divide and other aspects of mating strategy. We studied adult males of three wild ungulates with different levels of polygyny. A large dataset (4,264 red deer, 53,619 roe deer, and 13,537 Alpine chamois, respectively) was obtained during 2007–2017 in the whole territory of Slovenia and in the Trento province, Italy. During the rut, body mass loss of males in highly polygynous species was more than twice that of weakly polygynous species: on average, red deer stags lost 19.5%; chamois bucks 16.0%; and roe deer bucks 7.5% of their body mass. This indicates potential for a hitherto unrecognized link between the degree of intrasexual competition and the degree of capital mating. The variability in body mass at the end of the rut was clearly reduced in both highly polygynous species (from 15.1 to 9.4% in red deer, and from 12.5 to 10.5% in chamois), but did not change in roe deer. Finally, roe deer bucks had recovered body mass to that of the pre-rut period by just 2 months after the rut, while red deer stags did not manage to compensate the loss of weight until the end of the year. We suggest that, at least in ungulates, there is a link between the degree of polygyny and that of capital breeding. Males of capital and income breeders underwent body mass changes resulting from different reproductive investment during the rut. Capital breeders lost considerably more weight, and invested a variable amount of energy among individuals or among years, possibly to cope with different environmental or body conditions. In so doing, they ended the rut with poorer but more even condition among individuals.

Outdoor recreation is a known source of disturbance to many wildlife populations. We systematically reviewed 126 relevant papers that study the impact of outdoor recreation on wildlife, focusing on terrestrial wildlife (birds excluded) to assess the different methodological approaches adopted by researchers. We characterised the research methods into seven categories (direct observation, indirect observation (field-based), telemetry, camera traps, physiological measurement, trapping, and simulation). We find that direct observation is the most commonly used method to capture human-wildlife interactions, followed by the use of telemetry, and camera traps. The animals most commonly studied were ungulates, and the orders Carnivora and Rodentia. Studies typically captured data over longer periods (median 54 months) when using trapping methods; other methods exhibited shorter study durations (median 22 months). The size of the animal under study appears to influence how methods are chosen, with larger species often being studied using telemetry methods. We highlight advantages and disadvantages of each method depending on the aims of the study, the focal species, and the type of outdoor recreation. Our review highlights the need for simultaneous measurements of both human activity and wildlife response. We also recommend that researchers consider how to capture both short- and long-term impacts on animal welfare. Our findings should guide applied wildlife conservation and management research in scenarios where human-wildlife interactions lead to conservation issues.

Camera trapping has become an increasingly reliable and mainstream tool for surveying a diversity of wildlife species. Concurrent with this has been an increasing effort to involve the wider public in the research process, in an approach known as ‘citizen science’. To date, millions of people have contributed to research across a wide variety of disciplines as a result. Although their value for public engagement was recognised early on, camera traps were initially ill-suited for citizen science. As camera trap technology has evolved, cameras have become more user-friendly and the enormous quantities of data they now collect has led researchers to seek assistance in classifying footage. This has now made camera trap research a prime candidate for citizen science, as reflected by the large number of camera trap projects now integrating public participation. Researchers are also turning to Artificial Intelligence (AI) to assist with classification of footage. Although this rapidly-advancing field is already proving a useful tool, accuracy is variable and AI does not provide the social and engagement benefits associated with citizen science approaches. We propose, as a solution, more efforts to combine citizen science with AI to improve classification accuracy and efficiency while maintaining public involvement.