Optimizing the automated recognition of individual animals to support population monitoring.

Reliable estimates of population size and demographic rates are central to assessing the status of threatened species. However, obtaining individual-based demographic rates requires long-term data, which is often costly and difficult to collect. Photographic data offer an inexpensive, noninvasive method for individual-based monitoring of species with unique markings, and could therefore increase available demographic data for many species. However, selecting suitable images and identifying individuals from photographic catalogs is prohibitively time-consuming. Automated identification software can significantly speed up this process. Nevertheless, automated methods for selecting suitable images are lacking, as are studies comparing the performance of the most prominent identification software packages. In this study, we develop a framework that automatically selects images suitable for individual identification, and compare the performance of three commonly used identification software packages; Hotspotter, I3S-Pattern, and WildID. As a case study, we consider the African wild dog, Lycaon pictus, a species whose conservation is limited by a lack of cost-effective large-scale monitoring. To evaluate intraspecific variation in the performance of software packages, we compare identification accuracy between two populations (in Kenya and Zimbabwe) that have markedly different coat coloration patterns. The process of selecting suitable images was automated using convolutional neural networks that crop individuals from images, filter out unsuitable images, separate left and right flanks, and remove image backgrounds. Hotspotter had the highest image-matching accuracy for both populations. However, the accuracy was significantly lower for the Kenyan population (62%), compared to the Zimbabwean population (88%). Our automated image preprocessing has immediate application for expanding monitoring based on image matching. However, the difference in accuracy between populations highlights that population-specific detection rates are likely and may influence certainty in derived statistics. For species such as the African wild dog, where monitoring is both challenging and expensive, automated individual recognition could greatly expand and expedite conservation efforts.

High temperatures and human pressures interact to influence mortality in an African carnivore.

The impacts of high ambient temperatures on mortality in humans and domestic animals are well-understood. However much less is known about how hot weather affects mortality in wild animals. High ambient temperatures have been associated with African wild dog Lycaon pictus pup mortality, suggesting that high temperatures might also be linked to high adult mortality.We analyzed mortality patterns in African wild dogs radio-collared in Kenya (0°N), Botswana (20°S), and Zimbabwe (20°S), to examine whether ambient temperature was associated with adult mortality.We found that high ambient temperatures were associated with increased adult wild dog mortality at the Kenya site, and there was some evidence for temperature associations with mortality at the Botswana and Zimbabwe sites.At the Kenya study site, which had the highest human impact, high ambient temperatures were associated with increased risks of wild dogs being killed by people, and by domestic dog diseases. In contrast, temperature was not associated with the risk of snare-related mortality at the Zimbabwe site, which had the second-highest human impact. Causes of death varied markedly between sites.Pack size was positively associated with survival at all three sites.These findings suggest that while climate change may not lead to new causes of mortality, rising temperatures may exacerbate existing anthropogenic threats to this endangered species, with implications for conservation. This evidence suggests that temperature-related mortality, including interactions between temperature and other anthropogenic threats, should be investigated in a greater number of species to understand and mitigate likely impacts of climate change. ​.

Evaluating the status of African wild dogs Lycaon pictus and cheetahs Acinonyx jubatus through tourist-based photographic surveys in the Kruger National Park [corrected].

The Kruger National Park is a stronghold for African wild dog Lycaon pictus and cheetah Acinonyx jubatus conservation in South Africa. Tourist photographic surveys have been used to evaluate the minimum number of wild dogs and cheetahs alive over the last two decades. Photographic-based capture-recapture techniques for open populations were used on data collected during a survey done in 2008/9. Models were run for the park as a whole and per region (northern, central, southern). A total of 412 (329-495; SE 41.95) cheetahs and 151 (144-157; SE 3.21) wild dogs occur in the Kruger National Park. Cheetah capture probabilities were affected by time (number of entries) and sex, whereas wild dog capture probabilities were affected by the region of the park. When plotting the number of new individuals identified against the number of entries received, the addition of new wild dogs to the survey reached an asymptote at 210 entries, but cheetahs did not reach an asymptote. The cheetah population of Kruger appears to be acceptable, while the wild dog population size and density are of concern. The effectiveness of tourist-based surveys for estimating population sizes through capture-recapture analyses is shown.