Animal Species Recognition with Deep Convolutional Neural Networks from Ecological Camera Trap Images.

Accurate identification of animal species is necessary to understand biodiversity richness, monitor endangered species, and study the impact of climate change on species distribution within a specific region. Camera traps represent a passive monitoring technique that generates millions of ecological images. The vast numbers of images drive automated ecological analysis as essential, given that manual assessment of large datasets is laborious, time-consuming, and expensive. Deep learning networks have been advanced in the last few years to solve object and species identification tasks in the computer vision domain, providing state-of-the-art results. In our work, we trained and tested machine learning models to classify three animal groups (snakes, lizards, and toads) from camera trap images. We experimented with two pretrained models, VGG16 and ResNet50, and a self-trained convolutional neural network (CNN-1) with varying CNN layers and augmentation parameters. For multiclassification, CNN-1 achieved 72% accuracy, whereas VGG16 reached 87%, and ResNet50 attained 86% accuracy. These results demonstrate that the transfer learning approach outperforms the self-trained model performance. The models showed promising results in identifying species, especially those with challenging body sizes and vegetation.

Biogeographic consequences of shifting climate for the western massasauga (Sistrurus tergeminus).

The western massasauga (Sistrurus tergeminus) is a small pit viper with an extensive geographic range, yet observations of this species are relatively rare. They persist in patchy and isolated populations, threatened by habitat destruction and fragmentation, mortality from vehicle collisions, and deliberate extermination. Changing climates may pose an additional stressor on the survival of isolated populations. Here, we evaluate historic, modern, and future geographic projections of suitable climate for S. tergeminus to outline shifts in their potential geographic distribution and inform current and future management. We used maximum entropy modeling to build multiple models of the potential geographic distribution of S. tergeminus. We evaluated the influence of five key decisions made during the modeling process on the resulting geographic projections of the potential distribution, allowing us to identify areas of model robustness and uncertainty. We evaluated models with the area under the receiver operating curve and true skill statistic. We retained 16 models to project both in the past and future multiple general circulation models. At the last glacial maximum, the potential geographic distribution associated with S. tergeminus occurrences had a stronghold in the southern part of its current range and extended further south into Mexico, but by the mid-Holocene, its modeled potential distribution was similar to its present-day potential distribution. Under future model projections, the potential distribution of S. tergeminus moves north, with the strongest northward trends predicted under a climate scenario increase of 8.5 W/m2. Some southern populations of S. tergeminus have likely already been extirpated and will continue to be threatened by shifting availability of suitable climate, as they are already under threat from desertification of grasslands. Land use and habitat loss at the northern edge of the species range are likely to make it challenging for this species to track suitable climates northward over time.

Phylogeographic structure of the dunes sagebrush lizard, an endemic habitat specialist.

Phylogeographic divergence and population genetic diversity within species reflect the impacts of habitat connectivity, demographics, and landscape level processes in both the recent and distant past. Characterizing patterns of differentiation across the geographic range of a species provides insight on the roles of organismal and environmental traits in evolutionary divergence and future population persistence. This is particularly true of habitat specialists where habitat availability and resource dependence may result in pronounced genetic structure as well as increased population vulnerability. We use DNA sequence data as well as microsatellite genotypes to estimate range-wide phylogeographic divergence, historical population connectivity, and historical demographics in an endemic habitat specialist, the dunes sagebrush lizard (Sceloporus arenicolus). This species is found exclusively in dune blowouts and patches of open sand within the shinnery oak-sand dune ecosystem of southeastern New Mexico and adjacent Texas. We find evidence of phylogeographic structure consistent with breaks and constrictions in suitable habitat at the range-wide scale. In addition, we find support for a dynamic and variable evolutionary history across the range of S. arenicolus. Populations in the Monahans Sandhills have deeply divergent lineages consistent with long-term demographic stability. In contrast, populations in the Mescalero Sands are not highly differentiated, though we do find evidence of demographic expansion in some regions and relative demographic stability in others. Phylogeographic history and population genetic differentiation in this species has been shaped by the configuration of habitat patches within a geologically complex and historically dynamic landscape. Our findings identify regions as genetically distinctive conservation units as well as underscore the genetic and demographic history of different lineages of S. arenicolus.