Search

Simple Summary: The disappearance of many reptiles and amphibian species is directly and indirectly connected with habitat modification, introducing invasive species, disease, pollution, and climate change. Monitoring endangered species is essential for conservation action to mitigate the predominant threats to endangered species. According to wildlife researchers, visual information provides definitive evidence of an animal's distribution patterns and activity within an environmental context. At the Department of Biology and The Ingram School of Engineering at Texas State University and Texas A&M University, we collaborated on a camera trap project to monitor species from images in Texas, USA. We developed a framework to analyze the acquired images using artificial intelligence-driven technology and computer vision methods. The project aims to classify three broad groups of herpetofaunal species (i.e., toads/frogs, lizards, and snakes) from camera trap images with deep learning architectures. The experiment includes balancing the imbalanced dataset, investigating several image preprocessing techniques, and augmentation procedures. The classification results present tremendous prospects for automated species identification from challenging biological image data. The research outcome is essential to the academic community and wildlife researchers for conservation and monitoring purpose. 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. [ABSTRACT FROM AUTHOR]

The conservation of rarely encountered species is notoriously difficult mainly because of the lack of information about their natural history. This is definitely the case for the spot-tailed earless lizards (Holbrookia lacerata and H. subcaudalis). Sparse distributional records and infrequent observations at known sites were used as evidence to petition these species for protection under the Endangered Species Act. For this study, we did surveys in historic and new areas to determine the current distribution of both species. We also radio-tracked individuals from two populations to estimate movement potential and home range sizes, as well as understand habitat use. Distribution surveys indicate that H. lacerata has undergone range contraction (39%); however, H. subcaudalis was historically found in 21 counties but we only observed them in five. We found home ranges to be relatively large compared to similarly sized insectivores and at least four times larger than the similar H. maculata. Both species are inhabitants of historic grasslands, but within this habitat type they used sites that were more open compared to what was available, including areas such as row-crop agriculture and frequently mowed fields. Frequent habitat disturbance seems to be important for both species. Urbanisation, invasive woody vegetation and invasive grasses are all considered threats that may have already caused declines to both species. [ABSTRACT FROM AUTHOR]

Information on gopherus polyphemus from Florida including information related to topics like canis latrans, and predation by canis latrans on gopherus polyphemus is presented.

The article focuses on the first recorded instance of Holbrookia lacerata (Spot-tailed Earless Lizard) being preyed upon by Hypsiglena jani (a nocturnal snake), detailing the lizard's measurements before and after regurgitation and the impact of the attached radio transmitter on the predation event.

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., Competing Interests: The authors declare no conflict of interest.