Search

Motion-activated cameras (camera traps) are increasingly used in ecological and management studies for remotely observing wildlife and have been regarded as among the most powerful tools for wildlife research. However, studies involving camera traps result in millions of images that need to be analyzed, typically by visually observing each image, in order to extract data that can be used in ecological analyses. We trained machine learning models using convolutional neural networks with the ResNet-18 architecture and 3,367,383 images to automatically classify wildlife species from camera trap images obtained from five states across the United States. We tested our model on an independent subset of images not seen during training from the United States and on an out-of-sample (or out-of-distribution in the machine learning literature) dataset of ungulate images from Canada. We also tested the ability of our model to distinguish empty images from those with animals in another out-of-sample dataset from Tanzania, containing a faunal community that was novel to the model. The trained model classified approximately 2,000 images per minute on a laptop computer with 16 gigabytes of RAM. The trained model achieved 98% accuracy at identifying species in the United States, the highest accuracy of such a model to date. Out-of-sample validation from Canada achieved 82% accuracy, and correctly identified 94% of images containing an animal in the dataset from Tanzania. We provide an R package (Machine Learning for Wildlife Image Classification; MLWIC) that allows the users to A) implement the trained model presented here and B) train their own model using classified images of wildlife from their studies. The use of machine learning to rapidly and accurately classify wildlife in camera trap images can facilitate non-invasive sampling designs in ecological studies by reducing the burden of manually analyzing images. We present an R package making these methods accessible to ecologists. We discuss the implications of this technology for ecology and considerations that should be addressed in future implementations of these methods.

An individual’s spatial behavior is shaped by social and environmental factors and provides critical information about population processes to inform conservation and management actions. Heterogeneity in spatial overlap among conspecifics can be evaluated using estimates of home ranges and core areas and used to understand factors influencing space use and territoriality. To understand and test predictions about spatial behavior in an invasive large mammal, the wild pig (Sus scrofa), we examined variation in space use between sexes and seasons. We predicted that if animals were territorial that there would be a reduction in space-use overlap when comparing overlap of home ranges (HR-HR), to home ranges and core areas (HR-CA), and in-turn to core areas (CA-CA). Home ranges and core areas were estimated for 54 wild pigs at Buck Island Ranch, FL from GPS telemetry data. Overlap indices were calculated to estimate the strength (space-use overlap) and number of potential interactions within three wet seasons (June-October) and two dry seasons (December-April). Across all seasons, males exhibited larger home ranges compared to females (M = 10.36±0.79 km² (±SE), F = 3.21±0.16 km²) and interacted with a greater number of individuals than females. Home range size and strength of interactions did not vary between wet and dry seasons. Consistent with our predictions, wild pigs appeared to exhibit territorial behavior, where strength of overlap decreased when comparing HR-HR to HR-CA and HR-CA to CA-CA. Strength of overlap varied by sex, which was lowest between females, intermediate between females and males, and greatest between males. Our framework can be used to understand patterns of space use and territoriality in populations, which has important implications in understanding population processes and how pathogens and parasites might spread within and among populations.

Contact heterogeneity among hosts determines invasion and spreading dynamics of infectious disease, thus its characterization is essential for identifying effective disease control strategies. Yet, little is known about the factors shaping contact networks in many wildlife species and how wildlife management actions might affect contact networks. Wild pigs in North America are an invasive, socially structured species that pose a health concern for domestic swine given their ability to transmit numerous devastating diseases such as African swine fever (ASF). Using proximity loggers and GPS data from 48 wild pigs in Florida and South Carolina, USA, we employed a probabilistic framework to estimate weighted contact networks. We determined the effects of sex, social group and spatial distribution (monthly home-range overlap and distance) on wild pig contact. We also estimated the impacts of management-induced perturbations on contact and inferred their effects on ASF establishment in wild pigs with simulation. Social group membership was the primary factor influencing contacts. Between-group contacts depended primarily on space use characteristics, with fewer contacts among groups separated by >2 km and no contacts among groups >4 km apart within a month. Modelling ASF dynamics on the contact network demonstrated that indirect contacts resulting from baiting (a typical method of attracting wild pigs or game species to a site to enhance recreational hunting) increased the risk of disease establishment by ~33% relative to direct contact. Low-intensity population reduction (

Wildlife of Florida Factsheet: Virginia Opossum Learn more about the Florida Opossum! The Wildlife of Florida Factsheet series was created to provide the public with a quick accurate introduction to Florida’s wildlife, including both native and invasive. We hope these factsheets inspire people to investigate wildlife in their own backyard and communities and understand the amazing biodiversity of wildlife in the state of Florida.

As a result of shifts in the habitable range of ticks due to climate change and the ongoing threat of exotic tick species introductions, efficient surveillance tools for these pests and disease vectors are needed. Wild pigs are habitat generalists, distributed throughout most of the United States, and often hunted recreationally or removed as part of management programs, making them potentially useful sentinel hosts for ticks. We compared ticks collected from captured wild pigs and standard tick dragging methods on a south-central Florida cattle ranch from May 2015–August 2017. Three hundred and sixteen wild pigs were surveyed, and 84 km spanning three habitat types (seminative pasture, improved pasture, and hammock) were dragged. In total, 1023 adults of four species (Amblyomma auricularium, Amblyomma maculatum, Dermacentor variabilis, and Ixodes scapularis) were collected from wild pigs, while 39 adults of three species (A. auricularium, A. maculatum, and I. scapularis) were collected from drags. Only one immature specimen, a nymph, was collected from a pig, while dragging collected 2808 larvae and 150 nymphs. Amblyomma maculatum comprised 96% of adults collected from pigs, while A. maculatum, I. scapularis, and A. auricularium comprised 38%, 33%, and 28% of adults collected from drags, respectively. Adults of all tick species found on drags were found on pigs, and wild pig surveillance detected adults of an additional species not found on drags. Dragging was far superior for collection of immatures but not for adults of most species found in this study. These findings suggest wild pigs could be used as a sentinel for the detection of tick species. When combined with ongoing wild pig research, hunting, or management, wild pig surveillance can provide an effective method to survey for adult tick presence of some species of interest and may assist in tracking the range expansion of some tick species., Graphical abstract Image 1, Highlights • Surveillance for ticks, and potential disease risk in an area, is needed. • Wild pigs are found throughout the US and may be useful sentinel hosts for ticks. • We compared two methods for tick detection in south-central FL. • Sampling from wild pigs detected adults of more tick species than dragging. • Dragging was more successful than wild pig sampling at detecting immature ticks.

Little is known about disease transmission relevant contact rates at the wildlife-livestock interface and the factors shaping them. Indirect contact via shared resources is thought to be important but remains unquantified in most systems, making it challenging to evaluate the impact of livestock management practices on contact networks. Free-ranging wild pigs (Sus scrofa) in North America are an invasive, socially-structured species with an expanding distribution that pose a threat to livestock health given their potential to transmit numerous livestock diseases, such as pseudorabies , brucellosis , trichinellosis, and echinococcosis , among many others. Our objective in this study was to quantify the spatial variations in direct and indirect contact rates among wild pigs and cattle on a commercial cow-calf operation in Florida, USA. Using GPS data from 20 wild pigs and 11 cattle and a continuous-time movement model, we extracted three types of spatial contacts between wild pigs and cattle, including direct contact, indirect contact in the pastoral environment (unknown naturally occurring resources), and indirect contact via anthropogenic cattle resources (feed supplements and water supply troughs). We examined the effects of sex, spatial proximity, and cattle supplement availability on contact rates at the species level and characterized wild pig usage of cattle supplements. Our results suggested daily pig-cattle direct contacts occurred only occasionally, while a significant number of pig-cattle indirect contacts occurred via natural resources distributed heterogeneously across the landscape. At cattle supplements, more indirect contacts occurred at liquid molasses than water troughs or molasses-mineral block tubs due to higher visitation rates by wild pigs. Our results can be directly used for parameterizing epidemiological models to inform risk assessment and optimal control strategies for controlling transmission of shared diseases.

Florida is home to several species of animals in Order Carnivora, a group of mammals with teeth adapted to allow them to eat meat. Many of them, like panthers, you probably know about, and some, like raccoons, you may see regularly. But did you know Florida hosts two separate species of foxes? Two different skunks? Weasels? This 20-page fact sheet written by Raoul Boughton, Bethany Wight, Elizabeth Pienaar, and Martin B. Main and published by the UF/IFAS Department of Wildlife Ecology and Conservation provides an overview of the mammalian carnivores of Florida from panthers to mink.https://edis.ifas.ufl.edu/uw464

Learn more about White-tailed Deer in Florida! The Wildlife of Florida Factsheet series was created to provide the public with a quick accurate introduction to Florida’s wildlife, including both native and invasive species. We hope these factsheets inspire people to investigate wildlife in their own backyard and communities and understand the amazing biodiversity of wildlife in the state of Florida.

Learn more about coyotes in Florida! The Wildlife of Florida Factsheet series was created to provide the public with a quick accurate introduction to Florida’s wildlife, including both native and invasive. We hope these factsheets inspire people to investigate wildlife in their own backyard and communities and understand the amazing biodiversity of wildlife in the state of Florida.

Learn more about Florida Gopher Tortoises! The Wildlife of Florida Factsheet series was created to provide the public with a quick accurate introduction to Florida’s wildlife, including both native and invasive. We hope these factsheets inspire people to investigate wildlife in their own backyard and communities and understand the amazing biodiversity of wildlife in the state of Florida.

Feral swine are an invasive or nuisance species in Florida and most other states because their incessant rooting is ruinous to natural and agricultural habitat. They loosen the soil, destroy native vegetation, and modify the natural chemistry and nutrients of the soil, causing widespread destruction in natural ecosystems, agricultural areas, livestock pastures, and residential areas. They also carry numerous diseases, some of which are transmittable to wild and domestic animals and humans. Trapping and removing swine from your property is an effective way to reduce or control feral swine populations. This 9-page fact sheet written by Bethany Wight and Raoul K. Boughton and published by the UF/IFAS Wildlife Ecology and Conservation Department describes the most commonly used trapping techniques and illustrates several trap and gate designs.https://edis.ifas.ufl.edu/uw440

1. Motion-activated cameras (“camera traps”) are increasingly used in ecological and management studies for remotely observing wildlife and have been regarded as among the most powerful tools for wildlife research. However, studies involving camera traps result in millions of images that need to be analyzed, typically by visually observing each image, in order to extract data that can be used in ecological analyses.2. We trained machine learning models using convolutional neural networks with the ResNet-18 architecture and 3,367,383 images to automatically classify wildlife species from camera trap images obtained from five states across the United States. We tested our model on an independent subset of images not seen during training from the United States and on an out-of-sample (or “out-of-distribution” in the machine learning literature) dataset of ungulate images from Canada. We also tested the ability of our model to distinguish empty images from those with animals in another out-of-sample dataset from Tanzania, containing a faunal community that was novel to the model.3. The trained model classified approximately 2,000 images per minute on a laptop computer with 16 gigabytes of RAM. The trained model achieved 98% accuracy at identifying species in the United States, the highest accuracy of such a model to date. Out-of-sample validation from Canada achieved 82% accuracy, and correctly identified 94% of images containing an animal in the dataset from Tanzania. We provide an R package (Machine Learning for Wildlife Image Classification; MLWIC) that allows the users to A) implement the trained model presented here and B) train their own model using classified images of wildlife from their studies.4. The use of machine learning to rapidly and accurately classify wildlife in camera trap images can facilitate non-invasive sampling designs in ecological studies by reducing the burden of manually analyzing images. We present an R package making these methods accessible to ecologists. We discuss the implications of this technology for ecology and considerations that should be addressed in future implementations of these methods.