Motion‐activated cameras (“camera traps”) are increasingly used in ecological and management studies for remotely observing wildlife and are amongst the most powerful tools for wildlife research. However, studies involving camera traps result in millions of images that need to be analysed, 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) that allows the users to (a) use 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 analysing images. Our r package makes these methods accessible to ecologists.
All rights reserved. No reuse allowed without permission.(which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. from Canada. We also tested the ability of our model to distinguish empty images from those 56 with animals in another out-of-sample dataset from Tanzania, containing a faunal community 57 that was novel to the model. (which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.The copyright holder for this preprint . http://dx.doi.org/10.1101/346809 doi: bioRxiv preprint first posted online Jun. 13, 2018; 3 4. The use of machine learning to rapidly and accurately classify wildlife in camera trap images 66 can facilitate non-invasive sampling designs in ecological studies by reducing the burden of 67 manually analyzing images. We present an R package making these methods accessible to 68 ecologists. We discuss the implications of this technology for ecology and considerations that 69 should be addressed in future implementations of these methods. 70
Invasive feral swine (Sus scrofa) cause extensive damage to agricultural and wildlife resources throughout the United States. Development of sodium nitrite as a new, orally delivered toxicant is underway to provide an additional tool to curtail growth and expansion of feral swine populations. A micro-encapsulation coating around sodium nitrite is used to minimize detection by feral swine and maximize stability for the reactive molecule. To maximize uptake of this toxicant by feral swine, development a bait matrix is needed to 1) protect the micro-encapsulation coating so that sodium nitrite remains undetectable to feral swine, 2) achieve a high degree of acceptance by feral swine, and 3) be minimally appealing to non-target species. With these purposes, a field evaluation at 88 sites in south-central Texas was conducted using remote cameras to evaluate preferences by feral swine for several oil-based bait matrices including uncolored peanut paste, black-colored peanut paste, and peanut-based slurry mixed onto whole-kernel corn. These placebo baits were compared to a reference food, whole-kernel corn, known to be readily taken by feral swine (i.e., control). The amount of bait consumed by feral swine was also estimated using remote cameras and grid boards at 5 additional sites. On initial exposure, feral swine showed reduced visitations to the uncolored peanut paste and peanut slurry treatments. This reduced visitation subsided by the end of the treatment period, suggesting that feral swine needed time to accept these bait types. The black-colored peanut paste was visited equally to the control throughout the study, and enough of this matrix was consumed to deliver lethal doses of micro-encapsulated sodium nitrite to most feral swine during 1–2 feeding events. None of the treatment matrices reduced visitations by nontarget species, but feral swine dominated visitations for all matrices. It was concluded that black-colored peanut paste achieved satisfactory preference and consumption by feral swine, and no discernable preference by non-target species, compared to the other treatments.
These results demonstrate the potential for toxic bait to be an effective tool for reducing populations of wild pigs with minimal risks to non-target species, if optimized delivery procedures are followed. © 2018 Society of Chemical Industry.
With the development of a toxic bait (HOGGONE®) for the control of invasive wild pig (IWP; Sus scrofa) populations in the United States, there is a need to develop a bait station to mitigate potential effects on nontarget species. Our objective was to identify characteristics of a bait station that can successfully exclude raccoons (Procyon lotor)—a ubiquitous and dexterous nontarget species—while facilitating bait consumption by IWPs that exhibit group‐feeding behaviors. We evaluated abilities of captive raccoons (n = 19) and IWPs (n = 41) to open the lids of prototype resistance assessment bait stations (RABS) under various levels of resistance (range = 1.1–18.1 kg) at research facilities in Colorado and Texas, USA, during July–August 2014. We found that similar proportions (0.65) of individual raccoons and IWPs in our tests opened lids with 0–1.4 kg resistance, which decreased as resistance increased. No raccoons opened lids with ≥13.6 kg of resistance. However, equal proportions (0.45) of IWPs opened lids with 13.6 kg and 18.1 kg, and a greater proportion (0.73) secondarily accessed RABS after other IWPs opened them. Scrounging behaviors of IWPs (i.e., aggressively taking access to food from less dominate IWPs) increased as the levels of resistance increased, but similar proportions of animals gained access. These results suggest that a threshold‐weight‐of‐resistance of 13.6–18.1 kg on hinged lids excludes raccoons and allows access by IWPs. Furthermore, bait stations designed to allow multiple IWPs to feed simultaneously may be preferred because of group feeding behaviors. Field evaluations are required to evaluate the exclusion of other nontarget species (e.g., white‐tailed deer [Odocoileus virginianus], black bears [Ursus americanus], and coyotes [Canis latrans]), potential scrounging behaviors by nontargets, and bait consumption by IWPs. Published 2017. This article is a U.S. Government work and is in the public domain in the USA.
BACKGROUND An international effort to develop an acute and humane toxic bait for invasive wild pigs (Sus scrofa) is underway to curtail their expansion. We evaluated the ability to expose a population of wild pigs to a simulated toxic bait (i.e., placebo bait containing a biomarker, rhodamine B, in lieu of the toxic ingredient) to gain insight on potential population reduction. We used 28 GPS‐collars and sampled 428 wild pigs to examine their vibrissae for evidence of consuming the bait. RESULTS We estimated that 91% of wild pigs within 0.75 km of bait sites (total area = 16.8 km2) consumed the simulated toxic bait, exposing them to possible lethal effects. Bait sites spaced 0.75–1.5 km apart achieved optimal delivery of the bait, but wild pigs ranging ≥ 3 km away were susceptible. Use of wild pig‐specific bait stations resulted in no non‐target species directly accessing the bait. CONCLUSION Results demonstrate the potential for exposing a large proportion of wild pigs to a toxic bait in similar ecosystems. Toxic baits may be an effective tool for reducing wild pig populations especially if used as part of an integrated pest management strategy. Investigation of risks associated with a field‐deployment of the toxic bait is needed. © 2018 Society of Chemical Industry
Toxic baiting of wild pigs (Sus scrofa) is a potential new tool for population control and damage reduction in the US. Field trials testing a prototype toxic bait (HOGGONE 2 containing 5% sodium nitrite [SN]), though, revealed that wild pigs spilled small particles of toxic bait outside of bait stations which subsequently created hazards for non-target species that consumed those particles, primarily passerine birds. To deter non-target birds from consuming particles of spilled bait, we tested four deterrents at mock bait sites (i.e., baited with bird seed) in north-central Colorado, USA during April–May 2020. We found a programable, inflatable deterrent device (scare dancer) reduced bird visitation by an average of 96%. Then, we evaluated the deterrent devices at SN-toxic bait sites in north-central Texas, USA during July 2020, where the devices were activated the morning following deployment of SN-toxic bait. Overall, we found 139 dead wild pigs at 10 bait sites following one night of toxic baiting, which represented an average of 91% reduction in wild pigs visiting bait sites. We found that deterrent devices were 100% effective at deterring birds from toxic bait sites. We found two dead non-target mice at bait sites without deterrent devices. We noted that deploying toxic bait in mid-summer rather than late-winter/early-spring reduced hazards to migrating birds because they were not present in our study area during July. We recommend using deterrent devices (i.e., novel, programmable, battery operated, continuous and erratic movement, and snapping sounds) to reduce hazards to non-target birds at SN-toxic bait sites. We further recommend deploying SN-toxic bait during seasons when migrating birds are not as abundant until further research demonstrates minimal risks to migrating birds.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.