Biology subjects

Rast, W.

Publications and source records attributed to Rast, W..

2 recordsLinked to original sources

bioRxiv2024

Using animal tracking for early detection of mass poisoning events

1 Amidst the sixth mass extinction, some groups, such as vultures, the only obligate scavengers among vertebrates, are disappearing at an unprecedented rate. Vulture populations worldwide are largely threatened by poisoning. As many vulture species are social foragers, they can congregate in large numbers to scavenge at a carcass, potentially increasing their exposure to poisoning risk. Current anti-poisoning prevention and mitigation measures are insufficient to tackle this threat. There is an urgent need for new effective strategies to prevent mass vulture mortality. 2 In this study, we used agent-based modeling to: (1) quantify the impact of different foraging strategies on vulture poisoning risk, and (2) evaluate the cost-effectiveness of using vultures as sentinels for poisoning detection. This approach involves GPS tracking of various numbers of vultures and using the data to quickly detect poisoning incidents and decontaminate carcasses. These actions help mitigate further vulture mortality and prevent mass poisoning. 3 Our results indicate that social foraging significantly elevates the risk of vultures being poisoned. Vulture tracking contributes substantially to the early detection of poisoning events, which results in reduced mortality. Poisoning can be mitigated by tracking more vultures and responding faster, with an optimal cost-effectiveness achieved by tracking 5% of the vulture population (25 individuals in our system) and a budget of 58,728 USD. This approach could potentially prevent 45% of poisoning-related mortalities if interventions occur within 2 hours. 4 Synthesis and applications: Our results suggest that, in order to reduce mortality incidences from poisoning, it is sufficient to track a small proportion of the vulture population, which would act as sentinels for the rest. By evaluating the costs and ecological benefits of these mitigation strategies, we provide evidence-based solutions that practitioners can use to design conservation plans. These findings are therefore instrumental in supporting vulture and scavenger conservation policy and practice.

ecology↗

bioRxiv2019

Machine learning goes wild: Using data from captive individuals to infer wildlife behaviour

O_LIRemotely tracking distinct behaviours of animals using acceleration data and machine learning has been carried out successfully in several species in captive settings. In order to study the ecology of animals in natural habitats, such behaviour classification models need to be transferred to wild individuals. However, at present the development of those models usually requires direct observation of the target animals. C_LIO_LIThe goal of this study was to infer behaviour of wild, free roaming animals from acceleration data by training behaviour classification models on captive individuals, without the necessity to observe their wild conspecifics. We further sought to develop methods to validate the credibility of the resulting behaviour extrapolations. C_LIO_LIWe trained two machine learning algorithms proposed by the literature, Random Forest (RF) and Support Vector Machine (SVM), on data from captive red foxes (Vulpes vulpes) and later applied them to data from wild foxes. We also tested a new advance for behaviour classification, by applying a moving window to an Artificial Neural Network (ANN). Finally, we investigated four strategies to validate our classification output. C_LIO_LIWhile all three machine learning algorithms performed well under training conditions, the established methods, RF and SVM, failed in classifying distinct behaviours when transferred from captive to wild foxes. Behaviour classification with the ANN and a moving window, in contrast, inferred distinct behaviours and showed consistent results for most individuals. C_LIO_LIOur approach is a substantial improvement over the methods previously proposed in the literature as it generated plausible results for wild fox behaviour. We were able to infer the behaviour of wild animals that have never been observed in the wild and to further illustrate the outputs credibility. This framework is not restricted to foxes but can be applied to infer the behaviour of many other species and thus empowers new advances in behavioural ecology. C_LI

animal behavior and cognition↗