Predicting spatial and seasonal patterns of wildlife-vehicle collisions in high-risk areas

Abstract

ContextVehicle collisions with wildlife can injure or kill animals, threaten human safety, and threaten the viability of rare species. This has led to a focus in road-ecology research on identifying the key predictors of road-kill risk, with the goal of guiding management to mitigate its impact. However, because of the complex and context-dependent nature of the causes of risk exposure, modelling road-kill data in ways that yield consistent recommendations has proven challenging. AimHere we used a novel multi-model machine-learning approach to identify the spatio-temporal predictors, such as traffic volume, road shape, surrounding vegetation and distance to human settlements, associated with road-kill risk. MethodsWe collected data on the location, identity and size of each road mortality across four seasons along eight roads in southern Tasmania - a road-kill hotspot of management concern. We focused on three large-bodied and frequently impacted crepuscular Australian marsupial herbivore species, the rufous-bellied pademelon (Thylogale billardierii), Bennetts wallaby (Macropus rufogriseus) and the bare-nosed wombat (Vombatus ursinus). We fit the point-location data using lasso-regularization of a logistic generalized linear model (LL-GLM) and out-of-bag optimization of a decision-tree-based random forests (RF) algorithm. ResultsThe RF model, with high-level feature interactions, yielded superior results to the linear additive model, with a RF classification accuracy of 84.8% for the 871 road-kill observations and a true skill statistic of 0.708, compared to 61.2% and 0.205 for the LL-GLM. ConclusionsForested areas with no roadside barrier fence along curved sections of road posed the highest risk to animals. Seasonally, the frequency of wildlife-vehicle collisions increased notably for females during oestrus, when they were more dispersive and so had a higher encounter rate with roads. ImplicationsThese findings illustrate the value of using data-driven approaches to predictive modelling, as well as offering a guide to practical management interventions that can mitigate road-related hazards.