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

Abstract

Context Vehicle 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. Aim Here we used a 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. Methods We collected data on the location, identity and wildlife body 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 affected crepuscular Australian marsupial herbivore species, the rufous-bellied pademelon (Thylogale billardierii), Bennett’s wallaby (Macropus rufogriseus) and the bare-nosed wombat (Vombatus ursinus). We fit the point-location data using ‘lasso-regularisation’ of a logistic generalised linear model (LL-GLM) and out-of-bag optimisation of a decision-tree-based ‘random forests’ (RF) algorithm for optimised predictions. Results The RF model, with high-level feature interactions, yielded superior out-of-sample prediction 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 with 61.2% and 0.205 for the LL-GLM. The lasso rejected road visibility and human density, ranking roadside vegetation type and presence of barrier fencing as the most influential predictors of road-kill locality. Conclusions Forested 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. Implications These findings illustrate the value of using a combination of attributive and predictive modelling using machine learning to rank and interpret a complexity of possible predictors of road-kill risk, as well as offering a guide to practical management interventions that can mitigate road-related hazards.

Spatiotemporal Patterns of Reptile and Amphibian Road Fatalities in a Natura 2000 Area: A 12-Year Monitoring of the Lake Karla Mediterranean Wetland

“…This underestimation can be ascribed to various factors such as scavenger activity [ 82 , 83 , 84 ], post-accident mortality of injured individuals [ 68 ], the influence of weather conditions [ 85 ], road type [ 86 ], and detectability, which can be influenced by carcass size [ 87 ], the amount of roadside vegetation [ 88 ], displacement by traffic [ 89 ], and survey method [ 88 ]. Regarding survey methodology, our decision to employ a vehicle and adopt a cautious, low-speed driving approach to enhance roadkill detection, though a widely acknowledged sampling method for studying road mortality in reptiles, amphibians, and vertebrates in general [ 90 , 91 , 92 ], has been previously highlighted for potential underestimation up to 12–16 times less than the actual recorded roadkill count [ 93 ]. This might explain the reduced efficiency in detecting smaller herpetofauna species in the study area.…”

Anthropogenic, environmental and temporal associations with vertebrate road mortality in a wildland–urban interface of a biodiverse desert ecoregion

“…To understand factors associated with aridland vertebrate roadkill (here, DOR counts per survey) in the wildland–urban interface, we ran generalized additive models (GAMs) with negative binomial distributions in the R package mgcv [ 81 ]. We used GAMs owing to anticipated nonlinear effects of certain covariates on taxa [ 41 , 43 , 82 , 83 ]. Predictors included mean values for environmental recency (i.e.…”

“…Environmental factors, such as climate, development, traffic and luminosity, are associated with road mortality [37][38][39][40][41]. Roadkill rates can also vary temporally by diel and seasonal activity periods [42,43]. Many herpetofauna and small mammals, for example, employ nocturnal activity strategies to evade the heat of the day in desert climates [38,44]; herpetofauna often use roads for thermoregulation after the sun sets [34,35,45].…”