Analysing and predicting wildlife–vehicle collision hotspots for the Swiss road network

Laube, Patrick; Ratnaweera, Nils; Wróbel, Anna; Kaelin, Ivo; Stephani, Annette; Reifler-Baechtiger, Martina; Graf, Roland F.; Suter, Stefan

doi:10.1007/s10980-023-01655-5

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-28254

Publication type:	Article in scientific journal
Type of review:	Peer review (publication)
Title:	Analysing and predicting wildlife–vehicle collision hotspots for the Swiss road network
Authors:	Laube, Patrick Ratnaweera, Nils Wróbel, Anna Kaelin, Ivo Stephani, Annette Reifler-Baechtiger, Martina Graf, Roland F. Suter, Stefan
et. al:	No
DOI:	10.1007/s10980-023-01655-5 10.21256/zhaw-28254
Published in:	Landscape Ecology
Volume(Issue):	38
Issue:	7
Page(s):	1765
Pages to:	1783
Issue Date:	2023
Publisher / Ed. Institution:	Springer
ISSN:	0921-2973 1572-9761
Language:	English
Subjects:	Wildlife–vehicle collision; Kernel Density Estimation; Neighbourhood function; Spatial data science; Random forest
Subject (DDC):	333: Economics of land and resources 380: Transportation
Abstract:	Context: Wildlife–vehicle collisions (WVCs) are a significant threat for many species, cause financial loss and pose a serious risk to motorist safety. Objectives: We used spatial data science on regional collision data from Switzerland with the objectives of identifying the key environmental collision risk factors and modelling WVC risk on a nationwide scale. Methods: We used 43,000 collision records with roe deer, red deer, wild boar, and chamois from 2010 to 2015 for both midlands and mountainous landscape types. We compared a fixed-length road segmentation approach with segments based on Kernel Density Estimation, a data-driven segmentation method. The segments’ environmental properties were derived from land-cover geodata using novel neighbourhood operations. Multivariate logistic regression and random forest classifiers were used to identify and rank the relevant environmental factors and to predict collision risk in areas without collision data. Results: The key factors for WVC hotspots are road sinuosity, and two composite factors for browsing/forage availability and traffic noise—a proxy for traffic flow. Our best models achieved sensitivities of 82.5% to 88.6%, with misclassifications of 20.14% and 27.03%, respectively. Our predictions were better in forested areas and revealed limitations in open landscape due to lack of up-to-date data on annual crop changes. Conclusions: We illustrate the added value of using fine-grained land-cover data for WVC modelling, and show how such detailed information can be annotated to road segments using spatial neighbourhood functions. Finally, we recommend the inclusion of annual crop data for improving WVC modelling.
Further description:	Erworben im Rahmen der Schweizer Nationallizenzen (http://www.nationallizenzen.ch)
URI:	https://digitalcollection.zhaw.ch/handle/11475/28254
Fulltext version:	Published version
License (according to publishing contract):	CC BY 4.0: Attribution 4.0 International
Departement:	Life Sciences and Facility Management
Organisational Unit:	Institute of Computational Life Sciences (ICLS) Institute of Natural Resource Sciences (IUNR)
Published as part of the ZHAW project:	Prävention von Wildtierunfällen auf Verkehrsinfrastrukturen
Appears in collections:	Publikationen Life Sciences und Facility Management

Files in This Item:

File	Description	Size	Format
2023_Laube-etal_Analysing-and-predicting-wildlife-vehicle-collision-hotspots.pdf		1.37 MB	Adobe PDF	View/Open

Show full item record

Laube, P., Ratnaweera, N., Wróbel, A., Kaelin, I., Stephani, A., Reifler-Baechtiger, M., Graf, R. F., & Suter, S. (2023). Analysing and predicting wildlife–vehicle collision hotspots for the Swiss road network. Landscape Ecology, 38(7), 1765–1783. https://doi.org/10.1007/s10980-023-01655-5

Laube, P. et al. (2023) ‘Analysing and predicting wildlife–vehicle collision hotspots for the Swiss road network’, Landscape Ecology, 38(7), pp. 1765–1783. Available at: https://doi.org/10.1007/s10980-023-01655-5.

P. Laube et al., “Analysing and predicting wildlife–vehicle collision hotspots for the Swiss road network,” Landscape Ecology, vol. 38, no. 7, pp. 1765–1783, 2023, doi: 10.1007/s10980-023-01655-5.

LAUBE, Patrick, Nils RATNAWEERA, Anna WRÓBEL, Ivo KAELIN, Annette STEPHANI, Martina REIFLER-BAECHTIGER, Roland F. GRAF und Stefan SUTER, 2023. Analysing and predicting wildlife–vehicle collision hotspots for the Swiss road network. Landscape Ecology. 2023. Bd. 38, Nr. 7, S. 1765–1783. DOI 10.1007/s10980-023-01655-5

Laube, Patrick, Nils Ratnaweera, Anna Wróbel, Ivo Kaelin, Annette Stephani, Martina Reifler-Baechtiger, Roland F. Graf, and Stefan Suter. 2023. “Analysing and Predicting Wildlife–Vehicle Collision Hotspots for the Swiss Road Network.” Landscape Ecology 38 (7): 1765–83. https://doi.org/10.1007/s10980-023-01655-5.

Laube, Patrick, et al. “Analysing and Predicting Wildlife–Vehicle Collision Hotspots for the Swiss Road Network.” Landscape Ecology, vol. 38, no. 7, 2023, pp. 1765–83, https://doi.org/10.1007/s10980-023-01655-5.