Preprint
About this contribution
This preprint addresses the spatial and seasonal prioritisation of wild-boar train collisions across the French railway network. Its prediction framework combines recorded collisions with satellite observations, landscape properties, habitat suitability and other geospatial predictors. The target is risk on railway sections through time, not simply a map of where wild boar might be present.
The methodological emphasis is on integrating heterogeneous evidence, choosing appropriate spatial scales and evaluating how predictions generalise across locations and years. The resulting ranking can inform where practitioners examine preventive measures first, but it does not replace local assessments of infrastructure, train operations and wildlife crossings. The work is a preprint rather than a final peer-reviewed journal publication.
Preprint, e209840, 32 pages.
Citation
Meyer, A. F.; Pretali, S.; Reibel, T.; Bhardwaj, M.; Kneubühler, M.; Jordan, D. (2026). Multimodal Machine Learning to Predict Wild Boar Collision Risk on the French Railway Network ARPHA Preprints https://doi.org/10.3897/arphapreprints.e209840



