Rockfall susceptibility and network-ranked susceptibility along the Italian railway

TL;DR

This study models rockfall susceptibility along the Italian railway network using a physically based trajectory model and a data-driven source location method, producing detailed susceptibility and network-ranked hazard maps for safety prioritization.

Contribution

It introduces a large-scale, physically based rockfall trajectory modeling approach combined with a probabilistic source location method for the entire Italian railway network.

Findings

Generated the largest homogeneous rockfall trajectory map to date covering 24,500 km².

Produced detailed segment-wise susceptibility maps for the entire railway network.

Developed a network-ranked susceptibility classification for hazard prioritization.

Abstract

Rockfalls pose a substantial threat to ground transportation, due to their rapidity, destructive potential and high probability of occurrence on steep topographies, found along roads and railways. Approaches for assessment of rockfall susceptibility range from purely phenomenological methods and statistical methods, suitable for modeling large areas, to purely deterministic ones, usually easier to use in local analyses. A common requirement is the need to locate potential detachment points, often found uphill on cliffs, and the subsequent assessment of the runout areas of rockfalls stemming from such points. Here, we apply a physically based model to calculate rockfall trajectories along the whole Italian railway network, within a corridor of total length of about 17,000 km and varying width. We propose a data-driven method for the location of rockfall source points based on expert mapping of potential source areas on sample representative locations. Using empirical distributions of gridded slope values in source areas mapped by experts, we derived probabilistic maps of rockfall sources in the proximity of the railway network, regardless of a particular trigger. Source areas act as starting points of simulated trajectories in the three-dimensional model STONE. The program provides a pixel-by-pixel trajectory count, covering 24,500 km2, the largest homogeneous application of the model to date. We classified the map into a vector susceptibility map of the segments of the railway, for which we provide segment-wise rockfall susceptibility. Eventually, we considered a graph representation of the network to classify the segments both on the basis of rockfall susceptibility and the role of each segment in the network, resulting in a network-ranked susceptibility. Both maps are useful for subsequent hazard assessment, and to prioritize safety improvements along the railway, at national scale.