Articles | Volume 26, issue 10
https://doi.org/10.5194/nhess-26-4675-2026
https://doi.org/10.5194/nhess-26-4675-2026
Research article
 | 
01 Oct 2026
Research article |  | 01 Oct 2026

Spatial machine learning modelling reveals that soil indicators and tree type best explain shallow landslide release

Denise Christina Rüther, Kristine Flacké Haualand, Iris Louisa Johanna Peeters, and Mark Andrew Kusk Gillespie

Model code and software

Code repository ``Attributes to landslide and control points during storm Hans'' K. F. Haualand https://github.com/krifla/hans_landslide

Code repository ``Landslide analysis'' M. S. K. Gillespie https://github.com/makgillespie/Landslide-analysis

Download
Short summary
We use several machine learning models to explore which factors best explain landslide release during an extreme rainfall event in eastern Norway. As landslides often occur in clusters, methods must be chosen carefully to account for any spatial effects. When considering this, we find that south-facing slopes, thicker soils and more water made landslides most likely. On forested slopes, landslides are most likely in deciduous rather than spruce or pine stands.
Share
Altmetrics
Final-revised paper
Preprint