An interpretable and transferable model for shallow landslides detachment combining spatial Poisson point processes and generalized additive models

Shallow landslides are rapidly moving and strongly dangerous slides. In the present work, the probabilistic distribution of the landslide detachment points within a valley is modelled as a spatial Poisson point process, whose intensity depends on geophysical covariates according to a generalized additive model. This jointly allows to obtain good predictive performance and to preserve the interpretability of the effects of the geophysical predictors on the intensity of the process. We propose a novel workflow, based on Random Forests, to select the geophysical predictors entering the model for the intensity. The statistically significant effects are interpreted as activating or stabilizing factors for landslide detachment. The transferability of the resulting model is guaranteed by training, validating and testing the algorithms on mutually disjoint valleys in the Alps of Lombardy (Italy). Finally, the uncertainty around the estimated intensity of the process is quantified via semiparametric bootstrap.