Regional assessment of coastal landslide susceptibility in Liguria, Northern Italy, using MaxEnt

Coastal landslides pose significant hazards to populated areas and infrastructure, necessitating accurate assessment and mitigation strategies. In this study, landslide susceptibility maps for rockfalls/topples, rotational/translational slides, complex phenomena and rapid flows were developed in the Liguria region (Italy) from the coast to 2 km inland using the inventory of Italian landslides and the maximum entropy model that allows to develop, in a limited computational time, studies at regional scale. Sixteen environmental variabilities derived from the digital elevation model, geological map, CORINE land cover and topographic map of the region were used in the models. Only the variables found to be most significant for each model were used for each landslide type. The landslide occurrences were divided randomly into training (80%) and test set (20%). The accuracy of the models was evaluated by the receiver operating characteristic curves and the area under the curve. The rockfall/topple model and the rapid flow model showed high accuracy although this latter model was only evaluated on the training data due to an insufficient number of landslides for a split into test and training datasets. The rotational/translational slides model and the complex landslides model also performed well. We found that variables contributing most significantly to the models are the slope, lithology, land cover, distance from the shoreline and elevation. Susceptibility maps were created for each type of landslide and combined into a final map providing a comprehensive overview of the landslide hazard at the regional level.