| Popis: |
Landslides are some of the deadliest and most violent geological events. A lot of research has been done on this topic in order to understand its causes and propose solutions. An essential tool for landslide risk management is landslide susceptibility maps. In this paper, we developed a Convolutional Neural Network (CNN) model capable of producing a susceptibility map using seven explanatory variables: lithology, slope, drainage density, fault density, elevation, roughness, and aspect. A susceptibility index map was generated in the Aknoul Region in the Rif to illustrate the CNN results. We found that areas with very high susceptibility index are affected the most by landslides. |
