Landslide susceptibility mapping with r.landslide: A free open-source GIS-integrated tool based on Artificial Neural Networks

This study presents r.landslide, a free and open source add-on to the open source Geographic Information System (GIS) GRASS software for landslide susceptibility mapping. The tool was written in Python language and works on the top of an Artificial Neural Network (ANN) fed with environmental parameters and landslide databases. In order to illustrate the application and effectiveness of the developed tool, a case study is presented for the municipality of Porto Alegre, Brazil. The resulting landslide susceptibility maps are compared with the map published by the Brazilian Geological Survey (CPRM) and a direct comparison using unseen (new) landslide records indicate that the r.landslide can identify and pinpoint susceptible areas with better accuracy. The module can be used by natural disaster management bodies and land use planning organs as a support tool for the elaboration of landslide susceptibility maps in an agile and efficient manner. •Landslide susceptibility maps are generated on the basis of a data-driven approach.•The module has a user-friendly interface and is fully integrated with GRASS GIS.•The module can be used as a support tool for landslide susceptibility assessment.