Assessment of earthquake- triggered landslides in El Salvador based on an Artificial Neural Networks (ANN) model

Abstract

Landslide hazard studies are appropriate for evaluation and mitigation plan development in potential areas for the occurrence of landslides. There are several techniques available for landslide hazard research, however statistical approaches provide rigorous analysis to assess landslide hazard over large regions. This study is an approach for assessing earthquake-triggered landslides hazard using artificial neural networks (ANN). The computational method for the training process is a back-propagation learning algorithm. It is applied to El Salvador, one of the most seismically active regions in Central America, where the last severe destructive earthquakes occurred in January 13th (Mw 7.7) and February 13th, 2001, (Mw 6.6). The first of these earthquakes triggered more the 500 landslides, included the most tragic in Las Colinas landslide, and killed at least 844 people.