Comparison between Machine Learning and Physical Models Applied to the Evaluation of Co-Seismic Landslide Hazard

A comparative methodology between advanced statistical tools and physical-based methods is carried out to ensure their reliability objectivity for the evaluation of co-seismic landslide hazard maps. To do this, an inventory landslides induced by 2011 Lorca earthquake used highlight usefulness these improve earthquake-induced analyses. Various models, such as logistic regression, random forest, artificial neural network, support vector machine, have been employed susceptibility mapping. The results demonstrate that machine learning techniques using principal components (especially, network machine) yield better compared other models. In particular, forest shows poor results. Artificial approaches are in same area, suggesting can provide developing application different models need validation with actual objectivity. addition, require a great amount data. establish effective land planning management strategies seismic areas minimize damage future landslides.