Fragility analysis of slopes exposed to seismic hazard employing surrogate modeling techniques

Abstract Natural disasters may lead to failure of critical assets part railway systems. Slope often results in major economic consequences. Due the importance that railways systems have, it is pertinent ensure good performance and long‐term. The objective present research propose tools allow obtaining probability soil slopes under a seismic event by employing surrogate models ease computational cost considering uncertainties associated with geotechnical geometrical properties case study located Portugal. presented methodology derived fragility curves, using peak ground acceleration (PGA) as intensity measure (IM), can be used assess slope for different safety levels, thus providing useful information prioritizing taking preventive actions maintain desired system.