Development of a landslide susceptibility assessment for a rail network

摘要: Abstract This paper examines the applicability of a landslide susceptibility assessment approach to engineered slopes using data from Irish Rail network. A logistical regression model was used determine occurrence on an asset by basis input factors derived specifically for man-made earthworks. Records past failures were train predict probability future occurring. The analyse substantial section network comprising 1184 slopes. database assets split into training and validation datasets similar levels predictive performance achieved with both indicating robustness approach. results study show that simple databases, partially populated visual survey data, can be effectively carry out analysis. enables proactive identification critical as opposed current reactive industry standard, which represents important step forward in creating objective risk rating systems transport