SUPERVISED CLASSIFICATION METHODS FOR AUTOMATIC DAMAGE DETECTION CAUSED BY HEAVY RAINFALL USING MULTITEMPORAL HIGH RESOLUTION OPTICAL IMAGERY AND AUXILIARY DATA

A method for the evaluation of a model that maps the susceptibility of a territory to surface runoff is presented. It is based on proxy data of localized impacts related to runoff. It accounts for the hazard level, the vulnerability of the study area and possible mitigation actions taken to reduce the risk. The evaluation is made on a 80 km railway line in Normandy (north of France), where a comprehensive database of runoff-related impacts on the railway has been gathered over the 20th century.