Document Type


Publication Date



Susceptibility assessment concerning the estimation of areas prone to landslide is one of the most useful approach in the analysis of landslide hazard. Over the last years, in an attempt to find the best approach to evaluate landslide susceptibility, many methods have been developed. Among these, the heuristic, the statistical, and the data-driven approaches are very widespread, and they all are based on the concept that the conditions which led to landslide movements in the past will control the probability of movement occurrence in the future. The main disadvantage of the heuristic approach is its high level of subjectivity, since the decision rules to create the susceptibility map depend on the experience of the researcher. On the other hand, the heuristic approach allows the researcher, on the basis of a regressive analysis of results, to make adjustments in the model in order to improve its performances. Statistical and data-driven methods are more objective than the heuristic approach but they require the collection of large amounts of data to produce reliable results; finally, statistical methods allow one to estimate the contribution of each factor to the slope failure. This study presents an assessment of landslide susceptibility in which models of the three different methodologies, such as the generalized linear models, which include the logistic regression, the artificial neural networks, and the heuristic approach are used, along with GIS spatial analysis techniques. We compare the results by applying the three different approaches to evaluate the debris-mud flows susceptibility to Briga and Giampilieri basins, two catchments of the city area of Messina (Sicily) where a considerable number of historical events were documented. The evaluation is carried out by comparing the area under the ROC (Receiver Operating Characteristic) curves resulting from the application of the three approaches.


Session R44, Risk and Uncertainty in Decision Making and Assessment



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.