This study aims to compare binary logistic regression (BLR) and stochastic gradient treeboost (SGT) methods in assessing landslide susceptibility within the Mediterranean region for multiple-occurrence regional landslide events. A test area was selected in the north-eastern sector of Sicily (southern Italy) where thousands of debris flows and debris avalanches triggered on the first October 2009 due to an extreme storm. Exploiting the same set of predictors and the 2009 event landslide archive, BLR- and SGT-based susceptibility models have been obtained for the two catchments separately, adopting a random partition (RP) technique for validation. In addition, the models trained in one catchment have been tested in predicting the landslide distribution in the second, adopting a spatial partition (SP)-based validation. The models produced high predictive performances with a general consistency between BLR and SGT in the susceptibility maps, predictor importance and role. In particular, SGT models reached a higher prediction performance with respect to BLR models for RP-modelling, while for the SP-based models, the difference in predictive skills dropped, converging to equally excellent performances. However, analysing the precision of the probability estimates, BLR produced more robust models around the mean value for each pixel, indicating possible overfitting effects, which affect decision trees to a greater extent. The assessment of the predictor roles allowed identifying the activation mechanisms which are primarily controlled by steep south-facing open slopes located near the coastal area. These slopes are characterised by low/middle altitude downhill from mountain tops, having a medium-grade metamorphic bedrock, under grassland and cultivated (terraced) uses
A statistical approach was employed to model the spatial distribution of rainfall-triggered landslides in two areas in Sicily (Italy) that occurred during the winter of 2004-2005. The investigated areas are located within the Belice River basin and extend for 38.5 and 10.3 km2, respectively. A landslide inventory was established for both areas using two Google Earth images taken on October 25th 2004 and on March 18th 2005, to map slope failures activated or reactivated during this interval. Geographic Information Systems (GIS) were used to prepare 5 m grids of the dependent variables (absence/presence of landslide) and independent variables (lithology and 13 DEM-derivatives). Multivariate Adaptive Regression Splines (MARS) were applied to model landslide susceptibility whereas receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) were used to evaluate model performance. To evaluate the robustness of the whole procedure, we prepared 10 different samples of positive (landslide presence) and negative (landslide absence) cases for each area. Absences were selected through two different methods: (i) extraction from randomly distributed circles with a diameter corresponding to the mean width of the landslide source areas; and (ii) selection as randomly distributed individual grid cells. A comparison was also made between the predictive performances of models including and not including the lithology parameter.The models trained and tested on the same area demonstrated excellent to outstanding fit (AUC > 0.8). On the other hand, predictive skill decreases when measured outside the calibration area, although most of the landslides occur where susceptibility is high and the overall model performance is acceptable (AUC > 0.7). The results also showed that the accuracy of the landslide susceptibility models is higher when lithology is included in the statistical analysis. Models whose absences were selected using random circles showed a significantly better performance when learning and validation samples were extracted from the same area; whereas, conversely, no significant difference was observed when testing the models outside the training area
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.