Mariaelena Cama

Binary logistic regression versus stochastic gradient boosted decision trees in assessing landslide susceptibility for multiple-occurring landslide events: application to the 2009 storm event in Messina (Sicily, southern Italy)

AbstractnThis 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 test of transferability for landslides susceptibility models under extreme climatic events: application to the Messina 2009 disaster

A model building strategy is tested to assess the susceptibility for extreme climatic events driven shallow landslides. In fact, extreme climatic inputs such as storms typically are very local phenomena in the Mediterranean areas, so that with the exception of recently stricken areas, the landslide inventories which are required to train any stochastic model are actually unavailable. A solution is here proposed, consisting in training a susceptibility model in a source catchment, which was implemented by applying the binary logistic regression technique, and exporting its predicting function (selected predictors regressed coefficients) in a target catchment to predict its landslide distribution. To test the method, we exploit the disaster that occurred in the Messina area (southern Italy) on 1 October 2009 where, following a 250-mm/8-h storm, approximately two thousand debris flow/debris avalanches landslides in an area of 21xa0km2 triggered, killing 37 people and injuring more than 100, and causing 0.5xa0Mxa0€ worth of structural damage. The debris flows and debris avalanches phenomena involved the thin weathered mantle of the Varisican low to high-grade metamorphic rocks that outcrop in the eastern slopes of the Peloritani Mounts. Two 10-km2-wide stream catchments, which are located inside the storm core area, were exploited: susceptibility models trained in the Briga catchment were tested when exported to predict the landslides distribution in the Giampilieri catchment. The prediction performance (based on goodness of fit, prediction skill, accuracy and precision assessment) of the exported model was then compared with that of a model prepared in the Giampilieri catchment exploiting its landslide inventory. The results demonstrate that the landslide scenario observed in the Giampilieri catchment can be predicted with the same high performance without knowing its landslide distribution: we obtained, in fact, a very poor decrease in predictive performance when comparing the exported model to the native random partition-based model.

Exploring relationships between grid cell size and accuracy for debris-flow susceptibility models: a test in the Giampilieri catchment (Sicily, Italy)

AbstractnDebrisn flows are among the most hazardous phenomena in nature, requiring the preparation of susceptibility models in order to cope with this severe threat. The aim of this research was to verify whether a grid cell-based susceptibility model was capable of predicting the debris-flow initiation sites in the Giampilieri catchment (10xa0km2), which was hit by a storm on the 1st October 2009, resulting in more than one thousand landslides. This kind of event is to be considered as recurrent in the area as attested by historical data. Therefore, predictive models have been prepared by using forward stepwise binary logistic regression (BLR), a landslide inventory and a set of geo-environmental attributes as predictors. In particular, the effects produced in the quality of the predictive models by changing the grid cell size (2, 4, 16 and 32xa0m) have been explored in terms of predictive performance, robustness, importance and role of the selected predictors. The results generally attested for high predictive performances of the 2, 8 and 16xa0m model sets (AUROCxa0>xa00.8), with the latter producing slightly better predictions and the 32xa0m showing the worst yet still acceptable performance and the lowest robustness. As regards the predictors, although all the 4 sets of models share a common group (topographic attributes, outcropping lithology and land use), the similarity resulted higher between the 8 and 16xa0m sets. The research demonstrates that no meaningful loss in the predictive performance arises by adopting a coarser cell size for the mapping unit. However, the largest adopted cell size resulted in marginally worse model performance, with AUROC slightly below 0.8 and error rates above 0.3.

Geomorphologic map of the 1st Mutnaya River, Southeastern Kamchatka, Russia

The Kamchatka Peninsula–situated in the Pacific “Ring of Fire”–has 29 active and over 400 extinct volcanoes. Since it is situated in the northeastern extremity of Russia, in subarctic climate, the volcanic landforms are overprinted by the 446 glaciers. This research focuses on the 1stMutnaya catchment which drains the southern slopes of two active volcanoes: Avachinsky and Koryaksky. Those volcanoes are a permanent threat for the cities of Petropavlovsk and Elizovo, which are the 2 of 3 cities of the peninsula. Hence, most of the studies carried out in the area dealt with the natural hazards and only few focus on landscape evolution. Thus, the purpose of this study was to elaborate a cartographic approach which integrates classic geomorphology with state of the art GIS and remote sensing techniques. As result, different landforms and related processes have been analysed and included in the first general geomorphologic map of the 1stMutnaya catchment.