Presence-only approach to assess landslide triggering-thickness susceptibility: a test for the Mili catchment (north-eastern Sicily, Italy)

Abstract

This study evaluates the performances of the presence only approach, Maximum Entropy, in assessing landslide triggering-thickness susceptibility within the Mili catchment (Sicily, Italy). This catchment underwent several meteorological stresses, resulting in hundreds of shallow rapid mass movements between 2007 and 2011. In particular, the area has become known for two disasters, which occurred in 2009 and 2010; the first weather system did not pass directly over the catchment however peak rainfall was registered over the basin during the second meteorological event.Field data were collected to associate the depth from the slope surface that material was mobilised at the triggering zone to each mass movement within the catchment. This information has been used to model the landslide susceptibility for two classes of processes, divided into shallow failures for maximum depths of 1m and deep ones in case of values equal or greater than 1m. Topographic attributes from a 2m DEM were used as predictors, together with medium resolution vegetation indexes derived from ASTER scenes and geological, land use and tectonic maps. The presence-only approach discriminated between the two depth classes at the landslide trigger zone, producing excellent prediction skills associated with relatively low variances across a set of 50 randomly generated replicates. The role of each predictor was assessed to ascertain the significance to the final model output. This work uses simple field measurements to produce triggering-thickness susceptibility, which is a novel approach and may perform better as a proxy for landslide hazard assessments with respect to more common susceptibility practises.

Shallow Landslide Susceptibility Mapping by Random Forest Base Classifier and Its Ensembles in a Semi-Arid Region of Iran

“…However, producing standardized and accurate landslide susceptibility maps at catchment and regional scales is not a straightforward task. Nevertheless, accuracy can be determined with a variety of metrics [118], and the number of algorithms that evaluate accuracy is constantly increasing [119] as technology improves computational efficiency. Numerous modeling techniques have been employed over the past three decades to generate increasingly accurate landslide susceptibility maps, and several landslide researchers are seeking an optimal method or workflow in comparative studies [41,120] and for machine learning algorithms [121].…”

Geostatistical Modeling to Capture Seismic‐Shaking Patterns From Earthquake‐Induced Landslides

“…Therefore, a polygon‐to‐point conversion was required for the Wenchuan inventory. In the literature, two conversion methods are available: (i) extracting the highest location along the perimeter of the landslide scar (e.g., Cama et al, ; Lombardo et al, ); or (ii) computing centroids for each polygon (e.g., Hussin et al, ; Zêzere et al, ). Here, we selected the centroid option for consistency between the Lushan and Wenchuan data sets.…”

Exploiting Maximum Entropy method and ASTER data for assessing debris flow and debris slide susceptibility for the Giampilieri catchment (north‐eastern Sicily, Italy)

“…Among these, Philips et al (2004Philips et al ( , 2006 presented an integrated approach of maximum entropy and geographic information system (GIS) technologies for species distribution modelling where the application of this algorithm maximizes the entropy in a geographic space. In the present contribution, we exploit the MaxEnt approach to predict the spatial distribution of landslides, with a similar assumption to that described in Convertino et al (2013) and Lombardo et al (2016). Merow et al (2013) illustrate the MaxEnt model architecture as requiring presence-only (PO) data and a set of predictors distributed across a regularly gridded space.…”