Title: Multi-Scale Robust Modelling of Landslide Susceptibility: Regional Rapid Assessment and Catchment Robust Fuzzy Ensemble
Authors: BOSCO ClaudioDE RIGO DANIELEDIJKSTRA TomSANDER GrahamWASOWSKI Janusz
Citation: IFIP ADVANCES IN INFORMATION AND COMMUNICATION TECHNOLOGY vol. 413 p. 321-335
Publisher: SPRINGER VERLAG
Publication Year: 2013
JRC N°: JRC82753
ISSN: 1868-4238
URI: http://link.springer.com/chapter/10.1007%2F978-3-642-41151-9_31#
http://publications.jrc.ec.europa.eu/repository/handle/JRC82753
DOI: 10.1007/978-3-642-41151-9_31
Type: Articles in periodicals and books
Abstract: Landslide susceptibility assessment is a fundamental component of effective landslide prevention. One of the main challenges in landslides forecasting is the assessment of spatial distribution of landslide susceptibility. Despite the many different approaches, landslide susceptibility assessment still remains a challenge. A semi-quantitative method is proposed combining heuristic, deterministic and probabilistic approaches for a robust catchment scale assessment. A fuzzy ensemble model has been exploited for aggregating an array of different susceptibility zonation maps. Each susceptibility zonation has been obtained by applying heterogeneous statistical techniques as logistic regression (LR), relative distance similarity (RDS), artificial neural network (ANN) and two different landslide susceptibility techniques based on the infinite slope stability model. The sequence of data-transformation models has been enhanced following the semantic array programming paradigm. The ensemble has been applied to a study area in Italy. This catchment scale methodology may be exploited for analysing the potential impact of landscape disturbances. At regional scale, a qualitative approach is also proposed as a rapid assessment technique -- suitable to be applied in real-time operations such as wildfire emergency management.
JRC Directorate:Sustainable Resources

Files in This Item:
There are no files associated with this item.


Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.