Advertisement

Estimation of Information Loss When Masking Conditional Dependence and Categorizing Continuous Data: Further Experiments on a Database for Spatial Prediction Modelling in Northern Italy

  • Andrea G. Fabbri
  • Simone Poli
  • Antonio Patera
  • Angelo Cavallin
  • Chang-Jo Chung
Conference paper
Part of the Lecture Notes in Earth System Sciences book series (LNESS)

Abstract

Prediction patterns are generated using different data sets from a database for landslides hazard in northern Italy. A direct supporting pattern of the distribution of 28 complex landslides was previously used to obtain their spatial relationships with five categorical indirect supporting patterns representing the spatial context of the landslides: geology, land use, and permeability in addition to internal relief and slope, the latter two categorized into five classes. The five indirect supporting patterns were selected to minimize the effects of conditional dependence on prediction patterns by a Weight-of-Evidence model. The same set of patterns is reanalysed applying the Empirical Likelihood Ratio model using also uncategorized continuous supporting patterns: aspect, curvature, and digital elevation, in addition to internal relief and slope. The resulting prediction patterns are compared in terms of prediction rates and target-uncertainty patterns.

Keywords

Spatial Relationship Landslide Hazard Spatial Database Spatial Context Spatial Prediction 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Chung, C. F. (2006). Using likelihood ratio functions for modelling the conditional probability of occurrence of future landslides for risk assessment. Computers & Geosciences, 32, 1052–1065.CrossRefGoogle Scholar
  2. 2.
    Fabbri, A. G., Poli, S., Sterlacchini, S., Cavallin, A., Chung, C. J. (2011). Uncertainty of class membership in spatial prediction modelling: follow-up study to an application to complex landslides. Proceedings IAMG 2011, Peer-reviewed IAMG 2011 publication (12 pp). doi: 10.5242/iamg.2011.0241
  3. 3.
    Poli, S., & Sterlacchini, S. (2007). Landslide representation strategies of susceptibility studies using Weights-of-Evidence modelling technique. Natural Resources Research, 16(2), 121–134.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Andrea G. Fabbri
    • 1
  • Simone Poli
    • 2
  • Antonio Patera
    • 3
  • Angelo Cavallin
    • 1
  • Chang-Jo Chung
    • 4
  1. 1.DISATUniversità di Milano-BicoccaMilanItaly
  2. 2.ERMEnvironmental Resourse ManagementMilanItaly
  3. 3.INGVIstituto Nazionale di Geofisica e VulcanologiaRomeItaly
  4. 4.Spatial Models IncOttawaCanada

Personalised recommendations