Advertisement

Comparing the Performance of Different Landslide Susceptibility Models in ROC Space

Chapter
First Online:

Abstract

This article addresses performance evaluation routine for comparison of results of several different landslide susceptibility models. The study area is located on the NW slopes of Fruška Gora Mountain (Serbia). Five modelling methods were considered: Stability Index, Analytical Hierarchy Process (AHP), Fuzzy sets, Conditional Probability, and Support Vector Machines (SVM). In this respective order they gave more accurate spatial prediction of landslides. The performance of their “probabilistic” prediction is estimated by Receiver Operating Characteristics (ROC). Evaluation in ROC space is discussed in both quantitative – Area Under Curve (AUC) value, and qualitative manner – ROC curve trends. Finally, the article summarizes the advantages of the proposed ROC-based performance comparison.

Keywords

ROC curve AUC Landslide susceptibility 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgements

This work was supported by the Czech Science Foundation (Grant No. 205/09/079).

References

  1. Bell FG (2007) Engineering geology. Elsevier, Oxford, 581 p. ISBN_0750680776_Google Scholar
  2. Bonham-Carter G (1994) Geographic information system for geosciences: modeling with GIS. Pergamon, New York, 398 p. ISBN_008042420_Google Scholar
  3. Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2(1):121–167CrossRefGoogle Scholar
  4. Carrara A, Pike R (2008) GIS technology and models for assessing landslide hazard and risk. Geomorphology 94:257–260CrossRefGoogle Scholar
  5. Chacón J, Irigaray C, Fernández T, el Hamdouni R (2006) Engineering geology maps: landslides and geographical information systems. Bull Eng Geol Environ 65:341–411CrossRefGoogle Scholar
  6. Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27:861–874CrossRefGoogle Scholar
  7. Frattini P, Crosta G, Carrara A (2010) Techniques for evaluating performance of landslide susceptibility models. Eng Geol 111:62–72CrossRefGoogle Scholar
  8. Gokceoglu C, Sezer E (2009) A statistical assessment on international landslide literature (1945–2008). Landslides 6:345–351CrossRefGoogle Scholar
  9. Marjanović M (2009) Landslide susceptibility modelling: a case study on Fruška gora mountain, Serbia. Geomorphol Slov Bohem 1:29–42Google Scholar
  10. Marjanović M (2010) Regional scale landslide susceptibility analysis using different GIS-based approaches. In: Proceedings of IAEG conference, Auckland, New Zealand, 2–6 Sept 2010, pp 435–442Google Scholar
  11. Marjanović M, Caha J (2011) Fuzzy approach to landslide susceptibility zonation. In: Proceedings of Dateso 2011 workshop, Písek, Czech Republic, 21–23 Apr 2011, pp 181–195Google Scholar
  12. Marjanović M, Bajat B, Kovačević M, (2009) Landslide susceptibility assessment with machine learning algorithms. In: Proceedings of INCoS, Barcelona, Spain, 4–6 Nov 2009, pp 273–278Google Scholar
  13. Pack RT, Tarboton DG, Goodwin CN (2001) Assessing terrain stability in a GIS using SINMAP. In: Proceedings of 15th annual GIS conference, Vancouver, BC, 19–22 Feb 2001Google Scholar
  14. Saaty TL (1980) Analytical hierarchy process. McGraw-Hill, New York, 287 pp. ISBN_0070543712_Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Department for GeoinformaticsPalacký UniversityOlomoucCzech Republic

Personalised recommendations

Cite chapter

Buy options