Journal cover Journal topic
Natural Hazards and Earth System Sciences An interactive open-access journal of the European Geosciences Union
Nat. Hazards Earth Syst. Sci., 5, 853-862, 2005
http://www.nat-hazards-earth-syst-sci.net/5/853/2005/
doi:10.5194/nhess-5-853-2005
© Author(s) 2005. This work is licensed under the
Creative Commons Attribution-NonCommercial-ShareAlike 2.5 License.
 
07 Nov 2005
Spatial prediction models for landslide hazards: review, comparison and evaluation
A. Brenning Institute of Medical Informatics, Biometry and Epidemiology, University of Erlangen-Nürnberg, Erlangen, Germany
Abstract. The predictive power of logistic regression, support vector machines and bootstrap-aggregated classification trees (bagging, double-bagging) is compared using misclassification error rates on independent test data sets. Based on a resampling approach that takes into account spatial autocorrelation, error rates for predicting "present" and "future" landslides are estimated within and outside the training area. In a case study from the Ecuadorian Andes, logistic regression with stepwise backward variable selection yields lowest error rates and demonstrates the best generalization capabilities. The evaluation outside the training area reveals that tree-based methods tend to overfit the data.

Citation: Brenning, A.: Spatial prediction models for landslide hazards: review, comparison and evaluation, Nat. Hazards Earth Syst. Sci., 5, 853-862, doi:10.5194/nhess-5-853-2005, 2005.
Publications Copernicus
Download
Share