Journal metrics

Journal metrics

  • IF value: 2.281 IF 2.281
  • IF 5-year value: 2.693 IF 5-year 2.693
  • CiteScore value: 2.43 CiteScore 2.43
  • SNIP value: 1.193 SNIP 1.193
  • SJR value: 0.965 SJR 0.965
  • IPP value: 2.31 IPP 2.31
  • h5-index value: 40 h5-index 40
  • Scimago H index value: 73 Scimago H index 73
Volume 5, issue 6 | Copyright

Special issue: Spatial prediction modeling in natural hazards and risk

Nat. Hazards Earth Syst. Sci., 5, 853-862, 2005
https://doi.org/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

07 Nov 2005

Spatial prediction models for landslide hazards: review, comparison and evaluation

A. Brenning 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.

Publications Copernicus
Special issue
Download
Citation
Share