 |
| Titel |
Spatial prediction models for landslide hazards: review, comparison and evaluation |
| VerfasserIn |
A. Brenning |
| Medientyp |
Artikel
|
| Sprache |
Englisch
|
| ISSN |
1561-8633
|
| Digitales Dokument |
URL |
| Erschienen |
In: Natural Hazards and Earth System Science ; 5, no. 6 ; Nr. 5, no. 6 (2005-11-07), S.853-862 |
| Datensatznummer |
250002881
|
| Publikation (Nr.) |
 copernicus.org/nhess-5-853-2005.pdf |
|
|
|
|
|
| Zusammenfassung |
| 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. |
| |
|
| Teil von |
|
|
|
|
|
|
|
|