| Summary: | International audience This study compares the predictive accuracy of eight state-of-the-art modelling techniques for 12 landforms types in a cold environment. The methods used are Random Forest (RF), Artificial Neural Networks (ANN), Generalized Boosting Methods (GBM), Generalized Linear Models (GLM), Generalized Additive Models (GAM), Multivariate Adaptive Regression Splines (MARS), Classification Tree Analysis (CTA) unit Mixture Discriminant Analysis (MDA). The spatial distributions of 12 periglacial landforms types were recorded in sub-Arctic landscape of northern Finland in 2032 grid squares at a resolution of 25 ha. First, three topographic variables were implemented into the eight modelling techniques (simple model), and then six other variables were added (three soil and three vegetation variables; complex model) to reflect the environmental conditions of each grid square. The predictive accuracy was measured by two methods: the area under the curve (AUC) of a receiver operating characteristic (ROC) plot, and the Kappa index (K), based on spatially independent model evaluation data. The mean AUC values of the simple models varied between 0.709 and 0.796, whereas the AUC values of the complex model ranged from 0.725 to 0.825. For both simple and complex models GAM, GLM, ANN and GBM provided the highest predictive performances based on both AUC and kappa values. The results encourage further applications of the novel modelling methods in geomorphology. Copyright (D 2008 John Wiley & Sons, Ltd.
|
|---|