A comparison of predictive methods in modelling the distribution of periglacial landforms in Finnish Lapland

Auteur(s) et Affiliation(s)



Description :
This study compares the predictive accuracy of 8 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) and 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, 3 topographic variables were implemented into the 8 modelling techniques (simple model), and then 6 other variables were added (3 soil and 3 vegetation variables; complex model) to reflect the environmental conditions of each grid square. The predictive accuracy was measured by 2 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 results encourage further applications of the novel modelling methods in geomorphology.


Type de document :
Article de périodique

Source :
Earth surface processes and landforms, issn : 0197-9337, 2008, vol. 33, n°. 14, p. 2241-2254, nombre de pages : 14, Références bibliographiques : 2 p.

Date :
2008

Editeur :
Pays édition : Royaume-Uni, Chichester, Wiley