Various Approaches for Predicting Land Cover in Mountain Areas

Nathalie Villa (1) , Martin Paegelow (2) , Maria T. Camacho Olmedo (3) , Laurence Cornez (2) , Frédéric Ferraty (1) , Louis Ferré (1) , Pascal Sarda (1)

1 GRIMM - Groupe de Recherche en Mathématiques et Informatique du Mirail
2 GEODE - Géographie de l'environnement
3 Instituto de Desarollo Regional

Using former maps, geographers intend to study the evolution of the land cover in order to have a prospective approach on the future landscape; predictions of the future land cover, by the use of older maps and environmental variables, are usually done through the GIS (Geographic Information System). We propose here to confront this classical geographical approach with statistical approaches: a linear parametric model (polychotomous regression modeling) and a nonparametric one (multilayer perceptron). These methodologies have been tested on two real areas on which the land cover is known at various dates; this allows us to emphasize the benefit of these two statistical approaches compared to GIS and to discuss the way GIS could be improved by the use of statistical models.

Mots clés: Classification; Comparison; Multilayer perceptron; Polychotomous regression modeling; Prediction

Domaines: Statistiques [math.ST]

Nathalie Villa, Martin Paegelow, Maria T. Camacho Olmedo, Laurence Cornez, Frédéric Ferraty, et al.. Various Approaches for Predicting Land Cover in Mountain Areas. Communications in Statistics - Simulation and Computation, 2007, 36 (1), pp.73-86. ⟨10.1080/03610910601096379⟩. ⟨hal-00144147⟩