Predicting gully initiation : comparing data mining techniques, analytical hierarchy processes and the topographic threshold

Auteur(s) et Affiliation(s)

SVORAY, T.

Dep. of Geography and Environmental Development, Ben Gurion Univ. of the Negev, Beer Sheva, Israel

MICHAILOV, E.

Dep. of Information Systems Engineering, Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel

COHEN, A.

Dep. of Information Systems Engineering, Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel

ROKAH, L.

Dep. of Information Systems Engineering, Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel

STURM, A.

Dep. of Information Systems Engineering, Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel

Description :
In this work, a data mining (DM) procedure based on decision trees was applied to identify areas of gully initiation risk. Performance was compared with the analytic hierarchy process (AHP) expert system and with the commonly used topographic threshold (TT) technique. A spatial database was used to test the models, composed of a target variable (presence or absence of initial points) and ten independent environmental, climatic and human-induced variables. The following findings emerged : using the same input layers, DM provided better predictive ability of gully initiation points than the application of both AHP and TT. The main difference between DM and TT was the very high overestimation inherent in TT. The study area is the Yehezkel catchment in northern Israel.

Type de document :
Article de périodique

Source :
Earth surface processes and landforms, issn : 0197-9337, 2012, vol. 37, n°. 6, p. 607-619, nombre de pages : 13, Références bibliographiques : 64 ref.

Date :
2012

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

Langue :
Anglais