An Approach based on Adaptive Decision Tree for Land Cover Change Prediction in Satellite Images

Ahlem Ferchichi (1) , Wadii Boulila (1, 2) , Imed Riadh Farah (3)

1 RIADI - Laboratoire de recherche en Génie Logiciel, Applications distribuées, Systèmes décisionnels et Imagerie intelligente [Manouba]
2 IMT Atlantique - ITI - Département lmage et Traitement Information
3 ITI - Département Image et Traitement Information

Decision tree(DT)predictionalgorithmshavesignificantpotentialforremotesensingdataprediction.This paper presentsanadvancedapproachforland-coverchangepredictioninremote-sensingimagery.Several methods fordecisiontreechangepredictionhavebeenconsidered:probabilisticDT,beliefDT,fuzzyDT,and possibilistic DT.TheaimofthisstudyistoprovideanapproachbasedonadaptiveDTtopredictlandcover changes andtotakeintoaccountseveraltypesofimperfectionrelatedtosatelliteimagessuchas:uncertainty, imprecision, vagueness,conflict,ambiguity,etc.Theproposedapproachappliesanartificialneuralnetwork (ANN) modeltochoosetheappropriategainformulatobeappliedoneachDTnode.Theconsideredapproach is validatedusingsatelliteimagesrepresentingtheSaint-Paulregion,communeofReunionIsland.Results showgoodperformancesoftheproposedframeworkinpredictingchangefortheurbanzone.

Domaines: Informatique [cs]; Sciences de l'environnement

Ahlem Ferchichi, Wadii Boulila, Imed Riadh Farah. An Approach based on Adaptive Decision Tree for Land Cover Change Prediction in Satellite Images. International Conference on Knowledge Discovery and Information Retrieval, Sep 2013, Vilamoura, France. ⟨10.5220/0004519700820090⟩. ⟨hal-01930511⟩