Informations et ressources scientifiques
sur le développement des zones arides et semi-arides

Accueil du site → Master → Pays Bas → Remotely small reservoir monitoring : A Bayesian approach

Delft University of Technology (2013)

Remotely small reservoir monitoring : A Bayesian approach

Eilander, D.M. 

Titre : Remotely small reservoir monitoring : A Bayesian approach

Auteur : Eilander, D.M. 

Université de soutenance : Delft University of Technology

Grade : Master of Science 2013

Résumé
A new semi-supervised `growing’ Bayesian classifier for small reservoir delineation has been developed and is tested with Radarsat-2 data for reservoirs in the semi-arid Upper East Region of Ghana. The classifier reduces the confusion error to the land-water boundary pixels, can readily be extended with auxiliary information and has a high degree of automation. Results indicate that the algorithm is able to delineate open water from SAR imagery for different weather and environmental conditions. As such, the algorithm allows for remotely sensed operational monitoring of small reservoir storages.

Mots clés : small reservoirs ; SAR imagery ; Radarsat-2 ; reservoir storage ; Bayesian analysis ; remote sensing

Présentation

Version intégrale (2,0 Mb)

Page publiée le 18 juin 2013, mise à jour le 21 octobre 2017