Vol. 10, No. 2, 166-173, 2011

Abstract
The Belgian Federal Science Policy Office (BELSPO) has initiated a Preparatory Evaluation/Validation Programme for the products of the new PROBA-V satellite to be launched in 2012. The satellite will allow daily monitoring of terrestrial vegetation cover through remote sensing, and will cover the data provision gap between the closure of the SPOT/VEGETATION Programme and the launch of the SENTINEL-3 mission. The aim of this study is to evaluate the improvements that PROBA-V will bring along for forest monitoring in the Atlantic Biogeographical Region of Europe, and lies within the objectives of the FM@PROBA-V project. A representative site in Northern Portugal is selected for this reason. VEGETATION, LANDSAT-TM5, and MODIS data along with the JRC Forest Cover Map are used to train the classifiers, simulate PROBA-V data, apply the classifiers at 250 m, 1/3 of a km, and 1 km pixels, and validate the results, while quantifying the accuracies. Maximum Likelihood (ML), Artificial Neural Networks (ANN), and Support Vector Machine (SVM) methods were tested. From the confusion matrices the best result is obtained by MODIS 2 bands with ANN classifier. Further analysis on the base of those confusion matrices will be applied to define the best classifier taking into account all the parameters of the matrices. The best performing classifier will then be recommended to examine its robustness against sudden disastrous events, like fire, in the same area, performing change detection between sequential dates (before and after the event). The performance of the data and classifiers are demonstrated, and the preliminary results are discussed.

ISSN 1729-3782