Remote sensing and classification bogs in Quebec using RADARSAT-1 images

This study has been conducted within the Fonds pour la formation de chercheurs et l'aide la recherche (FCAR)-Action concertee RADARSAT program. The study shows the potential of RADARSAT-1 standard mode data (S1 and S7 beams) for mapping natural and exploited wetlands in southern Quebec. The best period for the acquisition of SI beam data is during the growing season. However, an S7 beam mode image acquired in February (winter) can help to discriminate different vegetation densities within wetlands. With a maximum likelihood classification method, the data set giving the best results is the winter S7 image and two summer S1 images (May 7 or June 11 and July 28 or August 3). The large wetlands can be easily classified amongst other areas (i.e., agricultural, open water, forest, etc.) by this method and data set, but the different categories of vegetation communities within wetlands cannot be well discriminated. However, the use of a texture parameter (mean, 7 x 7 windows) can significantly improve the classification accuracy. It also permits to distinguish exploited wetlands from natural wetlands and forest areas with an average precision of 89% (for training sites). Furthermore, a neural network classification approach has been adapted to classify radar images for three categories of natural wetlands (i.e., woody wetlands, shrubby wetlands and woody shrubby wetlands). The best classification results (i.e., 86% accuracy) were obtained using a neural network trained by 18 texture channels derived from six RADARSAT-1 images (three S1 and three S7). However, using only two images (one S1 and one S7) gave a similar level of accuracy (84% on test sites and 90% on training sites).