Résumé
Extraction of hydrological information from digital elevation models (DEMs) is a required Step When conducting and spatially distributed hydrological modelling. In particular automated methods are proposed to extract the drainage structure Front the DEM. However, a realistic river network is not always derived from conventional DEM processing methods. Indeed, inaccuracy Occurs in flat areas corresponding to floodplains. In these areas, additional Sources of information are required to extract the correct drainage direction from the DEM. In this study, it is demonstrated that traditional approaches of DEM-preprocessing Such as the commonly, known 'stream burning' fail to provide correct maps of drainage directions and catchment areas when the extension of flat areas is large. A new Method is proposed to take advantage of available imagery data. This method is based oil a 'double DEM burning' process: DEM is first burned in the main rivers using the channel network, and then in the floodplain using the spatial distribution of floodplains provided by classified satellite images. In this sense, the method has been referred to as the floodplain burning approach (or simply FB approach). Spatial distribution of floodplains is derived fro a multitemporal SAR image classification. A system Of equations is Used to vary the elevation Offset required to be 'burnt' in each cell representing the floodplain, according to the minimal distance front the channel network, which is calculated by a distance transformation. The F-B approach was applied to a sub-basin located within the larger Amazon River basin. The region is characterized by large floodplain extensions. Basin delineation maps derived from the, new method were compared With those obtained from the traditional stream burning Method and highlighted more realistic results. Copyright (C) 2009 John Wiley & Sons Ltd.