The Utility of Spaceborne Radar to Render Flood Inundation Maps Based on Multialgorithm Ensembles

Abstract

On December 12, 2006, both the European Remote Sensing Satellite 2 and Environmental Satellite recorded a high-magnitude flood event on the River Dee in Wales (U.K.) only 28 min apart. This unique opportunity enables the creation of a very rare but extremely useful observed data set for flood inundation studies. For flood management purposes, hydrodynamic models are often run after an event but with field data gauged during the event to approximate both flood area and depth. As an adequate a priori definition of model parameters is difficult, they tend to be run with multiple parameter sets to generate a likelihood of inundation map. However, as field observations of events are often very scarce, these output maps cannot be validated with field-observed probabilities. This paper illustrates how this unique set of spaceborne radar images can be used in combination with five widely used image processing techniques to generate an event-specific inundation map that expresses a degree of belief that a given pixel is possibly flooded. It is expected that the value of this multialgorithm ensemble-based map opens up new ways to evaluate the performance of hydrodynamic models, as it contains information which has, to the authors' knowledge, not previously been available.