Flood Extent Extraction Neural Networks Data Fusion SAR Images
Issue Date:
2008
Publisher:
Institute of Information Theories and Applications FOI ITHEA
Abstract:
Floods represent the most devastating natural hazards in the world, affecting more people and causing
more property damage than any other natural phenomena. One of the important problems associated with flood
monitoring is flood extent extraction from satellite imagery, since it is impractical to acquire the flood area through
field observations. This paper presents a method to flood extent extraction from synthetic-aperture radar (SAR)
images that is based on intelligent computations. In particular, we apply artificial neural networks, self-organizing
Kohonen’s maps (SOMs), for SAR image segmentation and classification. We tested our approach to process
data from three different satellite sensors: ERS-2/SAR (during flooding on Tisza river, Ukraine and Hungary,
2001), ENVISAT/ASAR WSM (Wide Swath Mode) and RADARSAT-1 (during flooding on Huaihe river, China,
2007). Obtained results showed the efficiency of our approach.
