Mapping Flooded Vegetation Using COSMO-SkyMed: Comparison With Polarimetric and Optical Data Over Rice Fields

The capability of COSMO-SkyMed (CSK) radar to remotely sense standing water beneath vegetation using an automatic algorithm working on a single image is investigated. The objective is to contribute to tackle the problem of missed detection of inundated vegetation by near real-time flood mapping algorithms using SAR data. The focus is on CSK because its four-satellite constellation is very suitable for rapid mapping. A set of CSK observations of an area in Northern Italy where many rice fields are present and recurrent artificial inundations occur were analyzed. Considering that double-bounce is the key process to detect floodwater under vegetation and that polarimetry is potentially able to discriminate double-bounce among different scattering mechanisms, single polarization CSK observations were compared with ALOS-2 and RADARSAT-2 fully polarimetric data. Such a multifrequency and multiangle dataset helped understanding the multitemporal signature of CSK data. A set of Landsat-8 images collected under cloud free conditions were also used as reference. Satellite acquisitions were gathered in order to ensure both spatial overlap among the images of the various sensors and temporal overlap along most of the rice growing season. The comparison between CSK and polarimetric data showed that at least for a slender leaf plant like rice, CSK can be able to detect the enhancement of double-bounce backscattering involving water and vertical plant stems. For some selected fields, it was found a good agreement between CSK-derived floodwater maps and those produced using the normalized-difference water index derived from Landsat-8 images, as well as double-bounce detection from polarimetric data.