Soilmoisture estimation from TerraSARX data usin

Authors: Matej Kseneman Dušan Gleich Božidar Potočnik

Publish Date: 2011/10/11

Volume: 23, Issue: 5, Pages: 937-952

PDF Link

Abstract

Early prediction of natural disasters like floods and landslides is essential for reasons of public safety This can be attained by processing SyntheticAperture Radar SAR images and retrieving soilmoisture parameters In this article TerraSARX product images are investigated in combination with a watercloud model based on the Shi semiempirical model to determine the accuracy of soilmoisture parameter retrieval SAR images were captured between January 2008 and September 2010 in the vicinity of the city Maribor Slovenia at different incidence angles The watercloud model provides acceptable estimated soilmoisture parameters at bare or scarcely vegetated soil areas However this model is too sensitive to speckle noise therefore a preprocessing step for specklenoise reduction is carried out Afterwards selforganizing neural networks SOM are used to segment the areas at which the performance of this model is poor and at the same time neural networks are also used for a more accurate approximation of model parameters’ values Groundtruth is measured using the Pico64 sensor located on the field simultaneously with capturing SAR images in order to enable the comparison and validation of the obtained results Experimental results show that the proposed method outperforms the watercloud model accuracy over all incidence angles

Keywords: