Abstract
Soil moisture monitoring around earthen levees can aid in the detection of vulnerability to potential failure of a levee segment. Estimation and classification of soil moisture from SAR is difficult when the surface is covered with significant vegetation. In levees the soil is typically covered with a uniform layer of grass. An increase in the height of grass creates more volume scattering and degrades the relationship between the backscattering and soil moisture. In this work the effect of different heights of grass on the soil moisture classification of earthen levees is studied. To classify the soil moisture a back propagation neural network is used with the following methodology: (1) segmentation of levee and buffer area from the background; (2) extracting the backscatter and texture features such as GLCM (Grey- Level Co-occurrence Matrix) and wavelet features; (3) training the back propagation neural network classier; (4) testing the area of interest and validation of the results using ground truth data. The preliminary results show that the height of grass has a significant impact on soil moisture classification accuracy. The grass height increase from one month's springtime growth caused the accuracy to decrease by around 20%.