Comparison of L-band and X-band polarimetric SAR data classification for screening earthen levees

The main focus of this research is to detect vulnerabilities on the Mississippi river levees using remotely sensed Synthetic Aperture Radar (SAR) imagery. Unstable slope conditions can lead to small landslides which weaken the levees and increase the likelihood of failure during floods. This paper analyzes the ability of detecting the landslides on the levee with different frequency bands of synthetic aperture radar data using supervised machine learning algorithms. The two SAR datasets used in this study are: (1) the X-band satellite-based radar data from DLR´s TerraSAR-X (TSX), and (2) the L-band airborne radar data from NASA JPL´s Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR). The Support Vector Machine (SVM) classification algorithm was implemented to detect the landslides on the levee. The results showed that higher accuracies have been attained using L-band radar data compared to the X-band data, likely due to the longer wavelength and deeper penetration capability of L-band data.