Landslide detection on earthen levees with X-band and L-band radar data

Abstract

This paper explores anomaly detection algorithms to detect vulnerabilities on Mississippi river levees using remotely sensed Synthetic Aperture Radar (SAR) data. Earthen levees protect large areas of populated and cultivated land in the United States. One sign of potential levee failure is the occurrence of landslides due to slope instabilities. Such slides could lead to further erosion and through seepage during high water events. This research seeks to design a system that is capable of performing automated target recognition tasks using radar data to detect problem areas on earthen levees. Polarimetric SAR data is effective for detecting such phenomena. In this research, we analyze the ability of different polarization channels in detecting landslides with different frequency bands of synthetic aperture radar data using anomaly detection algorithms. The two SAR datasets used in this study are: (1) the X-band satellite-based radar data from DLR's TerraSAR-X satellite, and (2) the L-band airborne radar data from NASA's Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR). The RX anomaly detector, an unsupervised classification algorithm, was implemented to detect anomalies on the levee. The discrete wavelet transform (DWT) is used for feature extraction. The algorithm was tested with both the L-band and X-band SAR data and the results demonstrate that landslide detection using L-band radar data has better accuracy compared to the X-band data based on the detection of true positives.