Khaled Hasan

Detection of slump slides on earthen levees using polarimetric SAR imagery

Key results are presented of an extensive project studying the use of synthetic aperture radar (SAR) as an aid to the levee screening process. SAR sensors used are: (1) The NASA UAVSAR (Uninhabited Aerial Vehicle SAR), a fully polarimetric L-band SAR capable of sub-meter ground sample distance; and (2) The German TerraSAR-X radar satellite, also multi-polarized and featuring 1-meter GSD, but using an X-band carrier. The study area is a stretch of 230 km of levees along the lower Mississippi River. The L-band measurements can penetrate vegetation and soil somewhat, thus carrying some information on soil texture and moisture which are relevant features to identifying levee vulnerability to slump slides. While X-band does not penetrate as much, its ready availability via satellite makes multitemporal algorithms practical. Various feature types and classification algorithms were applied to the polarimetry data in the project; this paper reports the results of using the Support Vector Machine (SVM) and back-propagation Artificial Neural Network (ANN) classifiers with a combination of the polarimetric backscatter magnitudes and texture features based on the wavelet transform. Ground reference data used to assess classifier performance is based on soil moisture measurements, soil sample tests, and on site visual inspections.

Use of remote sensing to screen earthen levees

Multi-polarized L-band Synthetic Aperture Radar is investigated for its potential to screen earthen levees for weak points. Various feature detection and classification algorithms are tested for this application, including both radiometric and textural methods such as grey-level co-occurrence matrix and wavelet features.

Earthen levee monitoring with Synthetic Aperture Radar

The latest results are presented from an ongoing study of the use of multi-polarized Synthetic Aperture Radar as an aid in screening earthen levees for weak points. Both L-band airborne and X-band spaceborne radars are studied, using the NASA UAVSAR and the German TerraSAR-X platforms. Feature detection and classification algorithms tested for this application include both radiometric and textural methods. Radiometric features include both the simple backscatter magnitudes of the HH, VV, and HV channels as well as decompositions such as Entropy, Anisotropy, and Alpha angle. Textural methods include grey-level co-occurrence matrix and wavelet features. Classifiers tested include Maximum Likelihood and Artificial Neural Networks. The study area includes 240 km of levees along the lower Mississippi River. Results to date are encouraging but still very preliminary and in need of further validation and testing.

A Machine Learning Framework for Detecting Landslides on Earthen Levees Using Spaceborne SAR Imagery

Earthen levees have a significant role in protecting large areas of inhabited and cultivated land in the United States from flooding. Failure of the levees can result in loss of life and property. Slough slides are among the problems which can lead to complete levee failure during a high water event. In this paper, we develop a method to detect such slides using X-band synthetic aperture radar (SAR) data. Our proposed methodology includes: radiometric normalization of the TerraSAR image using high-resolution digital elevation map (DEM) data; extraction of features including backscatter and texture features from the levee; a feature selection method based on minimum redundancy maximum relevance (mRMR); and training a support vector machine (SVM) classifier and testing on the area of interest. To validate the proposed methodology, ground-truth data are collected from slides and healthy areas of the levee. The study area is part of the levee system along the lower Mississippi River in the United States. The output classes are healthy and slide areas of the levee. The results show the average classification accuracies of approximately 0.92 and Cohens kappa measures of 0.85 for both healthy and slide pixels using ten optimal features selected by mRMR with a sigmoid SVM. A comparison of the SVM performance to the maximum likelihood (ML) and back propagation neural network (BPNN) shows that the average accuracy of the SVM is superior to that of the BPNN and ML classifiers.

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

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 DLRs TerraSAR-X satellite, and (2) the L-band airborne radar data from NASAs 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.

Effect of vegetation height and volume scattering on soil moisture classification using synthetic aperture radar (SAR) images

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 months springtime growth caused the accuracy to decrease by around 20%.