Lalitha Dabbiru

Levee anomaly detection using polarimetric synthetic aperture radar data

This research presents results of applying the NASA JPLs Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) quad-polarized L-band data to detect anomalies on earthen levees. Two types of problems / anomalies that occur along these levees which can be precursors to complete failure during a high water event are slough slides and sand boils. The study area encompasses a portion of levees of the lower Mississippi river in the United States. Supervised and unsupervised classification techniques have been employed to detect slough slides along the levee. RX detector, a training-free classification scheme is introduced to detect anomalies on the levee and the results are compared with the k-means clustering algorithm. Using the available ground truth data, a supervised kernel based classification technique using a Support Vector Machine (SVM) is applied for binary classification of slides on the levee versus the healthy levee and the performance is compared with a neural network classifier.

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 slide detection via automated analysis of synthetic aperture radar imagery

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 slump slides, which weaken the levees and increase the likelihood of failure during floods. On-site inspection of levees is expensive and time-consuming, so there is a need to develop efficient automated techniques based on remote sensing technologies to identify levees that are more vulnerable to failure under flood loading. Synthetic Aperture Radar technology, due to its high spatial resolution and potential soil penetration capability, is a good choice to identify problem areas along the levee so that they can be treated to avoid possible catastrophic failure. This research analyzes the ability of detecting the slump slides on the levee with NASA JPL’s Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) data. The main contribution of this research is the development of a machine learning framework to (1) provide improved knowledge on the status of the levees, (2) detect anomalies on the levee sections, (3) provide early warning of impending levee failures, and (4) develop efficient tools for levee health assessment. Textural features have been computed and utilized in the classification tasks to achieve efficient levee characterization. The RX anomaly detector, a training-free unsupervised classification algorithm, detected the active slides on the levee at the time of image acquisition and also flagged some areas as “anomalous,” where new slides appeared at a later date.

Fusion of synthetic aperture radar and hyperspectral imagery to detect impacts of oil spill in Gulf of Mexico

The Deepwater Horizon blowout in the Gulf of Mexico resulted in one of the largest accidental oil disasters in U.S. history. NASA acquired radar and hyperspectral imagery and made them available to the scientific community for analyzing impacts of the oil spill. In this study, we use the L-band quad-polarized radar data acquired by Unmanned Aerial Vehicle Synthetic Aperture Radar (UAVSAR) and Hyperspectral Imagery (HSI) from the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) optical sensor. The main objective of this research is to apply fusion techniques on polarimetric radar and hyperspectral imagery to investigate the benefit of fusion for improved classification of coastal vegetation contaminated by oil. In this approach, fusion is implemented at the pixel level by concatenating the hyperspectral data with the high resolution SAR data and analyze the fused data with Support Vector Machine (SVM) classification algorithm.

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.

Classification of levees using polarimetric Synthetic Aperture Radar (SAR) imagery

The recent catastrophe caused by hurricane Katrina emphasizes the importance of examination of levees to improve the condition of those that are prone to failure during floods. On-site inspection of levees is costly and time-consuming, so there is a need to develop efficient techniques based on remote sensing technologies to identify levees that are more vulnerable to failure under flood loading. This research uses NASA JPLs Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) backscatter data for classification and analysis of earthen levees. The overall purpose of this research is to detect the problem areas along the levee such as through-seepage, sand boils and slough slides. This paper focuses on detection of slough slides. Since the UAVSAR is a quad-polarized L-band (λ = 25 cm) radar, the radar signals penetrate into the soil which aids in detecting soil property variations in the top layer. The research methodology comprises three steps: initially the SAR image is classified into three scattering components using the Freeman-Durden decomposition algorithm; then unsupervised classification is performed based on the polarimetric decomposition parameters: entropy (H) and alpha (α); and finally reclassified using the Wishart classifier. A 3×3 coherency matrix is calculated for each pixel of the radars compressed Stokes matrix multi-look backscatter data and is used to retrieve these parameters. Different scattering mechanisms like surface scattering, dihedral scattering and volume scattering are observed to distinguish different targets along the levee. The experimental results show that the Wishart classifier can be used to detect slough slides on levees.

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 DLRs TerraSAR-X (TSX), and (2) the L-band airborne radar data from NASA JPLs 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.

Fusion of hyperspectral and LiDAR data using random feature selection and morphological attribute profiles

Hyperspectral imagery provides detailed information about land-cover materials over a wide spectral range. Land-cover classification using hyperspectral data has been an active topic of research. Elevation data from light detection and ranging (LiDAR) can aid the classification process in discriminating complex classes. Fusion of hyperspectral and LiDAR data has been investigated in the past where the goal was to extract features from both sources and combine them to improve the accuracy of land-cover classification. In this paper, we present a new fusion approach based on random feature selection (RFS) and morphological attribute profiles (AP). Our experimental study, conducted on a hyperspectral image and digital surface model (DSM) derived from first return LiDAR data collected over the Samford ecological research facility, Queensland, Australia indicate that the proposed approach yields excellent classification results.

Runway assessment via remote sensing

Airport pavements are constructed to provide adequate support for the loads and traffic volume imposed by aircrafts. One aspect of pavement evaluation is the pavement condition which is determined by the types and extent of distresses. These include cracking, rutting, weathering, and others that may affect pavement surface roughness and the potential for FOD (Foreign Object Debris). Pavement evaluations are necessary to assess the ability to safely operate aircraft on an airfield. The purpose of this study is to explore the potential use of microwave remote sensing to assess the pavement surface roughness. Radar backscatter responds to surface roughness as well as dielectric constant. The resulting changes in backscatter can convey information about the degree of cracking and surface roughness of the runway. In this study, we develop a relation between the Terrain Ruggedness Index (TRI) of the runway and radar backscatter magnitudes. Radar data from the TerraSAR-X satellite is used, along with airborne LiDAR data (30 cm spacing). Modest linear correlation was found between the vertical co-polarization channel of the radar data and TRI values computed in 5 by 5 pixel windows from the LiDAR elevation data. Over four different test areas on the runway, the coefficients of determination ranged from 0.12 to 0.46.