Quad-polarization Synthetic Aperture Radar Data Research Articles

Combination of Hyperspectral and Quad-Polarization SAR Images to Classify Marsh Vegetation Using Stacking Ensemble Learning Algorithm

Combinations of multi-sensor remote sensing images and machine learning have attracted much attention in recent years due to the spectral similarity of wetland plant canopy. However, the integration of hyperspectral and quad-polarization synthetic aperture radar (SAR) images for classifying marsh vegetation has still been faced with the challenges of using machine learning algorithms. To resolve this issue, this study proposed an approach to classifying marsh vegetation in the Honghe National Nature Reserve, northeast China, by combining backscattering coefficient and polarimetric decomposition parameters of C-band and L-band quad-polarization SAR data with hyperspectral images. We further developed an ensemble learning model by stacking Random Forest (RF), CatBoost and XGBoost algorithms for marsh vegetation mapping and evaluated its classification performance of marsh vegetation between combinations of hyperspectral and full-polarization SAR data and any of the lone sensor images. Finally, this paper explored the effect of different polarimetric decomposition methods and wavelengths of radar on classifying wetland vegetation. We found that a combination of ZH-1 hyperspectral images, C-band GF-3, and L-band ALOS-2 quad-polarization SAR images achieved the highest overall classification accuracy (93.13%), which was 5.58–9.01% higher than that only using C-band or L-band quad-polarization SAR images. This study confirmed that stacking ensemble learning provided better performance than a single machine learning model using multi-source images in most of the classification schemes, with the overall accuracy ranging from 77.02% to 92.27%. The CatBoost algorithm was capable of identifying forests and deep-water marsh vegetation. We further found that L-band ALOS-2 SAR images achieved higher classification accuracy when compared to C-band GF-3 polarimetric SAR data. ALOS-2 was more sensitive to deep-water marsh vegetation classification, while GF-3 was more sensitive to shallow-water marsh vegetation mapping. Finally, scattering model-based decomposition provided important polarimetric parameters from ALOS-2 SAR images for marsh vegetation classification, while eigenvector/eigenvalue-based and two-component decompositions produced a great contribution when using GF-3 SAR images.

Retrieval of Farmland Surface Soil Moisture Based on Feature Optimization and Machine Learning

Soil moisture is an important parameter affecting environmental processes such as hydrology, ecology, and climate. Synthetic aperture radar (SAR) microwave remote sensing is an important means of farmland surface soil moisture (SSM) measurement. The inversion of farmland SSM by microwave remote sensing is greatly affected by vegetation cover. To address this problem, a multisource remote sensing inversion method of farmland SSM based on feature optimization and machine learning is proposed in this paper. Six typical machine learning algorithms suitable for small sample training, including random forest, radial basis function neural network, generalized regression neural network, support vector regression, genetic algorithm–back propagation neural network, and extreme learning machine, were selected in this paper. The features extracted from Sentinel-1/2 and Radarsat-2 remote sensing data were analyzed by Pearson correlation, and those with high correlation coefficients were selected to form the optimal feature subset as the input for the subsequent machine learning models. Then, the SSM collaborative inversion models under different machine learning algorithms were constructed, and comparative experiments were set up to select the optimal prediction model. The models’ accuracy under different feature parameters were studied, and the difference in the performance between the dual-polarization SAR data and the quad-polarization SAR data in SSM inversion was explored. The experimental results showed that among the six models, the random forest model had a higher inversion accuracy, with a coefficient of determination of 0.6395 and a root mean square error of 0.0264 cm3/cm3. Meanwhile, the inversion accuracy could be greatly improved after feature optimization, and the inversion accuracy of the quad-polarization SAR data combined with optical remote sensing data, was better than that of the dual-polarization SAR data combined with optical remote sensing data.

HDEC-TFA: An Unsupervised Learning Approach for Discovering Physical Scattering Properties of Single-Polarized SAR Image

Understanding the physical properties and scattering mechanisms contributes to synthetic aperture radar (SAR) image interpretation. For single-polarized SAR data, however, it is difficult to extract the physical scattering mechanisms due to lack of polarimetric information. Time-frequency analysis (TFA) on complex-valued SAR image provides extra information in frequency perspective beyond the “image” domain. Based on TFA theory, we propose to generate the subband scattering pattern for every object in complex-valued SAR image as the physical property representation, which reveals backscattering variations along slant-range and azimuth directions. In order to discover the inherent patterns and generate a scattering classification map from single-polarized SAR image, an unsupervised hierarchical deep embedding clustering (HDEC) algorithm based on TFA (HDEC-TFA) is proposed to learn the embedded features and cluster centers simultaneously and hierarchically. The polarimetric analysis result for quad-pol SAR images is applied as reference data of physical scattering mechanisms. In order to compare the scattering classification map obtained from single-polarized SAR data with the physical scattering mechanism result from full-polarized SAR, and to explore the relationship and similarity between them in a quantitative way, an information theory based evaluation method is proposed. We take Gaofen-3 quad-polarized SAR data for experiments, and the results and discussions demonstrate that the proposed method is able to learn valuable scattering properties from single-polarization complex-valued SAR data, and to extract some specific targets as well as polarimetric analysis. At last, we give a promising prospect to future applications.

Generalized-K (GK)-Based Observation of Metallic Objects at Sea in Full-Resolution Synthetic Aperture Radar (SAR) Data: A Multipolarization Study

An electromagnetic model, based on the generalized-K (GK) speckle distribution, has been developed to read the scattering features associated with metallic objects at sea in full resolution single-look complex (SLC) synthetic aperture radar (SAR) data. The sensitivity of the GK parameters is investigated in both copolarized and cross-polarized SAR data. It is shown that a proper combination of GK parameters exhibits a completely different behavior with respect to sea surface with and without metallic objects, when measured over cross-polarized SAR data. As a matter of fact, a simple and very effective approach to observe metallic objects in full resolution SLC cross-polarized SAR data, is proposed. Experiments undertaken over a large data set consisting of RADARSAT-2 SLC fine quad polarization SAR data, confirm model predictions, and show that the proposed approach is both physically-based and operationally effective, since it is able to provide a logical true and false output.

Rice Crop Monitoring in South China With RADARSAT-2 Quad-Polarization SAR Data

This letter presents preliminary results of an attempt to monitor rice crop growth using RADARSAT-2 quad polarization synthetic aperture radar (SAR) data. Three RADARSAT-2 quad-polarization SAR images are collected from transplanting to rice crop harvesting. Ground truth data, such as rice height and biomass, are measured during RADARSAT-2 data acquisition in Hainan Province, South China. The correlation between backscattering coefficient and rice growth parameters is analyzed, and then, a rice field mapping method with quad polarization SAR image is developed. Experiments show that an HV or VH image backscattering coefficient exhibits the best correlation with rice age after transplantation. Furthermore, the HV or VH image is also more suitable for retrieving rice growth parameters, such as rice height and dry biomass, for FQ4 RADARSAT-2 SAR data. The ratio image of HH/VV possesses high separability required to distinguish rice crop from banana, forest, and river. Results indicate that RADARSAT-2 quad polarization SAR data presented enormous potential for monitoring rice crop growth.