Synthetic aperture radar (SAR) data classification has gained significant research interest, as accurate land-cover information is vital in a wide range of planning and management activities. While classification algorithms for full-polarimetric (full-pol) SAR data are typically based on the statistical or physical characteristics of the scattering mechanism from targets, classification of co-cross polarization (VV-VH or HH-HV) dual-polarimetric (dual-pol) SAR data has traditionally relied on backscatter intensity information due to its limited polarimetric information. Several studies also employ the dual-pol entropy/alpha decomposition parameters, establishing a conventional framework for supervised and unsupervised classification of dual-pol SAR data. However, it is essential to note that the conventional approach cannot differentiate between certain elementary targets, leading to misclassification among diverse land-cover targets. To address this limitation, we introduce an unsupervised clustering technique for dual-pol Sentinel-1 SAR data utilizing the conventional entropy parameter alongside a dual-pol target characteristic parameter that discriminates between various land-cover targets, including “dihedral-like” (buildings, etc.) and “surface-like” (water bodies, etc.) targets in a dual-pol scene. Thus, the proposed clustering scheme, which applies to both single look complex (SLC) and ground range detected (GRD) SAR, categorizes it into eight clusters, each representing specific target characteristics. We adopted two strategies to assess the proposed clustering scheme: 1) cluster zones obtained for diverse land-cover targets spanning continents and 2) temporal changes in cluster zones over rice-cultivated fields at various growth stages. The proposed approach effectively discriminates diverse land-cover targets and distinct growth stages of rice.

This paper explores four distinct target descriptors derived from full-polarimetric Synthetic Aperture Radar (SAR) data. Initially, we define a 2 × 1 real positive target vector by leveraging the mean and standard deviation of complex eigenvalues extracted from the 2 × 2 Sinclair matrix. This vector is the basis for two innovative parameters: 1) the scattering-type parameter, and 2) the scattering asymmetry parameter. Furthermore, we introduce the scattering purity and complexity parameters derived from the mean and standard deviation of the real positive eigenvalues of a Hermitian positive semi-definite 3 × 3 coherency (covariance) matrix. We highlight the efficacy of these parameters by conducting an experimental analysis with several canonical targets. Subsequently, we investigate their performance by thoroughly examining Radarsat-2 full-polarimetric SAR data.

This paper presents an investigation into the use of a random forest (RF) model for retrieving chlorophyll content from Sentinel-3 satellite data. We train various RF regression models on available datasets and introduce a classifier to identify instances where predictions may be inaccurate. This classifier aids in filtering out less reliable cases, enhancing the overall accuracy of our models at the expense of reducing the amount of processed data. Additionally, we optimize the hyperparameters of this hybrid model to improve its performance further. Our findings illustrate the effectiveness of combining regression models with a classifier in environmental remote sensing, offering a promising method for improving the accuracy of satellite-derived chlorophyll measurements.

Synthetic Aperture Radar (SAR) data, particularly for Asian countries, are valuable in monitoring crops. Scattering information extracted from full-polarimetric (FP) SAR data offers exceptional sensitivity to crop water content and geometrical properties. Thus, they are widely used for continuous crop monitoring throughout their growth stages. However, many of these methods are limited to FP SAR data. This study introduces a new approach to obtain scattering power components from SLC and GRD dual-polarimetric (DP) SAR data. We found the scattering powers obtained from the dual-pol SAR data to be sensitive to changes in the crop morphology as it progresses to advanced growth stages.

Characterizing targets with dual-polarimetric (dual-pol) Synthetic Aperture Radar (SAR) data has traditionally relied only on backscatter intensity. However, the limitations of conventional dual-pol parameters, such as the inability to differentiate between orthogonal targets like dihedral and trihedral structures, result in misclassification among diverse targets. This study proposes an innovative target characteristic parameter derived from both dual-pol single-look complex (SLC) and ground range detected (GRD) SAR data that effectively distinguishes between "dihedral-like" and "surface-like" targets, enabling improved characterization of diverse land cover targets.

This study proposes a target characterization technique using a complex scattering trace correlation measure. Several orthonormal projections for characterizing scattering information have been presented in the literature. For instance, one can project a particular target on different polarization bases. In doing so, two possible phenomena can happen: 1) either the structure of the target scattering vector entirely changes from one basis to another or 2) the vector retains some of its inherent characteristics while some get altered. Therefore, the complex correlation between the two projections provides information about the typology of the target present in the scene. Hence, in this study, we derive the amplitude and phase of the complex correlation measure between the linear and circular bases to describe different land cover targets. We have analyzed the proposed technique using the GaoFen-3 single look complex (SLC) image over San Francisco Bay, USA, the RADARSAT-2 SLC image over Vijayawada, India, and the ALOS PALSAR image over the coast of Futtsu, Japan. The results of these tests exhibit significant potential for retrieving comprehensive physical characteristics of the targets within the observed scenes.

Characterization and classification of natural and human-made targets using polarimetric Synthetic Aperture Radar (SAR) data have been widely explored for diverse applications. The Cloude and Pottier scattering-type parameter α has become a standard tool for target characterization and classification. However, it fails to discriminate between all canonical targets. In response to this limitation, this research introduces an alternative scattering-type parameter capable of distinguishing all canonical targets. To achieve this, we first define a real 2 × 1 vector comprising two roll-invariant descriptors derived from the 2 × 2 complex scattering matrix. Subsequently, we calculate the Euclidean norm of this vector relative to a reference real vector associated with a standard dipole scatterer. We leverage this computed Euclidean norm as a key element in formulating our alternate scattering-type parameter. The alternate scattering-type parameter is formulated to effectively characterize a wide spectrum of targets, encompassing both coherent and incoherent. We systematically evaluate the performance of our proposed alternate scattering-type parameter against the well-established Cloude-Pottier α parameter for a diverse set of targets. Additionally, we introduce a target classification framework for dominant scatterers utilizing the vector with two roll-invariant descriptors. To validate our approach, we conducted experiments utilizing two full-polarimetric Earth observation datasets acquired in the C- and L- bands and one full-polarimetric Lunar dataset in the L-band. These datasets were selected to showcase and validate the efficacy of both the alternate scattering-type parameter and the target classification framework.

Target characterization parameters are pivotal in accurately identifying and assessing diverse land cover targets in radar polarimetry. While full-polarimetric (full-pol) synthetic aperture radar (SAR) data offer numerous parameters, characterizing targets with HH-HV or VV-VH dual-polarimetric (dual-pol) SAR data has traditionally relied on backscatter intensity alone due to limited polarimetric information, which leads to ambiguities in characterizing diverse land cover targets. In response to this limitation, this study introduces a novel target characteristic parameter$\overline {\alpha }_{(k)}$derived from dual-pol single-look complex (SLC) and ground range detected (GRD) SAR data that are capable of discriminating between “dihedral-like” (buildings, bridges, ships, and so on) and “surface-like” (water bodies, bare fields, runways, and so on) targets, by employing a data-driven approach. We first derive a set of normalized descriptors independently of SLC and GRD SAR data to formulate two indices that characterize “dihedral-like” and “surface-like” targets. Using the two indices, we derive the dual-pol target characteristic parameter, providing a novel perspective on the intricate nature of radar responses from diverse land cover targets acquired by dual-pol SAR sensors. Furthermore, we employ this parameter to extract three scattering power components: “dihedral-like” ($P_{d-l}$), unpolarized ($P_{u}$), and “surface-like” ($P_{s-l}$) from both dual-pol SLC and GRD SAR data. We assess the proposed target characteristic parameter and scattering power components using Sentinel-1 images acquired over diverse land cover targets spanning six continents. This novel approach enables improved global land cover characterization with operational SAR missions such as Sentinel-1 and upcoming NASA-ISRO SAR (NISAR) missions.

Several orthonormal projections onto various bases have been proposed to analyze Polarimetric Synthetic Aperture Radar (PolSAR) data. These individual projections frequently lead to several additional ambiguities for target scattering characterization. Therefore, considerable confusion is common when using unsupervised classification approaches to classify targets. In this study, we project the scattering information onto several realizations of the normalized scattering configuration without imposing an orthogonality requirement. Using the full-polarimetric AIRSAR data over San Francisco, USA, we first compute the spectrum of the scattering-type parameter, θFP, and subsequently use it to categorize various land-cover targets.

In this paper, we propose a new hybrid methodology to decompose the polarimetric synthetic aperture radar (PolSAR) coherency matrix into sum of three basic scattering mechanisms. The proposed methodology first utilizes a physical scattering model to compute the volume scattering contribution using generalized eigen-decomposition approach. Later, the surface and dihedral scattering powers are computed simultaneously utilizing eigenvalues and dominant eigenvector (α1) of the remainder coherency matrix. We further enhance the performance of the proposed approach by two special unitary transformations which optimize α1parameter by increasing its dominancy towards a single scattering-type phenomenon. We demonstrated the superiority of the proposed two approaches by comparing the experimetal results on a fully polarimetric SAR dataset with recent state-of-the-art techniques.

Aquacultural rafts are important for a large-scale utilisation and conservation of marine resources. Synthetic Aperture Radar (SAR) sensors are viable for mapping and monitoring aquacultural structures. This research offers a novel method that uses dual polarimetric Sentinel-1 and Sentinel-2 data. We project the covariance matrix, obtained from Sentinel-1 onto random normalised scattering configurations. Following this we obtain a spectrum of the dual-polarimetric scattering-type parameter θDP. This θDPspectrum is used with the Random Forest Classifier to classify the rafts from water surface. These classified maps are compared with the conventional eigen decomposition based approach. It is found that the classification accuracy of the proposed technique outperforms the accuracy obtained from the eigen-based technique.

In this work, we propose two parameters in radar polarimetry: (i) scattering purity and (ii) scattering complexity. To obtain these expressions, we use inequalities on the bounds of the condition number in terms of the mean ( $m$ ) and standard deviation ( $s$ ) of the eigenvalues of a Hermitian positive semi-definite matrix. The polarimetric scattering purity characterizes the overall polarization structure in the scattered wave. In contrast, the polarimetric scattering complexity describes the mixture of orthogonal polarized pure components in the scattered wave. We discuss the variability of these metrics over various land cover classes using full-polarimetric C-band Synthetic Aperture Radar (SAR) data. We compare their spatial variations over the ocean surface, built-up areas, and vegetation. We notice significant differences in the purity and complexity characteristics across a wide range of targets in the scene.

Polarimetric Synthetic Aperture Radar (SAR) data has been extensively used to estimate soil permittivity because of its high sensitivity to the dielectric properties of the target. However, the presence of vegetation cover induces bias in the permittivity estimates. This work utilizes the scattering-type parameters: alpha$(\overline{\alpha})$and theta$(\theta_{\text{FP}})$to estimate soil permittivity using the X-Bragg as the dominant surface scattering model. A theoretical study ascertains that the recently proposed$\theta_{\text{FP}}$is fairly robust towards the depolarizing component in the X-Bragg model. Hence, it is expected to produce better inversion accuracy. This study analyzes major phenology stages of Canola using the UAVSAR full-pol SAR data and the ground measurements acquired during the SMAPVEX12 campaign over Manitoba, Canada. The proposed method achieved an RMSE of 5.9 for soil permittivity with a Pearson coefficient,$r=0.83$. Further, the temporal trend of the soil permittivity estimates also agrees with in-situ measurements for the entire timeframe.

In continuance to quad-pol SAR data analysis, Cloude proposed the eigenvalue-eigenvector decomposition of dual-pol 2 x 2 covariance matrix to compute the target characterization parameter, ᾱ. In this study, we explicitly demonstrate an alternative approach to compute the dual-pol ᾱ using De-schamps parameters defined using a spherical triangle structure on the Poincaré sphere. The geometrical construction provides inherent visual information in terms of the Stokes vectors for diverse targets characterized by HH-HV and VV-VH data. This technique produces the same result as proposed by Cloude. We utilized canonical targets and airborne SAR data to demonstrate the results with the proposed approach.

Built-up area (BA) mapping is vital for understanding the effect of the urban regions on the environment, thereby supporting sustainable development. This study proposes a new dual-pol radar built-up area index (DpRBI) to detect the BA using Sentinel-1 SAR data. The DpRBI formulation is based on the three Stokes vector elements of the scattered wave derived from the 2 × 2 covariance matrix C2. This study uses the Sentinel-1 SAR data sets over Milan, Italy and Barcelona, Spain to map the BA using DpRBI. The overall accuracy of the BA extracted using the proposed technique was found to be 84.19% and 87.95% over Milan and Barcelona, respectively. It is noteworthy that even relatively small low-density BA is precisely classified using the proposed built-up index.

This study proposes the spectrum analysis of the scattering-type parameter, θFP, to characterize different land cover targets. Many orthonormal projections of the scattering information onto distinct polarization bases have been proposed in the literature. However, these conventional orthonormal basis projection techniques often provide various target characterization ambiguities and classification. In this work, we propose projecting the target coherency matrix onto several random realizations of the normalized scattering configuration without restriction to the orthogonality constraint. This unique approach helps enhanced target characterization from polarimetric SAR data. We show the efficacy of our proposed technique over different land cover types using the C-band RADARSAT-2 data over SF and the L-band ALOS-2 data over Mumbai.

The generalized degree of polarimetric purity is a vital descriptor widely studied and interpreted for electromagnetic wave characterization. It is invariant under the rotation of the reference frame. In this work, we first propose an alternate expression of this purity measure using the mean$(m)$and standard deviation$(s)$of the real positive eigenvalues of a Hermitian positive semidefinite matrix. We then use this expression to propose a polarimetric scattering purity and scattering complexity measure. To obtain these expressions, we use certain inequalities on the bounds of the condition number for Hermitian positive definite matrices defined in terms of$m$and$s$. The polarimetric scattering purity parameter characterizes the overall polarization structure in the scattered wave. In contrast, the polarimetric scattering complexity parameter describes the mixture of orthogonal polarized pure components in the scattered wave. First, we demonstrate the two proposed measures by analyzing two cases: 1) multiple scattering and 2) a mixture of canonical targets. Then, we utilize full-polarimetric C- and L-band synthetic aperture radar (SAR) data to describe the variation of these measures over various land cover classes. We compare their spatial variations over the ocean surface, built-up areas, and vegetation. We observe notable contrasts in the purity and the complexity parameters over a diverse mixture of targets in the scene. Finally, we critically interpret the variation of the two measures over the temporal scene of rice crop acquired by C-band full-polarimetric SAR data. These analyses affirm the importance of these measures for explicit target characterization. The open-source version of the code is available athttps://github.com/Subho07/scattering-purity-and-complexity

Soil permittivity estimation using Polarimetric Synthetic Aperture Radar (PolSAR) data has been an extensively researched area. Nonetheless, it provides ample scope for further improvements. The vegetation cover over the soil surface leads to a complex interaction of the incident polarized wave with the canopy and subsequently with the underlying soil surface. This paper introduces a novel methodology to estimate soil permittivity over croplands with vegetation cover using the full and compact polarimetric modes. The proposed method utilizes the full and compact polarimetric scattering-type parameters, θFPand θCP, respectively. These scattering type parameters are a function of the soil permittivity and the Barakat degree of polarization. The method considers the X-Bragg scattering model for the soil surface. In particular, these scattering-type parameters explicitly account for the depolarizing structure of the scattered wave while characterizing targets. Thus, the depolarization information in terms of surface roughness in the X-Bragg model gets inherent importance while using θFPand θCP, unlike existing scattering-type parameters. Therefore, the proposed technique enhances the expected value of the inversion accuracies. This study validated the major phenology stages of four crops using the UAVSAR full-pol and simulated compact pol SAR data and the ground truth data collected during the SMAPVEX12 campaign over Manitoba, Canada. The proposed method estimated permittivity with an RMSE of 2.2 to 4.69 for FP and 3.28 to 5.45 for CP SAR data along with a Pearson coefficient,r≥ 0.62.

Accurate and high-resolution spatio-temporal information on wheat growth is an essential factor for agronomic management and grain yield estimation. In this study, we propose a new vegetation descriptor from the Sentinel-1 Synthetic Aperture Radar (SAR) GRD data for monitoring the growth stages of wheat. We also assess the performance of the proposed vegetation descriptor for estimating wheat biophysical parameters: Plant Area Index (PAI), Dry Biomass (DB), and Vegetation Water Content (VWC) over the Soil Moisture Active Passive Validation Experiment 2016 (SMAPVEX16-MB) test site in Manitoba, Canada. The proposed vegetation descriptor produced good correlation$(R^{2})$with the biophysical parameters of wheat: 0.63 (PAI), 0.64 (DB), and 0.57 (VWC) compared to$\sigma_{\text{VH}}^{\mathrm{o}}/\sigma_{\text{VV}}^{\mathrm{o}}$and the dual-pol Radar Vegetation Index (RVI).

Built-up area extraction from remote sensing images is essential for urban planning, disaster management and industrial development. In this study, we propose two built-up area indices for full (FP) and dual (DP) polarimetric Synthetic Aperture Radar (SAR) data. The built-up area index for FP SAR data is based on the dominant scattering mechanism of the electromagnetic (EM) waves from urban targets. In contrast, the built-up area index for DP SAR data is based on the scattering reflection symmetry property. The two proposed indexes are validated with full and extracted dual pol (VV-VH) scenes of a C-band RADARSAT-2 SAR data over urban San-Francisco. They show encouraging results in detecting urban areas within a SAR resolution cell. The overall accuracy of delineating built-up area is 84.2% for FP SAR data and 79% for DP SAR data.

Target decomposition methods for polarimetric Synthetic Aperture Radar (PolSAR) data aim at explaining the scattering information. In this regard, several conventional model-based methods use scattering power components to analyze polarimetric SAR data. However, the typical hierarchical process to enumerate power components uses various branching conditions, leading to several limitations. This study uses the 3D Barakat degree of polarization (DoP) to obtain the scattered wave polarization state. We employ the DoP to obtain the even bounce, odd-bounce, and diffuse scattering power components. Besides, we propose a measure of target scattering asymmetry, which is subsequently utilized to obtain the helicity power. All the power components in our approach are roll-invariant and non-negative, and the decomposition preserves the total power. We utilized C-band full polarimetric RADARSAT-2 data to show the effectiveness of the proposed decomposition.

In contrast to the widely used van Zyl received wave polarimetric signature, the Touzi scattered wave signature in term of the total power ($S$0), and the degree of polarization ($p$) is also helpful for target characterization. Although, the van Zyl polarimetric signature includes the contribution of So, and p, the explicit consideration of the two scattered wave parameters (i.e., independent of the received wave polarization basis) can provide additional information about the target. Hence, in this study, we have used both the van Zyl received, and Touzi scattered wave information to characterize scattering from Paddy at a particular phenological stage with C- and L-band full polarimetric SAR data.

In this study, we propose a sequence-to-sequence neural network architecture to jointly estimate the plant area index (PAI) and wet biomass of canola and soybean. The PAI and wet biomass have considerable importance for crop growth stage mapping and monitoring. RADARSAT-2 quad-pol data along within situmeasurements of canola and soybean obtained from the SMAPVEX16 campaign over Manitoba, Canada, are utilized for evaluating the efficiency and accuracy of the proposed estimation methodology. The analysis indicates promising results for the two crops with a correlation coefficient$(r)$in the range of 0.69–0.87. The results also confirm intercorrelation between the PAI and wet biomass for canola and soybean.

In radar polarimetry, incoherent target decomposition techniques help extract scattering information from polarimetric synthetic aperture radar (SAR) data. This is achieved either by fitting appropriate scattering models or by optimizing the received wave intensity through the diagonalization of the coherency (or covariance) matrix. As such, the received wave information depends on the received antenna configuration. Additionally, a polarimetric descriptor that is independent of the received antenna configuration might provide additional information which is missed by the individual elements of the coherency matrix. This implies that existing target characterization techniques might neglect this information. In this regard, we suitably utilize the 2-D and 3-D Barakat degree of polarization which is independent of the received antenna configuration to obtain distinct polarimetric information for target characterization. In this study, we introduce new roll-invariant scattering-type parameters for both full-polarimetric (FP) and compact-polarimetric (CP) SAR data. These new parameters jointly use the information of the 2-D and 3-D Barakat degree of polarization and the elements of the coherency (or covariance) matrix. We use these new scattering-type parameters, which provide equivalent information as the Cloude α for FP SAR data and the ellipticity parameter χ for CP SAR data, to characterize various targets adequately. Additionally, we appropriately utilize these new scattering-type parameters to obtain unique non-model-based three-component scattering power decomposition techniques. We obtain the even-bounce, and the odd-bounce scattering powers by modulating the total polarized power by a proper geometrical factor derived using the new scattering-type parameters for FP and CP SAR data. The diffused scattering power is obtained as the depolarized fraction of the total power. Moreover, due to the nature of its formulation, the decomposition scattering powers are non-negative and roll-invariant while the total power is conserved. The proposed method is both qualitatively and quantitatively assessed utilizing the L-band ALOS-2 and C-band Radarsat-2 FP and the associated simulated CP SAR data.

The scattering information from targets is either estimated by fitting suitable scattering models or by optimizing the received wave intensity through the diagonalization of the coherency (or covariance) matrix. In this study, a new roll-invariant scattering-type parameter is introduced, which jointly uses the 3D Barakat degree of polarisation and the elements of the coherency matrix as the received wave information from full-polarimetric (FP) SAR data. This scattering-type parameter is analogous to that of Cloude-Pottier's α for FP SAR data. Furthermore, we utilize this new scattering-type parameter to obtain a unique non-model based three-component scattering power decomposition technique. The powers obtained from the proposed technique are guaranteed to be non-negative, with the total power being conserved. The proposed method is qualitatively and quantitatively assessed using the L-band ALOS-2 and the C-band Radarsat-2 FP SAR data.

In this study, we propose a new vegetation index (DpRVI) for dual polarimetric synthetic aperture radar (SAR) data. The evaluation of this new index is performed with a particular attention towards the preparation of the NASA-ISRO SAR (NISAR) L-band system science objective. The proposed vegetation index is derived for two dual-pol (HH-HV and VV-VH) modes obtained through a simulation from L-band full-pol UAVSAR data. Time-series simulated NISAR data are obtained from the UAVSAR data acquired during the SMAPVEX12 campaign over the CAL/VAL test site in Winnipeg (Canada), to assess the proposed vegetation index. The temporal trend of DpRVI follows the growth stages of canola with a promising correlation of DpRVI with several biophysical variables. Correlation analysis indicates that DpRVI derived for VV-VH mode correlates better with the canola biophysical parameters than the HH-HV mode.

This work deals with the classification of wheat phenology by regressing the synthetic aperture radar (SAR) backscatter coefficients (VV, VH) to vegetation water content (VWC) and plant area index (PAI) through a representation learning network. The representation network architecture consists of a pair (VV, VH) of two regression layers (VWC, PAI) which finally converge to a classification (crop phenology) layer. The study was conducted with the Sentinel-1 C-band SAR data acquired during the SMAPVEX16 campaign in Manitoba, Canada. Using this framework, the wheat phenology was classified to an accuracy of 86.67%. However, in comparison, the classification accuracy reduced by ~ 20% while using only the backscatter coefficients of (VV, VH) polarization channels. The results obtained from this study justifies the potential of using a representation learning scheme for crop phenology classification with SAR data.

In this study, we propose a vegetation index for compact polarimetric (CP) SAR data (CpRVI) using a geodesic distance between two Kennaugh matrices projected on a unit sphere, as given in Ratha et. al. This distance is utilized to compute a similarity measure between the observed Kennaugh matrix and the Kennaugh matrix of an isotropic depolarizer. The proposed vegetation index is compared with the Radar Vegetation Index (RVI) obtained from RADARSAT-2 full-polarimetric SAR data. We use a time series of simulated compact-pol SAR data (RH-RV) obtained from the RADARSAT-2 data acquired during the SMAPVEX16-MB campaign over the Joint Experiment for Crop Assessment and Monitoring (JECAM) test site in Manitoba, Canada to assess the proposed vegetation index. Among the various crops grown in this region, only the growth stages of soybean are analyzed in this work. The temporal trend of CpRVI follows the growth stages of soybean. Regression analysis shows that CpRVI correlates better with the Plant Area Index (PAI) and Vegetation Water Content (VWC) than RVI.