Polarimetric synthetic aperture radar remote sensing extracts the information about the target using decomposition models to separate the polarimetric information into single-bounce (contributed by smooth surfaces), double-bounce (contributed by urban structure), and volume (mainly due to vegetation cover) scattering components. The penetration capacity of the electromagnetic wave into the surface increases with the decrease in its frequency. This study explores and compares the polarimetric decomposition models for scattering-based characterization of land use and cover using multifrequency spaceborne synthetic aperture radar sensor datasets that were acquired over San Francisco, CA, USA. The present work compares the scattering parameters of coherent (Pauli), roll-invariant (Barnes), eigenvalue–eigenvector (Cloude), and compact-polarimetric (Raney) decomposition modeling approaches for scattering-based characterization of urban structures, waterbody, and vegetation cover. The land use/cover classification was performed based on the scattering response of the scatterers using a support vector machine classifier. The outputs of the classification approach on multisensor, multifrequency, and multi-polarization polarimetric synthetic aperture radar data have shown reasonable accuracy in classifying the land use and land cover. The decomposition models fail to characterize the oriented urban structures that cause misclassification of urban structures as vegetation. The higher-order roll-invariant decomposition modeling approaches could improve the interpretation of different targets and accuracy in land use and land cover classification.

The polarimetric Synthetic Aperture Radar (SAR) data sets have been widely exploited for land use land cover (LULC) classification due to their sensitivity to the structural and dielectric properties of the imaging target. In this study, the potential of fully polarimetric L‐ and S‐band Airborne SAR (LS‐ASAR) data sets were explored for the machine‐learning‐based classification of Urban, Vegetation, Waterbody, and Open Ground. This work was done by utilizing dual‐frequency L‐ and S‐band airborne data of Santa Barbara, California, USA, acquired under the Airborne SAR (LS ASAR) campaign, a precursor airborne mission to the space‐borne NASA‐ISRO (NISAR) mission. The LS‐ASAR polarimetric information was utilized for LULC classification using the SVM classifier. The roll‐invariant Barnes, and eigenvalue/eigenvector‐based Cloude and H/A/Alpha decomposition were implemented to retrieve the scattering parameters. The backscatter response of classes was studied, and separability analysis was done to reduce the misclassification error between six class pairs‐ Vegetation—Urban, Vegetation—Waterbody, Vegetation—Open Ground, Urban—Waterbody, Urban—Open Ground, and Water—Open Ground. The decomposition models failed to achieve the desirable separability index for all six class pairs; consequently, the classification of Barnes, Cloude, H/A/Alpha decomposition showed misclassification between vegetation‐urban class, and waterbody‐open ground class for both L‐ and S‐band data sets. The effort was made toward improving the classification accuracy by integrating the roll‐invariant and eigenvalue‐eigenvector scattering parameters of the multifrequency L‐ and S‐band data set. This method presented the desirable separability index for all class‐pair; eventually highest classification accuracy was achieved i.e. 93.35% (kc ${k}_{c}$ = 0.91) by significantly reducing the misclassification error between class pairs.