The Information Consistency Between Full- and Improved Dual-Polarimetric Mode SAR for Multiscenario Oil Spill Detection

Detecting marine oil spills is vital for protecting the marine environment, ensuring maritime traffic safety, supporting marine development, and enabling effective emergency response. The dual-polarimetric (DP) synthetic aperture radar (SAR) system represents an evolution from single to full polarization (FP), which has become an essential tool for oil spill detection with the growing availability of open-source and shared datasets. Recent research has focused on enhancing DP information structures to better exploit this data. This study introduces improved DP models' structure with modified the scattering vector coefficients to ensure consistency with the corresponding components of the FP system, enabling comprehensive comparison and analysis with traditional DP structure, includes theoretical and quantitative evaluations of simulated data from FP system, as well as validation using real DP scenarios. The results showed the following: (1) The polarimetric entropy <i>H_L</i> obtained through the improved DP scattering matrix <i>C_L</i> can achieve higher information consistency results closely aligns with FP system and better performance, compared to the typical two DP scattering structures. (2) For multiple polarimetric features from DP scattering matrix (both traditional feature and combination feature), the improved DP scattering matrix <i>C_L</i> can be used for oil spill extraction effectively with prominent results. (3) For oil spill extraction, the polarimetric features-based <i>C_L</i> tend to have relatively high contribution, especially the <i>H_A</i> feature combination, leading to substantial gains in improved classification performance. This approach not only enriches the structural information of the DP system under VV-VH mode but also improves oil spill identification by integrating multi-structured DP features. Furthermore, it offers a practical alternative when FP data are unavailable.