Abstract: To investigate the feasibility of using compact polarimetric synthetic aperture radar (SAR) as an alternative to fully polarimetric SAR for oil spill detection and to determine the impact of different polarization parameters on the accuracy of oil spill detection. To this end,a SAR oil spill detection algorithm based on convolutional neural networks (CNN) is employed. This algorithm extracts polarization parameters from both fully polarimetric and derived compact polarimetric SAR data to study their impact on the classification accuracy of oil spills. Furthermore,the impact of different SAR data preprocessing steps on the accuracy of oil spill detection is evaluated. The results demonstrate that the linear stretching method can effectively enhance the accuracy of oil spill detection. Concerning the selection of polarization parameters,the polarization entropy H achieved the highest classification accuracy in both fully polarimetric and compact polarimetric modes,with a classification accuracy of 0.972 for fully polarimetric and 0.978 for compact polarimetric. This demonstrates the potential of using compact polarimetric SAR for oil spill detection and its promising application prospects.

Key words: marine oil spill, synthetic aperture radar, compact polarization, polarization decomposition, convolutional neural network