Active and passive microwave data fusion based sea ice concentration estimation

In this abstract, a decision-level fusion method by utilizing Synthetic Aperture Radar (SAR) and passive microwave remote sensing data for sea ice concentration estimation is investigated. In the proposed method, the merits from passive microwave data and SAR data are both taken into consideration. For SAR imagery, incident angles and azimuth angles were used to correct backscattering values from slant range to ground range in order to improve geocoding accuracy. Within a pixel, sea ice concentration from passive microwave data and sea ice category label derived from conditional random fields (CRF) framework in SAR imagery are calibrated under the least distance protocol. Then, posterior probability distribution between category label derived from SAR imagery and passive microwave sea ice concentration product is modeled and integrated under the Bayesian network. In the posterior probability estimation procedure, final sea ice concentration is obtained using maximum a posteriori probability (MAP) criterion, which equals to minimize the cost function by nonlinear iteration method. We construct the constrained least-squared method to derive sea ice concentration from passive microwave data. Sea ice type category is exploited by the proposed CRF based strategies including the mixed statistical conditional random fields (MSTA-CRF) and fully connected. In the experiments, results show that the proposed algorithm outperform both the concentration from SAR and the passive microwave product. Especially, the proposed fusion method can improve the accuracy of passive sea ice concentration products and reduce the uncertainty around the ice edge and thin ice area.