ERS-2 SAR image analysis for sea ice classification in the marginal ice zone

The possibility to distinguish between different sea ice types in the marginal ice zone in the Greenland Sea using ERS-2 SAR is investigated. Statistical, textural and spectral features derived from ERS-2 SAR images and ice concentrations from 85 GHz SSM/I data are analyzed using learning vector quantization. The proposed method is useful for resolving ambiguities arising from frost flowers or pancake ice with very high backscatter values similar to the wind roughened sea surface.