Robustness of SAR Sea Ice Type Classification Across Incidence Angles and Seasons at L-Band

In recent years, space-borne synthetic aperture radar (SAR) polarimetry has become a valuable tool for sea ice type retrieval. L-band SAR proven to be sensitive toward deformed and is complementary compared with operationally used C-band classification during the early advanced melt seasons. Here, we employ an artificial neural network (ANN)-based algorithm on comprehensive data set of ALOS-2 PALSAR-2 fully polarimetric images acquired range incidence angles different environmental conditions. The variability within means that it ideal making novel assessment robustness classification, investigating intraclass variability, seasonal variations, angle effect results. coincide two Arctic campaigns in 2015: Norwegian Young Sea Ice Cruise 2015 (N-ICE2015) Polarstern’s (PS92) Transitions Seasonal Zone (TRANSSIZ). We find essential take into account seasonality when establishing training machine learning-based algorithms though moderate differences are possible accommodate by classifier dry cold winter season. also conclude dependence backscatter given consistent regions.