Information on ice cover extent, distribution, concentration, ice surface temperature and other physical parameters of the ice pack is needed in numerical weather prediction, ship navigation, water management, and regional/global climate change impact assessment. Ice cover is also a sensitive indicator of climate variations. Ability of satellites to provide global observations at high temporal frequency has made them the primary tool for the ice cover monitoring. The main objective of this research is to explore the potentials of mapping ice cover with the future GOES-R ABI and to develop an automated ice-mapping algorithm which would make maximum use of ABI’s improved observing capabilities and its frequent observation will provide an extreme enhanced temporal variability of scene response to improve image classification. Data collected by SEVIRI instrument onboard of the Meteosat Second Generation (MSG) satellite have been used as a prototype. The Northern region of the Caspian Sea has been selected for algorithm development and calibration. The approach used in the algorithm development includes daily cloud-clear image compositing as well as pixel-by-pixel image classification using spectral criteria. Available spectral channels (reflectance and temperature) have been tested and used in a statistical-based approach to accurately discriminate between water, cloud and ice pixels. To assess the accuracy of ice mapping algorithm and maps, the produced ice maps over Caspian Sea derived with the automated algorithm were compared with interactive snow/ice charts produced with NOAA Interactive Multi-sensor Snow and Ice Mapping System (IMS). The results are promising and an additional screening is undergoing further research in order to reduce some remaining confusions related to water properties and presence of fractional ice.