Cheryl Bertoia

Learn More
We present an intelligent system for satellite sea ice image analysis named Advanced Reasoning using Knowledge for Typing Of Sea ice (ARKTOS). ARKTOS performs fully automated analysis of synthetic aperture radar (SAR) sea ice images by mimicking the reasoning process of sea ice experts. ARKTOS automatically segments a SAR image of sea ice, generates(More)
ARKTOS is a fully automated intelligent system that classifies sea ice and that is now being used by the U.S. National Ice Center (NIC) for daily operations related to the NIC’s task of mapping the ice covered oceans. In this paper we describe the process of taking a research project and transitioning it to an operational environment. We discuss the(More)
In this paper we describe ARKTOS, a system that uses a Dempster-Shafer rule base to integrate data from multiple sources in order to classify sea ice. ARKTOS analyzes SAR imagery to generate a feature set that describes the image. Next it fuses the SAR-extracted features with digital grid climatology data and sea ice concentration data extracted from SSM/I(More)
Ship and iceberg drifts, along with data from modern satellite-tracked drifting buoys, portray generally northward flow in the southwest Ross Sea. Less is known, however, about the ocean variability in this region. Here we use Defense Meteorological Satellite Program (DMSP) Operational Linescan System (OLS) imagery to describe a cyclonically rotating gyre(More)
ARKTOS (Advanced Reasoning Using Knowledge for Typing of Sea Ice) is a fully automated intelligent sea ice classification system. ARKTOS is in use at the U.S. National Ice Center (NIC) for daily operations related to the NIC’S task of mapping the ice covered oceans. ARKTOS incorporates image processing, input from ancillary data, and artificial intelligence(More)
The United States National Ice Center (NIC) provides weekly ice analyses of the Arctic and Antarctic using information from ice reconnaissance, ship reports and high-resolution satellite imagery. In cloud-covered areas and regions lacking imagery, the higher-resolution sources are augmented by ice concentrations derived from Defense Meteorological Satellite(More)
identify sea ice features in SAR imagery [2,3]. Of particular ARKTOS is a fully automated intelligent system that interest to the NIC was a system to classify winter sea ice into classifies sea ice and that is now being used by the U.S. three major classes using dynamic thresholding and expert, National Ice Center (NIC) for daily operations related to the(More)
A new SSM/I algorithm is described that is based on near real-time data fusion with portions of operational ice charts derived from RADARSAT, OLS or AVHRR data. The aim of this is to enable parts of the ice chart where there is no cloud-free imagery or SAR data to be completed using an SSM/I algorithm that is tuned to the region and time associated with the(More)
A new SSM/I algorithm is described that is based on near Previous NIC chart Climatology real-time data fusion with portions of operational ice charts derived from RADARSAT, OLS or AVHRR data. The aim Weather Forecast model of this is to enable parts of the ice chart where there is no Preparation cloud-free imagery or SAR data to be completed using an SSM/I(More)
  • 1