Climate modelling and high-latitude marine navigation require improved information on sea-ice floe extents and dynamics. New satellite sensors provide raw data of this nature but the volume of information makes human analysis impractical. To address this problem, a software system for automatic tracking of sea-ice floes in satellite imagery has been designed and evaluated. Using a recurrent neural network model, experiments were conducted to discover suitable design parameters. Simulated imagery time-sequences of increasing complexity were produced to train successive models. The networks produced were evaluated based on performance and reliability. A small-scale working system, able to map multiple input features in image sequences to Cartesian coordinates, was produced. Results show that a recurrent neural network is suitable for the tracking task and has advantages in robustness and speed over other approaches. Recurrency (feedback) was found to be crucial in achieving good performance.

A sea ice model developed by W. D. Hibler (1979) was applied to the Lancaster Sound/Barrow Strait channel in an effort to simulate the observed ice environment. The simulation covered a ten month period, from October 1985 until August 1986. The impact of atmospheric and oceanographic forcing on the development of characteristic ice features that develop seasonally within the channel was examined. The importance of the ice interaction component of the model when simulating a restricted channel ice environment was also examined. The model was able to simulate regional scale processes and conditions within the channel. Small scale localised processes and conditions which control the spatial variability and complexity of the ice regime were not accurately reproduced. Simulation results provided insights into the effect and importance of both the model and geophysical variables examined. The study highlighted concerns that need be addressed in future modelling work in the Lancaster Sound/Barrow Strait channel.

No description available.

No description available.

No description available.

No description available.