Arctic sea ice drifts under the influence of winds and ocean currents. Ice motion is important - up to several kilometers a day. Tracking the movement of sea ice can be applied to different research questions, including the transition from older sea ice to a younger seasonal ice pack, the transport of ice-rafted sediments, or pollutants in the context of an oil spill, and the risk assessment associated with navigation and marine operations in the Arctic. In the McGill sea-ice group, we use ice motion tracking to understand how the dynamics of sea ice can be used as a seasonal predictor for the summer ice conditions. As sea ice experiences convergent motion, it ridges and forms thick piles of sea ice, or to the contrary, divergent ice motion leads to the formation of open water areas or leads. These changes in the ice thickness distribution of the pack ice consequently influence the melt of sea ice in the summer.

Information about the velocity of sea ice is required for performing sea ice tracking; and in a perfect world, we would like this information to be available everywhere in the Arctic in space and time. The most reliable information about ice motion comes from passively drifting buoys that were deployed in the Arctic over the last few decades. These GPS-equipped instruments provide a very precise measure of ice motion, but unfortunately offer limited spatial coverage. Remote sensing offers a better spatial coverage; image processing on sequences of satellite imagery can be used to reconstruct ice motion. Still, these satellite-derived ice motion vectors may not be available all year long due to the sensitivity of the different instruments. When neither of these two observational sources of ice motion is available, we need to make a best estimate of the sea ice drift to fill the gaps. As the atmospheric forcing is one of the main drivers of the circulation of sea ice, we can use information about the winds for estimating the sea ice drift.

In this challenge, your task is to use an AI approach for building the model that best reproduces the buoy drift, based on the wind fields. For doing so, you will be provided with a forty years data record of drifting Arctic buoys, and co-located winds, and additional environmental parameters (such as sea ice conditions). If successful, your model could be used to produce sea ice motion estimates that will be combined to other observations of sea ice motion and help the polar research community.

Built With

Share this project:

Updates