The Arctic sea ice is declining in extent, volume and thickness. With this decline comes an increased interest in the two main Arctic shipping routes: Canada’s Northwest Passage (NWP) and Russian Northern Sea Route (NSR). The NWP is the most direct route between Asia and the East coast of North America. Some routes are up to 40% shorter than those using the Suez Canal.
With commercial and contractual implications, Arctic shipping route access needs to be predictable with sufficient lead time to allow optimization. This paper presents a methodology for forecasting the timing and length of the open-water season (by determining freeze-up and break-up dates) on regional scales at key locations in the NWP along with examples of applications.
A suite of statistical models were developed to forecast the timing and length of the open-water season at key locations within the NWP, using a multi-node based quadratic discriminant (QD) approach. Forecasts are feasible up to four weeks in advance. Ensembles of QD models were built for key regions using a feature selection method to select an optimized set of input parameters to better discriminate between two states (i.e., ice or open-water). The set of available features used included observed and modeled environmental, oceanographic and atmospheric parameters. Results of models with a 28-day forecast horizon show that over 59% of predictions for break-up and 79% of predictions for freeze-up fall within a ±4-day range, which is the error on the reference dates derived from the weekly CIS ice charts.
