Seasonal Prediction of Arctic Summer Sea Ice Concentration from a Partial Least Squares Regression Model

The past decade has witnessed a rapid decline in the Arctic sea ice and therefore raised rising demand for forecasts. In this study, based on an analysis of long-term summer concentration (SIC) global surface temperature (SST) datasets, physical–empirical (PE) partial least squares regression (PLSR) model is presented order to predict SIC variability around key areas shipping route. First, main SST modes closely associated with anomalies are found by PLSR method. Then, prediction reasonably established basis these modes. We investigate performance PE examining its reproducibility seasonal variability. Results show that proposed turns out promising reliability accuracy change, thus providing reference further study climate change.