Title: Inference for Spatio-Temporal Changes of Arctic Sea Ice
Arctic sea-ice extent has been of considerable interest to scientists in recent years, mainly due to its decreasing trend over the past two decades. In this talk, a hierarchical spatio-temporal generalized linear model (GLM) is fitted to binary Arctic-sea-ice data, where data dependencies are introduced in the model through a latent dynamic spatio-temporal linear mixed-effects model. By using a reduced number of spatial basis functions, the resulting model achieves both dimension reduction and non-stationarity for spatial fields at different time points. An EM algorithm is used to estimate model parameters, and a (empirical) hierarchical-statistical-modelling approach is used to obtain the predictive distribution of the latent spatio-temporal process. Spatial binary Arctic-sea-ice data for each September over the last 20 years are analysed in this way. Maps of predicted water-ice potential and their uncertainties and posterior summaries show the changes in Arctic sea-ice cover during this relatively short time period.