Spatio-Temporal Dynamic Fields Estimating and Modeling of Missing Points in Data Sets Using a Flexible State-Space Model

Modelling and estimating spatio-temporal dynamic field are common challenges in much applied research. Most existing interpolation methods require massive prior calculations consistent observational data, resulting low efficiency. This paper presents a flexible state-space model for iteratively fitting time-series from random missing points data sets, namely Flexible Universal Kriging model(FUKSS). In this work, recursive method similar to Kalman filter is used estimate the time-series, avoiding problem of increasing caused by space-time extension. Based on statistical characteristics Kriging, introduces spatial selection matrix make different observation state vectors identical at times, which solves reduces calculation complexity. addition, linear autoregressive introduced solve that universal cannot predict. We have demonstrated superiority our comparing it with through experiments, verified effectiveness practical cases.