A New Precipitable Water Vapor STARMA Model Based on Newton’s Method

The STARMA (space-time autoregressive moving average) model is introduced in 2002–2008 monthly PWV fitting and forecast. To enhance the model’s ability of dealing with satellite remote sensing raster data, this article extends the parameter estimation process in the STARMA model by augmenting the Newton’s method to high dimensions for solving system of nonlinear equations, and the process of parameter estimation is elaborated. This operation is validated by real data experiment results. The confirmation results of this method reveals that the STARMA model has good accuracy in both fitting and predicting.

[1]  J. K. Ord,et al.  Space-time modelling with an application to regional forecasting , 1975 .

[3]  P. Pfeifer,et al.  Stationarity and invertibility regions for low order starma models , 1980 .

[4]  Marta E. Zorrilla,et al.  A new image prediction model based on spatio-temporal techniques , 2007, The Visual Computer.

[5]  B. Epperson,et al.  Spatial and space-time correlations in systems of subpopulations with genetic drift and migration. , 1993, Genetics.

[6]  T. Herring,et al.  GPS Meteorology: Remote Sensing of Atmospheric Water Vapor Using the Global Positioning System , 1992 .

[7]  Noel A Cressie,et al.  Spatio-Temporal Statistical Modeling of Livestock Waste in Streams , 1996 .

[8]  J. Oeppen.  The identification of regional forecasting models using space-time correlation , 1975 .

[9]  Leo A. Aroian,et al.  Time series in m dimensions: Autoregressive models , 1980 .

[10]  Rodrigo A. Garrido,et al.  Spatial interaction between the truck flows through the Mexico–Texas border , 2000 .

[11]  Leo A. Aroian.  Time series in m-dimensions definition, problems and prospects , 1980 .

[12]  General considerations and interrelationships between ma and ar models, time series in m dimensions, the arma model , 1980 .

[13]  C. Granger,et al.  Aggregation of Space-Time Processes , 2001 .

[14]  Yiannis Kamarianakis,et al.  Space-time modeling of traffic flow , 2002, Comput. Geosci..

[15]  Michael T. Owyang,et al.  The Information Content of Regional Employment Data for Forecasting Aggregate Conditions , 2004 .

[16]  Leo A. Aroian,et al.  Moving average models—time series in m-dimensions , 1980 .