G-STAR Model for Forecasting Space-Time Variation of Temperature in Northern Ethiopia

Authors : Mulugeta Aklilu ZEWDİE, Gebretsadik G WUBİT, Amare W AYELE

Pages : 9-19

Doi:10.34110/forecasting.437599

View : 16 | Download : 15

Publication Date : 2018-09-01

Article Type : Research Paper

Abstract :Among many indicators of climate change, the temperature is a key indicator to take remedial action for world global warming. This finding provides application of space-time models for temperature data, which is selected in three meteorology stations insert ignore into journalissuearticles values(Mekelle, Adigrat and Adwa); of Northern Ethiopia. The objectives of this research are to see the space-time variations of temperature and to find better forecasting model. The steps for building this model starting from order selection of space and autoregressive order, parameters estimation, a diagnostic check of errors and finally forecasting for the long term. The preliminary model is identified by VAR insert ignore into journalissuearticles values(vector autoregressive); model and tentatively selects the order by using MIC insert ignore into journalissuearticles values(minimum information criteria); and uses the autoregressive order for the model and fixes the spatial effect, model parameters are estimated using the least square method. Weighted matrix computed by using queen contiguity criteria. It is found that the model STARinsert ignore into journalissuearticles values(1,1); and GSTARinsert ignore into journalissuearticles values(1,1); are two options, finally the best-fitted model is GSTARinsert ignore into journalissuearticles values(1,1); which has high forecasting performance and smallest RMSEF. The outcome of the forecast indicated that in northern Ethiopia, the weather conditions especially temperature of future is increasing trend in dry seasons in all 3 stations in similar fashion but more consistent and has less variation across the region, and less consistent and high variation within the region and the researcher found that spatial effect has high impact on prediction of models.
Keywords : Temperature, STAR GSTAR, Forecasting