G-STAR Model for Forecasting Space-Time Variation of Temperature in Northern Ethiopia
Journal Title: Turkish Journal of Forecasting - Year 2018, Vol 2, Issue 1
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 (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 (vector autoregressive) model and tentatively selects the order by using MIC (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 STAR(1,1) and GSTAR(1,1) are two options, finally the best-fitted model is GSTAR(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.
Authors and Affiliations
Mulugeta Aklilu Zewdie, G. G. Wubit, A. W. Ayele
Keywords
Related Articles
- EP ID EP462695
- DOI -
- Views 101
- Downloads 0
A Fuzzy Modelling Approach to Robust Design via Loss Functions
Especially in a world where industrial development is reinforced by globalization tendencies, competitive companies know that satisfying customers' needs and running a successful operation requires a process that is reli...
Forecasting Chestnut Production and Export of Turkey Using ARIMA Model
Turkey is one of main producers and exporter countries of chestnut in the world. It is essential to assess scientifically the accurate future production and export potentials of chestnut on the basis of past trends. This...
Multi-layer Perceptron and Pruning
A Multi-Layer Perceptron (MLP) defines a family of artificial neural networks often used in TS modeling and forecasting. Because of its “black box” aspect, many researchers refuse to use it. Moreover, the optimization (o...
Time Series Prediction with Direct and Recurrent Neural Networks
This article presents a comparative study of the prediction of time series for the Consumer Price Index (CPI) using a recurrent neural network (RNN). For this, three models are designed for recurrent networks, with chang...
Bayesian Learning based Gaussian Approximation for Artificial Neural Networks
In the nonlinear systems, the pre-knowledge about the exact functional structure between inputs and outputs is mostly either unavailable or insufficient. In this case, the artificial neural networks (ANNs) are useful too...