Application of ARIMA Models in Forecasting Air Temperature of Tehran

The main purpose of time series analysis is to find a best fitted model for describing the underlying stochastic structure of data. Then, the built model based on historical data can be used for forecasting. There are different case studies oftime series analysis, such as economics, production, weather forecasting, and so on, in literature. In two recent decades, weather forecasting have been propounded in many researches for investigating the changes in global climate. In this research, the average monthly air temperatures in Tehran metropolis is modeled. Using various measures, different types of models have been studied to confirm their usefulness. Consequently, Seasonal ARIMA (1, 0, 0) (0, 1, 1)12 issuggested to be most appropriate.

Keywords:

Time Series , ARIMA , SARIMA , Box-Jenkins procedure , Temperature