BEST ARIMA MODELS FOR FORECASTING INFLOW OF HIT STATION

  View PDF

  Download PDF

  Adnan K. Shathir   |      Layla A. Mohammed Saleh   |   

Time series analysis for hydrological phenomena has an important role in water resources engineering. In this study, seven models of the ARIMA family are tested for forecasting the monthly discharge at the Hit station on the Euphrates river in Iraq. The statistical analyses were done for models with help of IBM SPSS statistics 21 software, The number of observations used is equal to 480 reading, start from October 1932 and end in September 1972, this period represents the near-natural streamflow of the river before the construction of dams in Syria and Turkey. Statistical tests such as T-test and F-test were used to detect any change in Mean and Variance at a 95 % significant probability level. Results showed that the best model is (2,0,1)×(0,1,1)12 which gives a minimum error and good agreement between observed and forecast discharge.