Comparison of Seasonal Time Series, Bi-linear and Nonlinear Threshold (SETAR) Models in Forecasting the Monthly Inflow to Maroun Dam Reservoir

Document Type : Research Article


1 Department of Water Resources Engineering, University of Zabol, Iran

2 PhD in Irrigation and Drainage, Faculty of Water and Soil, University of Zabol, Iran

3 Associate Professor, Dept. of Water Engineering, Faculty of Water and Soil, University of Zabol, Iran

4 M. Sc. of Water Resources, Khuzestan Water and Power Organization, Ahwaz, Iran


In the present research, the SARIMA seasonal time series, Holt-Winters, bi-linear (BL) and Self-Exciting Threshold Auto-Regressive (SETAR) models were used to predict the monthly inflow to the Maroun dam reservoir. To this end, the 34-year data of the Idanak hydrometric station located in Khuzestan province of Iran between the years 1982 and 2015 have been used. The logarithmic transformation was used to normalize the monthly discharge data of the Idanak hydrometric station. Also, differencing technique was used to eliminate the seasonal component of the monthly data. The independence test of the model residuals (Ljung-Box or porte-manteau), the autocorrelation and partial autocorrelation functions were used to check the validity (quality of fitting) of these models. Finally, SARIMA models (1.0.1) * (2.0.2) 12, BL ( and SETAR (2; 7.3) were chosen as the best models with the minimum values of Akaike and Schwartz criteria. The results of the evaluation of fitted models showed that the BL model with the values ​​of the coefficient of determination and root mean square error which are 0.81 and 14.80 m3/s, respectively, has an acceptable accuracy to predict the monthly flow to the Maroun River. It was also found that by increasing the non-seasonal rank degree in SARIMA models, the model validity and performance are weakened to predict monthly flow. Also, the results showed that the Holt-Winters model with the values of the coefficient of determination and root mean square error which are 0.56 and 10 m3/s, respectively, has the weakest performance to predict the monthly flow to the Maroun dam reservoir.


Main Subjects

[1]. Thomas Harold A. Mathematical synthesis of streamflow sequences for the analysis of river basin by simulation. Design of water resources-systems. 1962, 459-493.
[2].  McKerchar AI, Delleur LW. Application of Seasonal Parametric Linear Stochastic Models to Monthly Flow Data. Journal of Water Resources. 1974, 10: 246-255.
[3].  Jain SK, Das A, Sirvastava DK. Application of ANN for Reservoir Inflow Prediction and Operation. Journal of water Resources planning and Management. 1999, 125: 263-271.
[4].  Banihabib ME, Mousavi SM, Jamali FS. Artificial neural network model to study the spatial and temporal correlation between stations in reservoir inflow forecasting. In: 3rd Iran Water Resources Management Conference, Tabriz, Iran 2008. [Persian]
[5].  Naveh H, Khalili K, Aalami MT, Behmanesh j. Prediction of Streamflow using Bilinear Time Series Models (Case study: Barandouz Chai and Shahr Chai River). Journal of Water and Soil, Food Industries Science. 2012, 26(5): 1299-1307. [Persian]
[6].  Svetlíková D, Komorníková M, Kohnová S, Szolgay J, Hlavčová K. Analysis of discharge and rainfall time series in the region of the Káštorské lúky wetland inSlovakia, In XXIVth conference of the Danubian countries on the hydrological forecasting.Conference E-papers. Bled.2008.
[7].  Ahmadi F, Dinpashoh Y, Fakheri Fard, A, Khalili K, Darbandi S. Comparing nonlinear time series models and genetic programming for daily river flow forecasting (Case study: Barandouz-Chai River).Journal of Water and Soil Conservation. 2015, 22(1):151-169. [Persian]
[8].  Wang WC, Chau KW, Xu DM, Chen XY. improving forcesting accurancy of annual runoff time series using ARIMA based on EEMD decomposition , water resources management. 2015, 29(8):.2655-2675.
[9].  Pasandidehfard Z, Mikaeili tabrizi AZ, Mosaedi A, Rezaei H. Assessment of land-use change impacts on water quality parameters in sub-basins of Hableh rood watershed using multivariate statistics and time series models (ARIMA). Iranin Journal of Ecohydrology. 2019, 6(1): 29-39. [Persian]
[10].            Valipour M, Banihabib M.E, Behbahani S.M.R. Monthly Inflow Forecasting Using Autoregressive Artificial Neural Network.Journal of applied Sciences. 2013, 12(20):2139-2147.
[11].            Wang W, Vrijling JK, Van Gelder PH, Ma J. Testing for nonlinearity of streamflow processes at different timescales. Journal of Hydrology. 2006, 322(1-4): 247-268.
[12].            Komorník J, Komorníková M, Mesiar R, Szökeová D, Szolgay J. Comparison of forecasting performance of nonlinear models of hydrological time series. Physics and Chemistry of the Earth, Parts A/B/C. 2006, 31(18): 1127-1145.
[13].            Box GEP, Jenkins GM, Reinsel GC. Time series Analysis: Forecasting and Control. 3rdEd. prentice Hall, Englewood Cliffs Inc., New Jersey.1994, 598p.
[14].            Granger CWJ, Andersen AP. An Introduction to Bilinear Time Series Models.
Vandenhoek and Ruprecht: Gottingen. North Holland Publishing Company Press. 1978
[15].            Akaike H. A new look at statistical model Identification. IEEE. Transaction on Automatic Control AC-19. 1974, 716-723.
[16].            Tong H. Threshold Models in Non-Linear Time Series Analysis. Springer, New York. 1983.
[17].            Ja¨ras J. Gishani AM Threshold detection in autoregressive non-linear models. M. A. Thesis, Department of Statistics, Lund University 2010.
[18].            Bashari M, Vafakhah M. Comparison of Different Time Series Analysis Methods for Forecasting Monthly Discharge in Karkheh Watershed. Journal of Irrigation and Water Engineering. 2011, 2(1): 75- 86.
[19].            Zhang L, Zhang GX, Li RR. Water quality analysis and prediction using hybrid time series and neural network models. Journal of Agricultural Science and Technology. 2016; 18(4): 975-983.
[20].            Oliveira JP, Steffen JL, Cheung P. Parameter estimation of seasonal ARIMA models for water demand forecasting using the Harmony Search Algorithm. Procedia Engineering. 2017; 186: 177 - 185.