Skip to main content
SpringerLink
Log in

Forecasting monthly inflow with extreme seasonal variation using the hybrid SARIMA-ANN model

  • Original Paper
  • Published:
Stochastic Environmental Research and Risk Assessment Aims and scope Submit manuscript

Abstract

The optimal operation of dam reservoirs can be programmed and managed by predicting the inflow to these structures more accurately. To this end, there are various linear and nonlinear models. However, some hydrological problems like inflow with extreme seasonal variation are not purely linear or nonlinear. To improve the forecasting accuracy of this phenomenon, a linear Seasonal Auto Regressive Integrated Moving Average (SARIMA) model is combined with a nonlinear Artificial Neural Network (ANN) model. This new model is used to predict the monthly inflow to the Jamishan dam reservoir in West Iran. A comparison of the SARIMA and ANN models with the proposed hybrid model’s results is provided accordingly. More specifically, the models’ performance in forecasting base and flood flows is evaluated. The effect of changing the forecasting period length on the models’ accuracy is studied. The results of increasing the number of SARIMA model parameters up to five are investigated to achieve more accurate forecasting. The hybrid model predicts peak flood flows much better than the individual models, but SARIMA outperforms the other models in predicting base flow. The obtained results indicate that the hybrid model reduces the overall forecast error more than the ANN and SARIMA models. The coefficient of determination of the hybrid, ANN and SARIMA models were 0.72, 0.64 and 0.58, and the root mean squared error values were 1.02, 1.16 and 1.27 respectively, during the forecast period. Changing the forecasting length also indicated that these models can be used in the long term without increasing the forecast error.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  • Abebe A, Foerch G (2008) Stochastic simulation of the severity of hydrological drought. Water Environ J 22(1):2–10

    Article  Google Scholar 

  • Aladag CH, Egrioglu E, Kadilar C (2012) Improvement in forecasting accuracy using the hybrid model of ARFIMA and feed forward neural network. Am J Intell Syst 2(2):12–17

    Article  Google Scholar 

  • Anctil F, Perrin C, Andreassian V (2004) Impact of the length of observed records on the performance of ANN and of conceptual parsimonious rainfall-runoff forecasting models. Environ Modell Softw 19(4):357–368

    Article  Google Scholar 

  • Box GE, Cox DR (1964) An analysis of transformations. J R Stat Soc B Met 26:211–252

    Google Scholar 

  • Box GEP, Jenkins GM (1976) Time series analysis: forecasting and control. Holden-Day, San Francisco

  • Box GE, Pierce DA (1970) Distribution of residual autocorrelations in autoregressive-integrated moving average time series models. J Am Stat Assoc 65(332):1509–1526

    Article  Google Scholar 

  • Cantet P, Bacro JN, Arnaud P (2011) Using a rainfall Stochastic generator to detect trends in extreme rainfall. Stoch Environ Res Risk A 25(3):429–441

    Article  Google Scholar 

  • Coulibaly P, Anctil F, Bobee B (2000) Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. J Hydrol 230(3):244–257

    Article  Google Scholar 

  • Cryer JD, Chan KS (2008) Time series analysis, with applications in R, 2nd edn. Springer, New York

    Google Scholar 

  • Damle C, Yalcin A (2007) Flood prediction using time series data mining. J Hydrol 333(2):305–316

    Article  Google Scholar 

  • Durdu ÖF (2010) Application of linear stochastic models for drought forecasting in the Büyük Menderes river basin, western Turkey. Stoch Environ Res Risk A 24(8):1145–1162

    Article  Google Scholar 

  • Faruk DO (2010) A hybrid neural network and SARIMA model for water quality time series prediction. Eng Appl Artif Intell 23(4):586–594

    Article  Google Scholar 

  • Fereydooni M, Rahnemaei M, Babazadeh H, Sedghi H, Elhami MR (2012) Comparison of artificial neural networks and stochastic models in river discharge forecasting, Case study, Ghara-Aghaj river, Fars Province, Iran. Afr J Agric Res 7(40):5446–5458

    Google Scholar 

  • Firat M (2008) Comparison of artificial intelligence techniques for river flow forecasting. Hydrol Earth Syst Sci 12(1):123–139

    Article  Google Scholar 

  • Firat M, Güngör M (2010) Monthly total sediment forecasting using adaptive neuro fuzzy inference system. Stoch Environ Res Risk A 24(2):259–270

    Article  Google Scholar 

  • Golabi MR, Radmanesh F, Akhondali AM, Kashefipoor M (2013) Simulation of seasonal precipitation using ANN and SARIMA models, a case study of (Iran) Khozestan. Elixir Comput Sci Eng 55:13039–13046

    Google Scholar 

  • He HD, Lu WZ (2012) Spectral analysis of vehicle pollutants at traffic intersection in Hong Kong. Stoch Environ Res Risk A 26(8):1053–1061

    Article  Google Scholar 

  • Hipel KW, McLeod AI, Lennox WC (1977) Advances in Box-Jenkins modeling, 1, model construction. Water Resour Res 13(3):567–575

    Article  Google Scholar 

  • Hirsch RM, Slack JR (1984) A nonparametric trend test for seasonal data with serial dependence. Water Resour Res 20:727–732

    Article  Google Scholar 

  • Hurst HE, Black RP, Simaika YM (1965) Long-term storage, an experimental study. Constable Press, London

    Google Scholar 

  • Jain SK, Das A, Srivastava DK (1999) Application of ANN for reservoir inflow prediction and operation. J Water Res Plan ASCE 125(5):263–271

    Article  Google Scholar 

  • Jarque CM, Bera AK (1980) Efficient tests for normality, homoscedasticity and serial independence of regression residuals. Econ Lett 6(3):255–259

    Article  Google Scholar 

  • Jeong K, Koo C, Hong T (2014) An estimation model for determining the annual energy cost budget in educational facilities using SARIMA (seasonal autoregressive integrated moving average) and ANN (artificial neural network). Energy 71:71–79

    Article  Google Scholar 

  • Khashei M, Bijari M (2010) An artificial neural network (p, d, q) model for time series forecasting. Expert Syst Appl 37(1):479–489

    Article  Google Scholar 

  • Khatibi R, Ghorbani MA, Naghipour L, Jothiprakash V, Fathima TA, Fazelifard MH (2014) Inter-comparison of time series models of lake levels predicted by several modeling strategies. J Hydrol 511:530–545

    Article  Google Scholar 

  • Kisi Ö (2004) River flow modeling using artificial neural networks. J Hydrol Eng 9(1):60–63

    Article  Google Scholar 

  • Kisi I, Cigizoglu K (2005) Reservoir management using artificial neural networks. 14th Reg Directorate of DSI State Hydraulic Works, Istanbul

  • Kisi O, Cigizoglu HK (2007) Comparison of different ANN techniques in river flow prediction. Civ Eng Environ Sys 24(3):211–231

    Article  Google Scholar 

  • Koutroumanidis T, Loannou K, Arabatzis G (2009) Predicting fuelwood prices in Greece with the use of SARIMA models, artificial neural networks and a hybrid SARIMA–ANN model. Energy Policy 37(9):3627–3634

    Article  Google Scholar 

  • Levenberg K (1944) A method for the solution of certain non-linear problems in least squares. Quart Appl Math 2:164–168

    Article  Google Scholar 

  • Martins VLM, Werner L (2012) Forecast combination in industrial series: a comparison between individual forecasts and its combinations with and without correlated errors. Expert Syst Appl 39(13):11479–11486

    Article  Google Scholar 

  • McLeod A (1978) On the distribution of residual autocorrelations in Box-Jenkins models. J R Stat Soc B Met 40(3):296–302

    Google Scholar 

  • Mohammadi K, Eslami HR, Dardashti SH (2005) Comparison of regression, SARIMA and ANN models for reservoir inflow forecasting using snowmelt equivalent a case study of Karaj. J Agric Sci Technol 7:17–30

    Google Scholar 

  • Nirmala M, Sundaram SM (2010) Modeling and predicting the monthly rainfall in Tamil Nadu as a seasonal multivariate SARIMA process. Int J Comput Eng 1:103–111

    Google Scholar 

  • Nourani V, Kisi O, Komasi M (2011) Two hybrid artificial intelligence approaches for modeling rainfall–runoff process. J Hydrol 402(1):41–59

    Article  Google Scholar 

  • Pektas AO, Cigizoglu HK (2013) ANN hybrid model versus SARIMA and SARIMAX models of runoff coefficient. J Hydrol 500:21–36

    Article  Google Scholar 

  • Peña D, Tiao GC, Tsay RS (2011) A course in time series analysis. Wiley, New York

    Google Scholar 

  • Ruiz-Aguilar J, Turias I, Jiménez-Come M (2015) A novel three-step procedure to forecast the inspection volume transport. Res C-Emerg 56:393–414

    Google Scholar 

  • Salas JD, Delleur JW, Yevjevich V, Lane WL (1988) Applied modeling of hydrologic time series. Water Resources Publication, Highlands Ranch

    Google Scholar 

  • Shao Q, Li Z, Xu Z (2010) Trend detection in hydrological time series by segment regression with application to Shiyang River Basin. Stoch Environ Res Risk A 24(2):221–233

    Article  Google Scholar 

  • Tao H, Fraedrich K, Menz C, Zhai J (2014) Trends in extreme temperature indices in the Poyang Lake Basin, China. Stoch Environ Res Risk A 28(6):1543–1553

    Article  Google Scholar 

  • Tongal H, Demirel MC, Booij MJ (2013) Seasonality of low flows and dominant processes in the Rhine River. Stoch Environ Res Risk A 27(2):489–503

    Article  Google Scholar 

  • Valipour M (2012) Ability of Box-Jenkins models to estimate of reference potential evapotranspiration a case study, Mehrabad synoptic station, Tehran, Iran. J Agric Vet Sci 1(5):1–11

    Google Scholar 

  • Valipour M (2013) Estimation of surface water supply index using snow water equivalent. Advances in agriculture. Sci Eng Res 3(1):587–602

    Google Scholar 

  • Valipour M (2015) Long-term runoff study using SARIMA and ARIMA models in the United States. Meteorol Appl 22(3):592–598

    Article  Google Scholar 

  • Valipour M (2016) Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms. Meteorol Appl 23(1):91–100

    Article  Google Scholar 

  • Valipour M, Banihabib ME, Behbahani SM (2012a) Parameters estimate of autoregressive moving average and autoregressive integrated moving average models and compare their ability for inflow forecasting. J Math Stat 8(3):330–338

    Article  Google Scholar 

  • Valipour M, Banihabib ME, Behbahani SM (2012b) Monthly inflow forecasting using autoregressive artificial neural network. J Appl Sci 12(20):2139

    Article  Google Scholar 

  • Valipour M, Banihabib ME, Behbahani SMR (2013) Comparison of the ARMA, SARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir. J Hydrol 476:433–441

    Article  Google Scholar 

  • Xu ZX, Li JY (2002) Short-term inflow forecasting using an artificial neural network model. Hydrol Process 16(12):2423–2439

    Article  Google Scholar 

  • Yurekli K, Kurunc A (2005) Performances of stochastic approaches in generating low streamflow data for drought analysis. J Spat Hydrol 5(1):20–32

    Google Scholar 

  • Yurekli K, Kurunc A, Ozturk F (2005) Application of linear stochastic models to monthly flow data of Kelkit Stream. Ecol Model 183(1):67–75

    Article  Google Scholar 

  • Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Civil Engineering, Razi University, Kermanshah, Iran

    Hamid Moeeni & Hossein Bonakdari

Authors
  1. Hamid Moeeni
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hossein Bonakdari
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hossein Bonakdari.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Moeeni, H., Bonakdari, H. Forecasting monthly inflow with extreme seasonal variation using the hybrid SARIMA-ANN model. Stoch Environ Res Risk Assess 31, 1997–2010 (2017). https://doi.org/10.1007/s00477-016-1273-z

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00477-016-1273-z

Keywords

Search

Navigation