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

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.

[1]  Liane Werner,et al.  Forecast combination in industrial series: A comparison between individual forecasts and its combinations with and without correlated errors , 2012, Expert Syst. Appl..

[2]  R. Hirsch,et al.  A Nonparametric Trend Test for Seasonal Data With Serial Dependence , 1984 .

[3]  M. Valipour.  Long‐term runoff study using SARIMA and ARIMA models in the United States , 2015 .

[4]  Bernard Bobée,et al.  Daily reservoir inflow forecasting using artificial neural networks with stopped training approach , 2000 .

[5]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[6]  Mohammad Valipour.  Ability of Box-Jenkins Models to Estimate of Reference Potential Evapotranspiration (A Case Study: Mehrabad Synoptic Station, Tehran, Iran) , 2012 .

[7]  Anil K. Bera,et al.  Efficient tests for normality, homoscedasticity and serial independence of regression residuals: Monte Carlo Evidence , 1981 .

[8]  Ozgur Kisi,et al.  Two hybrid Artificial Intelligence approaches for modeling rainfall–runoff process , 2011 .

[9]  G. C. Tiao,et al.  A Course in Time Series Analysis , 2000 .

[10]  Kung-Sik Chan,et al.  Time Series Analysis: With Applications in R , 2010 .

[11]  Ö. F. Durdu.  Application of linear stochastic models for drought forecasting in the Büyük Menderes river basin, western Turkey , 2010 .

[12]  Ozgur Kisi,et al.  River Flow Modeling Using Artificial Neural Networks , 2004 .

[13]  Wei-Zhen Lu,et al.  Spectral analysis of vehicle pollutants at traffic intersection in Hong Kong , 2012, Stochastic Environmental Research and Risk Assessment.

[14]  D. Cox,et al.  An Analysis of Transformations , 1964 .

[15]  Using a rainfall stochastic generator to detect trends in extreme rainfall , 2011 .

[16]  Feridon Radmanesh,et al.  Simulation of Seasonal precipitation using ANN and ARIMA Models: A case study of (Iran) Khozestan , 2013 .

[17]  François Anctil,et al.  Impact of the length of observed records on the performance of ANN and of conceptual parsimonious rainfall-runoff forecasting models , 2004, Environ. Model. Softw..

[18]  Kadri Yürekli,et al.  Application of linear stochastic models to monthly flow data of Kelkit Stream , 2005 .

[19]  Ignacio J. Turias,et al.  A novel three-step procedure to forecast the inspection volume , 2015 .

[20]  Durdu Ömer Faruk.  A hybrid neural network and ARIMA model for water quality time series prediction , 2010, Eng. Appl. Artif. Intell..

[21]  Erol Egrioglu,et al.  Improvement in Forecasting Accuracy Using the Hybrid Model of ARFIMA and Feed Forward Neural Network , 2012 .

[22]  Ali Yalcin,et al.  Flood prediction using Time Series Data Mining , 2007 .

[23]  D. K. Srivastava,et al.  Application of ANN for Reservoir Inflow Prediction and Operation , 1999 .

[24]  Zongxue Xu,et al.  Trend detection in hydrological time series by segment regression with application to Shiyang River Basin , 2010 .

[25]  Hossein Sedghi,et al.  Comparison of artificial neural networks and stochastic models in river discharge forecasting, (Case study: Ghara- Aghaj River, Fars Province, Iran) , 2012 .

[26]  M. Valipour,et al.  Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir , 2013 .

[27]  H. Tao,et al.  Trends in extreme temperature indices in the Poyang Lake Basin, China , 2014, Stochastic Environmental Research and Risk Assessment.

[28]  Ozgur Kisi,et al.  Comparison of different ANN techniques in river flow prediction , 2007 .

[29]  A. I. McLeod,et al.  Advances in Box-Jenkins modeling: 1. Model construction , 1977 .

[30]  Mohammad Ebrahim Banihabib,et al.  Monthly Inflow Forecasting using Autoregressive Artificial Neural Network , 2012 .

[31]  Adane Abebe,et al.  Stochastic simulation of the severity of hydrological drought , 2008 .

[32]  Mahmud Güngör,et al.  Monthly total sediment forecasting using adaptive neuro fuzzy inference system , 2010 .

[33]  Mehdi Khashei,et al.  An artificial neural network (p, d, q) model for timeseries forecasting , 2010, Expert Syst. Appl..

[34]  Konstantinos Ioannou,et al.  Predicting fuelwood prices in Greece with the use of ARIMA models, artificial neural networks and a hybrid ARIMA–ANN model , 2009 .

[35]  M. Valipour,et al.  Parameters Estimate of Autoregressive Moving Average and Autoregressive Integrated Moving Average Models and Compare Their Ability for Inflow Forecasting , 2012 .

[36]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[37]  Taehoon Hong,et al.  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) , 2014 .

[38]  M. Valipour.  Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms , 2016 .

[39]  Anil K. Bera,et al.  Efficient tests for normality, homoscedasticity and serial independence of regression residuals , 1980 .

[40]  M. J. Booij,et al.  Seasonality of low flows and dominant processes in the Rhine River , 2013, Stochastic Environmental Research and Risk Assessment.

[41]  K. Mohammadi,et al.  Comparison of regression, ARIMA and ANN models for reservoir inflow forecasting using snowmelt equivalent (a case study of Karaj). , 2005 .

[42]  Kadri Yürekli,et al.  Performances of Stochastic Approaches in Generating Low Streamflow Data for Drought Analysis , 2005 .

[43]  J. Y. Li,et al.  Short‐term inflow forecasting using an artificial neural network model , 2002 .

[44]  M. Ghorbani,et al.  Inter-comparison of time series models of lake levels predicted by several modeling strategies , 2014 .

[45]  E. H. Lloyd,et al.  Long-Term Storage: An Experimental Study. , 1966 .

[46]  Ismail KILINÇ,et al.  Reservoir Management Using Artificial Neural Networks , 2006 .

[47]  M. Valipour.  Estimation of surface water supply index using snow water equivalent. , 2013 .

[48]  G. Box,et al.  Distribution of Residual Autocorrelations in Autoregressive-Integrated Moving Average Time Series Models , 1970 .

[49]  W. L. Lane,et al.  Applied Modeling of Hydrologic Time Series , 1997 .

[50]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[51]  M. Firat,et al.  Comparison of Artificial Intelligence Techniques for river flow forecasting , 2008 .

[52]  A. I. McLeod,et al.  On the Distribution of Residual Autocorrelations in Box–Jenkins Models , 1978 .

[53]  Ali Osman Pektas,et al.  ANN hybrid model versus ARIMA and ARIMAX models of runoff coefficient , 2013 .