Advertisement

Auto-Regressive Neural-Network Models for Long Lead-Time Forecasting of Daily Flow

  • Mohammad Ebrahim Banihabib
  • Reihaneh Bandari
  • Richard C. Peralta
Article
  • 30 Downloads

Abstract

Accurate reservoir-inflow forecasting is especially important for optimizing operation of multi-propose reservoirs that provide hydropower generation, flood control, and water for domestic use and irrigation. There are no previous reports of successful daily flow prediction using a 1-year lead-time. This paper reports successful daily stream flow predictions for that extended lead-time. It presents the first NARX (Nonlinear Auto Regressive model with eXogenous inputs)-type recurrent neural network (NARX-RNN) model used to forecast daily reservoir inflow for a long lead-time. It is the first use of dynamic memory to extend the forecast lead-time beyond the previously reported 1-week lead-times. For new nonlinear NARX-RNN models, we present and test 1600 alternative structures, differing in transfer functions (2), and numbers of inputs (2 to 5), neurons per hidden layer (1 to 20), input delays and output delays. For predicting inflow to the reservoir of the multi-purpose Dez Dam, we contrast accuracies of forecasts from the new models, and from a conventional auto-regressive linear ARIMA model. Based upon normalized root-mean-square error \( \mathrm{RMSE}/{\overline{Q}}_{obs} \) the best NARX-RNN has log-sigmoid transfer functions, three inputs, one hidden layers, four neurons in the hidden layer, two input delays, and 10 output delays. That NARX-RNN structure yields \( \mathrm{RMSE}/{\overline{Q}}_{obs} \) values of 0.616 in training and 0.678 in forecasting. The proposed model’s forecasting \( \mathrm{RMSE}/{\overline{Q}}_{obs} \) is 20% lower than that of the ARIMA model.

Keywords

NARX-RNN Daily inflow forecasting Dez Reservoir Lead-time 

Notes

Compliance with Ethical Standards

Conflict of Interest

None

References

  1. Akaike H (1974) A new look at the statistical model identification. IEEE Trans Autom Control AC-19(6):716–723CrossRefGoogle Scholar
  2. Baareh AKM, Sheta AF, Al khanifes K, (2006). Forecasting river flow in the USA: a comparison between auto-regression and neural network non-parametric models. J Comput Sci 2(10):775–780CrossRefGoogle Scholar
  3. Banihabib ME, Mousavi SM, Jamali FS (2008) 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 (In Persian)Google Scholar
  4. Chaouachi A, Kamel RM, Nagasaka K (2010) Neural network ensemble-based solar power generation short-term forecasting. JACIII 14(1):69–75CrossRefGoogle Scholar
  5. Coulibaly P, Anctil F, Bobée B (2000) Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. J Hydrol 230:244–257CrossRefGoogle Scholar
  6. Cryer JD, Chan KS (2008) Time series analysis: with applications in R, second ed. Springer, New York ISBN: 0387759581; 491CrossRefGoogle Scholar
  7. Diaconescu E (2008) The use of NARX neural networks to predict chaotic time series. WSEAS Trans on Comput Res 3(3):182–191Google Scholar
  8. Huang W, Xu B, Chan-Hilton A (2004) Forecasting flows in Apalachicola River using neural networks. Hydrol Process 18:2545–2564CrossRefGoogle Scholar
  9. Jeong DI, Kim YO (2005) Rainfall-runoff models using artificial neural networks for ensemble streamflow prediction. Hydrol Process 19:3819–3835CrossRefGoogle Scholar
  10. Karunasinghe DSK, Liong S (2006) Chaotic time series prediction with a global model: artificial neural network. J Hydrol 3232:92–105CrossRefGoogle Scholar
  11. Kia M (2010) Neural network on MATLAB. Kian Yarane Sabz Press, TehranGoogle Scholar
  12. Kisi I, Cigizoglu K (2005) Reservoir management using artificial neural networks. In: 14th. Reg. Directorate of DSI (State Hydraulic Works). Istanbul. TurkeyGoogle Scholar
  13. Lin GF, Wu M-C, Chen GR, Tsai FY (2009) An RBF-based model with an information processor for forecasting hourly reservoir inflow during typhoons. Hydrol Process 23:3598–3609CrossRefGoogle Scholar
  14. Mohammadi K, Eslami HR, Dayyani Dardashti S (2005) Comparison of regression ARIMA and ANN models for reservoir inflow forecasting using snowmelt equivalent. J Agric Sci Technol 7:17–30Google Scholar
  15. Noakes DJ, McLeod AI, Hipel KW (1985) Forecasting monthly river flow time series. Int J Forecast 1:179–190CrossRefGoogle Scholar
  16. Pekarova P, Pekar J (2006) Long-term discharge prediction for the Turnu Severin station (the Danube) using a linear autoregressive model. Hydrol Process 20:1217–1228CrossRefGoogle Scholar
  17. Pulido-Calvo I, Portela MM (2007) Application of neural approaches to one-step daily flow forecasting in Portuguese watersheds. J Hydrol 332:1–15CrossRefGoogle Scholar
  18. Riad S, Mania J, Bouchaou L, Najjar Y (2004) Predicting catchment flow in a semi-arid region via an artificial neural network technique. Hydrol Process 18:2387–2393CrossRefGoogle Scholar
  19. Rojas I, Valenzuela O, Rojasa V, Guillen A, Herrera LJ, Pomares H, Marquez L, Pasadas M (2007) Hybridization of intelligent techniques and ARIMA models for time series prediction. Fuzzy Set Syst 159(7):821–845Google Scholar
  20. Salas JD, Delleur JW, Yevjevich V, Lane WL (1980) Applied modeling of hydrological time series. Water Resource Publication. Littleton, ColoradoGoogle Scholar
  21. Sattaria MT, Yurekli K, Pal M (2012) Performance Evaluation of artificial neural network approaches in forecasting reservoir inflow. Appl Math Model 36:2649–2657CrossRefGoogle Scholar
  22. Shalamu A. (2009) Monthly and Seasonal Streamflow Forecasting in the RIO GRAND Basin. A thesis submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy in Civil Engineering. New Mexico State University; 321Google Scholar
  23. Shamseldin AY, O'Connor KM (2001) A non-linear neural network technique for updating of river flow forecasts. Hydrol Earth Syst Sci Discuss 5(4):577–598CrossRefGoogle Scholar
  24. Tawfik M (2003) Linearity versus non-linearity in forecasting Nile River flows. Adv Eng Softw 34:515–524CrossRefGoogle Scholar
  25. Valipour M, Banihabib ME, Behbahani SMR (2013) Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir. J Hydrol 476:433–441CrossRefGoogle Scholar
  26. Wang W, Van Gelder PH, Vrijling JK, Ma J (2006) Forecasting daily streamflow using hybrid ANN models. J Hydrol 324(1):383–399CrossRefGoogle Scholar
  27. Xie M (2001) Prediction of daily net inflows for management of reservoir systems. Master of Science Thesis in Agricultural and Biosystems Engineering. McGill University, Quebec, CanadaGoogle Scholar
  28. Xu ZX, Li JY (2002) Short-term inflow forecasting using an artificial neural network model. Hydrol Process 16:2423–2439CrossRefGoogle Scholar
  29. Yurekli K, Kurunc A, Ozturk F (2005) Application of linear stochastic models to monthly flow data of KELKIT Stream. Ecol Model 183(1):67–75CrossRefGoogle Scholar
  30. Zealand CM, Burn DH, Simonovic SP (1999) Short term streamflow forecasting using artificial neural networks. J Hydrol 214:32–48CrossRefGoogle Scholar

Copyright information

© Springer Nature B.V. 2018

Authors and Affiliations

  1. 1.Department of Irrigation and Drainage EngineeringCollege Aburaihan, University of TehranTehranIran
  2. 2.Civil and Environmental Engineering DepartmentUtah State UniversityLoganUSA

Personalised recommendations