Daily reservoir inflow forecasting using artificial neural networks with stopped training approach

In this paper, an early stopped training approach (STA) is introduced to train multi-layer feed-forward neural networks (FNN) for real-time reservoir inflow forecasting. The proposed method takes advantage of both Levenberg–Marquardt Backpropagation (LMBP) and cross-validation technique to avoid underfitting or overfitting on FNN training and enhances generalization performance. The methodology is assessed using multivariate hydrological time series from Chute-du-Diable hydrosystem in northern Quebec (Canada). The performance of the model is compared to benchmarks from a statistical model and an operational conceptual model. Since the ultimate goal concerns the real-time forecast accuracy, overall the results show that the proposed method is effective for improving prediction accuracy. Moreover it offers an alternative when dynamic adaptive forecasting is desired.

[1]  G. W. Kite.  Development of a hydrologic model for a Canadian watershed , 1978 .

[2]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[3]  Jean Rousselle,et al.  Comparaison de deux modles pour la prvision journalire en temps rel des apports naturels , 1998 .

[4]  Xiao-Hu Yu,et al.  Efficient Backpropagation Learning Using Optimal Learning Rate and Momentum , 1997, Neural Networks.

[5]  James M. Ehrman,et al.  Using neural networks to assess the influence of changing seasonal climates in modifying discharge, dissolved organic carbon, and nitrogen export in eastern Canadian rivers , 1998 .

[6]  Lutz Prechelt,et al.  Automatic early stopping using cross validation: quantifying the criteria , 1998, Neural Networks.

[7]  J. Amorocho,et al.  Determination of Nonlinear Functional Response Functions in Rainfall-Runoff Processes , 1971 .

[8]  Tom Tollenaere,et al.  SuperSAB: Fast adaptive back propagation with good scaling properties , 1990, Neural Networks.

[9]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[10]  George E. P. Box,et al.  Time Series Analysis: Forecasting and Control , 1977 .

[11]  Ferdinand Hergert,et al.  Improving model selection by nonconvergent methods , 1993, Neural Networks.

[12]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[13]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

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

[15]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[16]  Slobodan P. Simonovic,et al.  Short term streamflow forecasting using artificial neural networks , 1998 .

[17]  F. Smieja.  Neural network constructive algorithms: Trading generalization for learning efficiency? , 1993 .

[18]  W. T. Illingworth,et al.  Practical guide to neural nets , 1991 .

[19]  Kurt Hornik,et al.  Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.

[20]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[21]  Jason Smith,et al.  Neural-Network Models of Rainfall-Runoff Process , 1995 .

[22]  S. L. Jacoby.  A mathematical model for nonlinear hydrologic systems , 1966 .

[23]  Paulin Coulibaly,et al.  A recurrent neural networks approach using indices of low-frequency climatic variability to forecast regional annual runoff. , 2000 .

[24]  Martin T. Hagan,et al.  Neural network design , 1995 .

[25]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[26]  David E. Rumelhart,et al.  Generalization by Weight-Elimination with Application to Forecasting , 1990, NIPS.

[27]  Nachimuthu Karunanithi,et al.  Neural Networks for River Flow Prediction , 1994 .

[28]  A. Shamseldin.  Application of a neural network technique to rainfall-runoff modelling , 1997 .

[29]  Makarand Deo,et al.  Real‐Time Flood Forecasting Using Neural Networks , 1998 .

[30]  H. Tong.  Non-linear time series. A dynamical system approach , 1990 .

[31]  A. Soldati,et al.  River flood forecasting with a neural network model , 1999 .

[32]  Timothy Masters,et al.  Advanced algorithms for neural networks: a C++ sourcebook , 1995 .

[33]  A. Tokar,et al.  Rainfall-Runoff Modeling Using Artificial Neural Networks , 1999 .

[34]  Bernard Bobée,et al.  Prévision hydrologique par réseaux de neurones artificiels : état de l'art , 1999 .

[35]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[36]  Jirí Síma,et al.  Back-propagation is not Efficient , 1996, Neural Networks.

[37]  Kuolin Hsu,et al.  Artificial Neural Network Modeling of the Rainfall‐Runoff Process , 1995 .

[38]  A. Turgeon,et al.  Fuzzy Learning Decomposition for the Scheduling of Hydroelectric Power Systems , 1996 .

[39]  Heinz Mühlenbein,et al.  Limitations of multi-layer perceptron networks-steps towards genetic neural networks , 1990, Parallel Comput..

[40]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[41]  B. S. Thandaveswara,et al.  A non-linear rainfall–runoff model using an artificial neural network , 1999 .

[42]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[43]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .