Multivariate synthetic streamflow generation using a hybrid model based on artificial neural networks

Abstract. A model for multivariate streamflow generation is presented, based on a multilayer feedforward neural network. The structure of the model results from two components, the neural network (NN) deterministic component and a random component which is assumed to be normally distributed. It is from this second component that the model achieves the ability to incorporate effectively the uncertainty associated with hydrological processes, making it valuable as a practical tool for synthetic generation of streamflow series. The NN topology and the corresponding analytical explicit formulation of the model are described in detail. The model is calibrated with a series of monthly inflows to two reservoir sites located in the Tagus River basin (Spain), while validation is performed through estimation of a set of statistics that is relevant for water resources systems planning and management. Among others, drought and storage statistics are computed and compared for both the synthetic and historical series. The performance of the NN-based model was compared to that of a standard autoregressive AR(2) model. Results show that NN represents a promising modelling alternative for simulation purposes, with interesting potential in the context of water resources systems management and optimisation. Keywords: neural networks, perceptron multilayer, error backpropagation, hydrological scenario generation, multivariate time-series. .

[1]  B. D. Ripley,et al.  [Neural Networks: A Review from Statistical Perspective]: Comment , 1994 .

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

[3]  J. David Fuller,et al.  Backpropagation in Hydrological Time Series Forecasting , 1994 .

[4]  Kishan G. Mehrotra,et al.  Forecasting the behavior of multivariate time series using neural networks , 1992, Neural Networks.

[5]  J. ...,et al.  Applied modeling of hydrologic time series , 1980 .

[6]  Jukka Saarinen,et al.  A network of autoregressive processing units for time series modeling , 1996 .

[7]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[8]  Jose D. Salas,et al.  APPROACHES TO MULTIVARIATE MODELING OF WATER RESOURCES TIME SERIES1 , 1985 .

[9]  N. Null Artificial Neural Networks in Hydrology. I: Preliminary Concepts , 2000 .

[10]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[11]  D. M. Titterington,et al.  [Neural Networks: A Review from Statistical Perspective]: Rejoinder , 1994 .

[12]  Thomas Kolarik,et al.  Time series forecasting using neural networks , 1994, APL '94.

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

[14]  Kuolin Hsu,et al.  Effective and Efficient Modeling for Streamflow Forecasting , 2000 .

[15]  Jose D. Salas,et al.  Streamflow Forecasting Based on Artificial Neural Networks , 2000 .

[16]  Hal S. Stern,et al.  Neural networks in applied statistics , 1996 .

[17]  Jose D. Salas,et al.  Periodic Gamma Autoregressive Processes for Operational Hydrology , 1986 .

[18]  Joaquín Andreu,et al.  AQUATOOL, a generalized decision-support system for water-resources planning and operational management , 1996 .

[19]  Donald R. Kendall,et al.  A comparison of index-sequential and AR(1) generated hydrologic sequences , 1991 .

[20]  I. Rodríguez‐Iturbe,et al.  Random Functions and Hydrology , 1984 .

[21]  Makarand Deo,et al.  Real Time Forecasting Using Neural Networks , 2000 .

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

[23]  J. Stedinger,et al.  Water resource systems planning and analysis , 1981 .

[24]  Sevket Durucan,et al.  River flow prediction using artificial neural networks: generalisation beyond the calibration range. , 2000 .

[25]  Jery R. Stedinger,et al.  Synthetic streamflow generation: 1. Model verification and validation , 1982 .

[26]  H. Raman,et al.  Multivariate modelling of water resources time series using artificial neural networks , 1995 .

[27]  B. B. Jackson The use of streamflow models in planning , 1975 .

[28]  Paul A. Fishwick,et al.  Time series forecasting using neural networks vs. Box- Jenkins methodology , 1991, Simul..

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

[30]  Rao S. Govindaraju,et al.  COMPARISON OF ANNS AND EMPIRICAL APPROACHES FOR PREDICTING WATERSHED RUNOFF , 2000 .

[31]  Demetris Koutsoyiannis A generalized mathematical framework for stochastic simulation and forecast of hydrologic time series , 2000 .