State space neural networks for short term rainfall-runoff forecasting

Rainfall-runoff processes are dynamic systems that are better described by a dynamic model. In this paper, a specific dynamic neural network, called state space neural network (SSNN), is modified to perform short term rainfall-runoff forecasts. The lead time is extended to 3 h. To improve the link between the weights of the network and physical concepts that most neural networks lack for, a method of the unit hydrograph representation is proposed to reproduce the unit hydrographs based on the weights of the network. Hence, a transition of rainfall-runoff systems can be observed via the changes of the unit hydrograph hour by hour. Furthermore, a new learning method developed from the interchange of the roles of the network states and the weight matrix is applied to train the SSNN and helps the network to evolve into a time-variant model while forecasting the rainfall-runoff process. A study case has been implemented in Taiwan's Wu-Tu watershed, where the runoff path-lines are short and steep. Forty-seven events from 1966 to 1997 are forecasted via the SSNN, and the results are validated via four criteria. The convergence of the new learning algorithm is shown during the model training process. Performance of the SSNN for short term rainfall-runoff forecasting reveals that the specific dynamic recurrent neural network is appropriate for hydrological forecasts.

[1]  Li-Chiu Chang,et al.  Real‐time recurrent learning neural network for stream‐flow forecasting , 2002 .

[2]  Yen-Chang Chen,et al.  Counterpropagation fuzzy–neural network for streamflow reconstruction , 2001 .

[3]  Shin-jen Cheng,et al.  An approach for evaluating the hydrological effects of urbanization and its application , 2002 .

[4]  Amir F. Atiya,et al.  Multi-step-ahead prediction using dynamic recurrent neural networks , 2000, Neural Networks.

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

[6]  DeLiang Wang,et al.  On Temporal Generalization of Simple Recurrent Networks , 1996, Neural Networks.

[7]  Jie Zhang,et al.  Long-term prediction models based on mixed order locally recurrent neural networks , 1998 .

[8]  Marco Lovera,et al.  Identification of the rainfall-runoff relationship in urban drainage networks , 1999 .

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

[10]  R. Abrahart,et al.  Comparing neural network and autoregressive moving average techniques for the provision of continuous river flow forecasts in two contrasting catchments , 2000 .

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

[12]  Amir F. Atiya,et al.  New results on recurrent network training: unifying the algorithms and accelerating convergence , 2000, IEEE Trans. Neural Networks Learn. Syst..

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

[14]  Ana P. Barros,et al.  Quantitative flood forecasting using multisensor data and neural networks , 2001 .

[15]  E. Toth,et al.  Comparison of short-term rainfall prediction models for real-time flood forecasting , 2000 .

[16]  C. Lee Giles,et al.  How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies , 1998, Neural Networks.

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

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

[19]  Fernanda Botelho,et al.  Dynamical features simulated by recurrent neural networks , 1999, Neural Networks.

[20]  Tawatchai Tingsanchali,et al.  Application of tank, NAM, ARMA and neural network models to flood forecasting , 2000 .

[21]  Fi-John Chang,et al.  A self-organization algorithm for real-time flood forecast , 1999 .

[22]  Daniel S. Yeung,et al.  A Quantified Sensitivity Measure for Multilayer Perceptron to Input Perturbation , 2003, Neural Computation.

[23]  Ah Chung Tsoi,et al.  Discrete time recurrent neural network architectures: A unifying review , 1997, Neurocomputing.

[24]  R. Golob,et al.  Neural-network-based water inflow forecasting , 1997 .

[25]  K. Warwick,et al.  Dynamic recurrent neural network for system identification and control , 1995 .

[26]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[27]  C. Lee Giles,et al.  Using recurrent neural networks to learn the structure of interconnection networks , 1995, Neural Networks.

[28]  Yen-Chang Chen,et al.  A counterpropagation fuzzy-neural network modeling approach to real time streamflow prediction , 2001 .

[29]  P. Vega,et al.  State-space neural network for modelling, prediction and control , 2000 .

[30]  Ning Gong,et al.  Neural networks for solid transport modelling in sewer systems during storm events , 1996 .