Improving event-based rainfall–runoff modeling using a combined artificial neural network–kinematic wave approach

Summary The results of a study using a combined artificial neural network–kinematic wave (ANN-KW) approach to simulate event-based rainfall–runoff process are reported in this paper. Three types of ANN models were used, the first (NN R ) takes only measured rain as input, the second (NN RQ ) takes rain and estimated discharge obtained from a kinematic wave model assuming zero losses (KW o ) as input and the third (NN Q ) takes estimated discharge from the KW o model only as input. The NN R and NN RQ model outputs were compared to assess improvements to ANN model predictions when estimated discharge is included as input to the ANN model. NN Q model results were compared to a kinematic wave model (KW c ) which was modeled based on the loss rate of a calibration event. Three sets of rainfall–runoff data were used in the analyses; two obtained from an experimental station (completely impervious) and a third dataset from a real catchment. Using various performance measures, the results show that the NN RQ model performed better than the NN R model. Significantly, the NN RQ model produced hydrographs that were smoother than those predicted by the NN R model. The KW c modeled hydrographs for the experimental station were close to the measured hydrographs because the loss rates in the experimental station were small. For the real catchment however, since the loss rates were large and varied significantly between events, the KW c model was not able to produce the hydrographs from the catchment accurately. On the other hand, the NN Q model was able to produce hydrographs that were much closer to the measured hydrographs.

[1]  U. C. Kothyari,et al.  Modeling of the daily rainfall-runoff relationship with artificial neural network , 2004 .

[2]  Indrajeet Chaubey,et al.  Comparison of artificial neural network models for hydrologic predictions at multiple gauging stations in an agricultural watershed , 2008 .

[3]  Y. Najjar,et al.  Predicting catchment flow in a semi‐arid region via an artificial neural network technique , 2004 .

[4]  Souad Riad,et al.  Rainfall-runoff model usingan artificial neural network approach , 2004, Math. Comput. Model..

[5]  Robert J. Abrahart,et al.  Neural network emulation of a rainfall-runoff model , 2007 .

[6]  Tommy S. W. Wong,et al.  Effect of loss model on evaluation of Manning roughness coefficient of experimental concrete catchment , 2006 .

[7]  Vijay P. Singh,et al.  ANN and Fuzzy Logic Models for Simulating Event-Based Rainfall-Runoff , 2006 .

[8]  Robert J. Marks,et al.  Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks , 1999 .

[9]  Tommy S. W. Wong.  Optimum Rainfall Interval and Manning’s Roughness Coefficient for Runoff Simulation , 2008 .

[10]  Ashu Jain,et al.  Comparative Analysis of Event-Based Rainfall-Runoff Modeling Techniques—Deterministic, Statistical, and Artificial Neural Networks , 2003 .

[11]  Cláudia Cristina dos Santos,et al.  Modeling a densely urbanized watershed with an artificial neural network, weather radar and telemetric data , 2006 .

[12]  Momcilo Markus,et al.  PRECIPITATION-RUNOFF MODELING USING ARTIFICIAL NEURAL NETWORKS AND CONCEPTUAL MODELS , 2000 .

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

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

[15]  K. P. Sudheer,et al.  Identification of physical processes inherent in artificial neural network rainfall runoff models , 2004 .

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

[17]  Chung-Chieh Meng,et al.  Deterministic Insight into ANN Model Performance for Storm Runoff Simulation , 2008 .

[18]  Ashu Jain,et al.  Development of effective and efficient rainfall‐runoff models using integration of deterministic, real‐coded genetic algorithms and artificial neural network techniques , 2004 .

[19]  Rao S. Govindaraju,et al.  Prediction of watershed runoff using Bayesian concepts and modular neural networks , 2000 .

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

[21]  Ashu Jain,et al.  Integrated approach to model decomposed flow hydrograph using artificial neural network and conceptual techniques , 2006 .

[22]  H. Halff,et al.  Predicting Runoff from Rainfall Using Neural Networks , 1993 .

[23]  K. P. Sudheer,et al.  Rainfall‐runoff modelling using artificial neural networks: comparison of network types , 2005 .

[24]  Martin F. Lambert,et al.  Calibration and validation of neural networks to ensure physically plausible hydrological modeling , 2005 .

[25]  J. Schaake,et al.  Parametric-Deterministic Urban Watershed Model , 1980 .

[26]  Tommy S. W. Wong,et al.  Comparison between kinematic wave and artificial neural network models in event-based runoff simulation for an overland plane , 2008 .

[27]  Mohamed Nasr Allam,et al.  Rainfall‐runoff modelling using artificial neural networks technique: a Blue Nile catchment case study , 2006 .

[28]  Yen-Ming Chiang,et al.  Comparison of static-feedforward and dynamic-feedback neural networks for rainfall -runoff modeling , 2004 .

[29]  T. Rientjes,et al.  Constraints of artificial neural networks for rainfall-runoff modelling: trade-offs in hydrological state representation and model evaluation , 2005 .