River flow estimation using adaptive neuro fuzzy inference system

Accurate estimation of River flow changes is a quite important problem for a wise and sustainable use. Such a problem is crucial to the works and decisions related to the water resources and management. In this study, an adaptive network-based fuzzy inference system (ANFIS) approach was used to construct a River flow forecasting system. In particular, the applicability of ANFIS as an estimation model for River flow was investigated. To illustrate the applicability and capability of the ANFIS, the River Great Menderes, located the west of Turkey and the most important water resource of Great Menderes Catchment's, was chosen as a case study area. The advantage of this method is that it uses the input-output data sets. Totally 5844 daily data sets collected in 1985-2000 years were used to estimate the River flow. The models having various input structures were constructed and the best structure was investigated. In addition four various training/testing data sets were constructed by cross validation methods and the best data set was investigated. The performance of the ANFIS models in training and testing sets were compared with the observations and also evaluated. The results indicated that the ANFIS can be applied successfully and provide high accuracy and reliability for River flow estimation.

[1]  P. C. Nayak,et al.  A neuro-fuzzy computing technique for modeling hydrological time series , 2004 .

[2]  Shie-Yui Liong,et al.  Advance flood forecasting for flood stricken Bangladesh with a fuzzy reasoning method (Copies of English Papers by the Center Staff Published in the Fiscal Year of 1999) , 2000 .

[3]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[4]  A. Robinson Fayek,et al.  Application of fuzzy logic to forecast seasonal runoff , 2003 .

[5]  Yong-Huang Lin,et al.  The strategy of building a flood forecast model by neuro‐fuzzy network , 2006 .

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

[7]  Wagner Caradori do Amaral,et al.  A novel approach to robust parameter estimation using neurofuzzy systems , 1999 .

[8]  H. D. Scott,et al.  Applications of fuzzy logic to the prediction of soil erosion in a large watershed , 1998 .

[9]  Lucien Duckstein,et al.  Fuzzy conceptual rainfall–runoff models , 2001 .

[10]  Fi-John Chang,et al.  Adaptive neuro-fuzzy inference system for prediction of water level in reservoir , 2006 .

[11]  Kuolin Hsu,et al.  Streamflow Forecasting Using Artificial Neural Networks , 1998 .

[12]  Dimitri P. Solomatine,et al.  River flow forecasting using artificial neural networks , 2001 .

[13]  P. C. Nayak,et al.  Fuzzy computing based rainfall–runoff model for real time flood forecasting , 2005 .

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

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

[16]  L. Bodri,et al.  Prediction of extreme precipitation using a neural network: application to summer flood occurence in Moravia , 2000 .

[17]  H. Nagy,et al.  Prediction of Sediment Load Concentration in Rivers using Artificial Neural Network Model , 2002 .