A Takagi-Sugeno Fuzzy System for the Prediction of River Stage Dynamic

Abstract

An algorithm for real-time prediction of river stage dynamics using a Takagi-Sugeno fuzzy system is presented in this paper. The system is trained incrementally each time step and is used to predict onestep and multi-step ahead of river stages. The number of input variables that were considered in the analysis was determined using two statistical methods, i.e. autocorrelation and partial autocorrelation between the variables. Effectiveness of the identification technique was demonstrated by a simulation study on the river stage of the Cilalawi River in Indonesia. The numerical results of the Takagi-Sugeno fuzzy modeling method were compared with the results of a conventional linear regression model. Through inspection of the results it was found that the Takagi-Sugeno fuzzy approach was more accurate in predicting one-step and multi-step ahead of river stage dynamics than the conventional multiple linear regression approach. The Takagi-Sugeno fuzzy system was able to make a proper fuzzy rule from the training data set, which might be considered as one of the main drawbacks of the Takagi-Sugeno fuzzy system. Yet, more substantial improvement certainly should be pursued through further research to improve the forecast results at greater lead times.

Fuzzy Rule Based Models Modification by New Data: Application to Flood Flow Forecasting

“…Every fuzzy rule is made up of sets of input variables or premises in the form of fuzzy sets and a fuzzy consequence (Mamdani controller) or crisp function (Takagi and Sugeno controller). Many applications of both model types have been presented in engineering problems (Aquil et al 2006;Deka and Chandramouli 2005). Since Sugeno system is computationally more efficient than Mamdani system, this study employs the former one.…”

“…Chau et al (2005) compared genetic algorithm-based artificial neural network (ANN-GA) and ANFIS and linear regression model for water level forecasting in a channel reach of Yangtze River in China. Aquil et al (2006) applied an algorithm for real-time prediction of river stage dynamic using a Takagi-Sugeno fuzzy system and showed its superiority to the multiple linear regression approach.…”

“…Fuzzy models may form an alternative to process-based models in applications where computational speed and reduction of simulation time is critical, and/or the underlying relationships are poorly understood. In the fields of hydrology and water resources engineering, fuzzy models have extensively been applied to rainfall, runoff and water level fluctuation forecasting (Aquil et al 2006;Chau et al 2005;Deka and Chandramouli 2005;Stüber et al 2000;Yu et al 2000), water quality parameters estimation (Maier et al 2000) as well as reservoir operation (Dubrovin et al 2002;Karaboga et al 2004;Mehta and Jain 2008;Pinthong et al 2008;Russell and Campbell 1996;Shrestha et al 1996).…”

A Comparison between Fuzzy Inference Systems for Prediction (with Application to Prices of Fund in Egypt)

“…Alvisi [3] showed water level forecasted through Fuzzy Logic and Artificial Neural Network Approaches. Aqil [4] used A Takagi-Sugeno Fuzzy System for the Prediction of River Stage Dynamicsmes. Keskin [5] applied Fuzzy Logic approaches to flow Predicted Dim Stream.…”