A non-linear combination of the forecasts of rainfall-runoff models by the first-order Takagi–Sugeno fuzzy system

Abstract With a plethora of watershed rainfall-runoff models available for flood forecasting and more than adequate computing power to operate a number of such models simultaneously, we can now combine the simulation results from the different models to produce the combination forecasts. In this paper, the first-order Takagi–Sugeno fuzzy system is introduced and explained as the fourth combination method (besides other three combination methods tested earlier, i.e. the simple average method (SAM), the weighted average method (WAM), and the neural network method (NNM)) to combine together the simulation results of five different conceptual rainfall-runoff models in a flood forecasting study on eleven catchments. The comparison of the forecast simulation efficiency of the first-order Takagi–Sugeno combination method with the other three combination methods demonstrates that the first-order Takagi–Sugeno method is just as efficient as both the WAM and the NNM in enhancing the flood forecasting accuracy. Considering its simplicity and efficiency, the first-order Takagi–Sugeno method is recommended for use as the combination system for flood forecasting.

[1]  J. M. Bates,et al.  The Combination of Forecasts , 1969 .

[2]  A. Shamseldin,et al.  Methods for combining the outputs of different rainfall–runoff models , 1997 .

[3]  X. R. Liu,et al.  The Xinanjiang model. , 1995 .

[4]  A. Fiordaliso.  A nonlinear forecasts combination method based on Takagi–Sugeno fuzzy systems , 1998 .

[5]  I. Bogardi,et al.  Application of fuzzy rule-based modeling technique to regional drought , 1999 .

[6]  J. Dickinson.  Some Comments on the Combination of Forecasts , 1975 .

[7]  L. Natale,et al.  Non-linear modelling of the rainfall-runoff transformation , 1992 .

[8]  George J. Klir,et al.  Fuzzy sets and fuzzy logic - theory and applications , 1995 .

[9]  C. Granger,et al.  Experience with Forecasting Univariate Time Series and the Combination of Forecasts , 1974 .

[10]  Frank Klawonn,et al.  Foundations of fuzzy systems , 1994 .

[11]  J. E. Nash,et al.  Linear models for river flow routing on large catchments , 1988 .

[12]  Dr. Hans Hellendoorn,et al.  An Introduction to Fuzzy Control , 1996, Springer Berlin Heidelberg.

[13]  Wayne Woldt,et al.  Fuzzy rule-based approach to describe solute transport in the unsaturated zone , 1999 .

[14]  P. E. O'connell,et al.  An introduction to the European Hydrological System — Systeme Hydrologique Europeen, “SHE”, 1: History and philosophy of a physically-based, distributed modelling system , 1986 .

[15]  G. C. Liang,et al.  Observed seasonal hydrological behaviour used in flow forecasting on the Yangtze River above Hankou , 1994 .

[16]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[17]  Pao-Shan Yu,et al.  Fuzzy multi-objective function for rainfall-runoff model calibration , 2000 .

[18]  J. Dickinson.  Some Statistical Results in the Combination of Forecasts , 1973 .

[19]  Kieran M. O'Connor,et al.  A simple non-linear rainfall-runoff model with a variable gain factor , 1994 .

[20]  L. K. Sherman.  Streamflow from rainfall by the unit-graph method , 1932 .

[21]  Keith Beven,et al.  Catchment geomorphology and the dynamics of runoff contributing areas , 1983 .

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

[23]  P. E. O'connell,et al.  An introduction to the European Hydrological System — Systeme Hydrologique Europeen, “SHE”, 2: Structure of a physically-based, distributed modelling system , 1986 .

[24]  R. K. Kachroo,et al.  River flow forecasting. Part 5. Applications of a conceptual model , 1992 .

[25]  V. Singh,et al.  Computer Models of Watershed Hydrology , 1995 .

[26]  Karsten Schulz,et al.  Parameter uncertainty in chemical equilibrium calculations using fuzzy set theory , 1999 .

[27]  A. Bárdossy,et al.  Fuzzy regression in hydrology , 1990 .

[28]  R. Clemen.  Combining forecasts: A review and annotated bibliography , 1989 .

[29]  P. D. Thompson,et al.  How to Improve Accuracy by Combining Independent Forecasts , 1977 .

[30]  M. Franchini,et al.  Comparative analysis of several conceptual rainfall-runoff models , 1991 .

[31]  Keith Beven,et al.  Estimation of evapotranspiration at the landscape scale: A fuzzy disaggregation approach , 1997 .

[32]  K. Beven,et al.  On constraining the predictions of a distributed model: The incorporation of fuzzy estimates of saturated areas into the calibration process , 1998 .

[33]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[34]  Keith Beven,et al.  A Discussion of Distributed Hydrological Modelling , 1990 .

[35]  Stan Openshaw,et al.  A hybrid multi-model approach to river level forecasting , 2000 .

[36]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[37]  R. K. Kachroo,et al.  River flow forecasting. Part 2. Algebraic development of linear modelling techniques , 1992 .

[38]  Hans-Jürgen Zimmermann,et al.  Fuzzy Set Theory - and Its Applications , 1985 .

[39]  James C. Bezdek,et al.  Efficient Implementation of the Fuzzy c-Means Clustering Algorithms , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[40]  Karsten Schulz,et al.  Water flow modeling in the unsaturated zone with imprecise parameters using a fuzzy approach , 1997 .

[41]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[42]  Keith Beven,et al.  The future of distributed models: model calibration and uncertainty prediction. , 1992 .

[43]  D. J. Reid.  Combining Three Estimates of Gross Domestic Product , 1968 .