Abstract
This study investigates the potential of nonlinear local function approximation in a Takagi–Sugeno (TS) fuzzy model for river flow forecasting. Generally, in a TS framework, the local approximation is performed by a linear model, while in this approach, linear function approximation is substituted using a nonlinear function approximation. The primary hypothesis herein is that the process being modeled (rainfall–runoff in this study) is highly nonlinear, and a linear approximation at the local domain might still leave a lot of unexplained variance by the model. In this study, subtractive clustering technique is used for domain partition, and neural network is used for function approximation. The modeling approach has been tested on two case studies: Kolar basin in India and Kentucky basin in USA. The results of fuzzy nonlinear local approximation (FNLLA) model are highly promising. The performance of the FNLLA is compared with that of a pure fuzzy inference system (FIS), and it is observed that both the models perform similar at 1-step-ahead forecasts. However, the FNLLA performs much better than FIS at higher lead times. It is also observed that FNLLA forecasts the river flow with lesser error compared to FIS. In the case of Kolar River, more than 40 % of the total data are forecasted with <2 % error by FNLLA at 1 h ahead, while the corresponding value for FIS is only 20 %. In the case of 3-h-ahead forecasts, these values are 25 % for FNLLA and 15 % for FIS. Performance of FNLLA in the case of Kentucky River basin was also better compared to FIS. It is also found that FNLLA simulates the peak flow better than FIS, which is certainly an improvement over the existing models.
Similar content being viewed by others
References
Abrahart RJ, Anctil F, Coulibaly P, Dawson CW, Mount NJ, See LM, Shamseldin AY, Solomatine DP, Toth E, Wilby RL (2012) Two decades of anarchy? Emerging themes and outstanding challenges for neural network modelling of surface hydrology. Prog Phys Geogr 36:480–513
Amorocho J, Brandstetter A (1971) A critique of current methods of hydrologic systems investigations. EOS Trans AGU 45:307–321
Anders U, Korn O (1999) Model selection in neural networks. Neural Netw 12:309–323
Beven KJ (2001) Rainfall–runoff modelling—the primer. Wiley, Chichester
Chang F-J, Hu H-F, Chen Y-C (2001) Counterpropagation fuzzy-neural network for streamflow reconstruction. Hydrol Process 15:219–232
Chang L-C, Chang F-J, Tsai Y-H (2005) Fuzzy exemplar-based inference system for flood forecasting. Water Resour Res 41:W02005. doi:10.1029/2004WR003037
Chen YH, Chang FJ (2009) Evolutionary artificial neural networks for hydrological systems forecasting. J Hydrol 367:125–137
Chiang YM, Hsu KL, Chang FJ, Hong Y, Sorooshian S (2007) Merging multiple precipitation sources for flash flood forecasting. J Hydrol 340:183–196
Chiu S (1994) Fuzzy model identification based on cluster estimation. J Intell Fuzzy Syst 2(3):267–278
Cigizoglu HK, Kisi O (2006) Methods to improve the neural network performance in suspended sediment estimation. J Hydrol 317:221–238
Daniel TM (1991) Neural networks—applications in hydrology and water resources engineering. In: Proceedings on international hydrology and water resources symposium. Institution of Engineers, Perth, Australia
Farmer JD, Sidorowich JJ (1987) Predicting chaotic time series. Phys Rev Lett 5(59):845–848
Hsu K, Gupta VH, Sorooshian S (1995) Artificial neural network modeling of the rainfall–runoff process. Water Resour Res 31(10):2517–2530
Ikeda S, Ochiai M, Sawaragi Y (1976) Sequential GMDH algorithm and its applications to river flow prediction. IEEE Trans Syst Manag Cybern 6(7):473–479
Imrie CE, Durucan S, Korre A (2000) River flow prediction using artificial neural networks: generalization beyond the calibration range. J Hydrol 233:138–153
Jain A, Srinivasulu S (2004) Development of effective and efficient rainfall–runoff models using integration of deterministic, real-coded genetic algorithms and artificial neural network techniques. Water Resour Res 40(4):W04302. doi:10.1029/2003WR002355
Jain A, Sudheer KP, Srinivasulu S (2004) Identification of physical processes inherent in artificial neural rainfall–runoff models. Hydrol Process 18(3):571–581
Jain SK (2008) Development of integrated discharge and sediment rating relation using a compound neural network. J Hydrol Eng ASCE 13(3):124–131
Jones LK (2000) Local greedy approximation for nonlinear regression and neural network training. Ann Stat 28(5):1379–1389
Maier HR, Jain A, Dandy GC, Sudheer KP (2010) Methods used for the development of neural networks for the prediction of water resources variables in river systems: current status and future directions. Env Mod Softw 25:891–909. doi:10.1016/j.envsoft.2010.02.003
Maiorov VE (1999) On best approximation by ridge functions. J Approx Theory 99:68–94
Nayak PC (2010) Explaining internal behavior in a fuzzy if–then rule-based flood-forecasting model. J Hydrol Eng 15(1):20–28. doi:10.1061/(ASCE)HE.1943-5584.0000146
Nayak PC, Sudheer KP (2008) Fuzzy model identification based on cluster estimation for reservoir inflow forecasting. Hydrol Process 22:827–841. doi:10.1002/hyp.6644
Nayak PC, Sudheer KP, Ramasastri KS (2005) Fuzzy computing based rainfall–runoff model for real time flood forecasting. Hydrol Process 19:955–968. doi:10.1002/hyp.5553
Nayak PC, Sudheer KP, Rangan DM, Ramasastri KS (2004) A neuro-fuzzy computing technique for modeling hydrological time series. J Hydrol 291(1–2):52–66
Parasuraman K, Elshorbagy A, Carey SK (2006) Spiking modular neural networks: a neural network modeling approach for hydrological processes. Water Resour Res 42:W05412. doi:10.1029/2005WR004317
Sajikumar N, Thandaveswara BS (1999) A non-linear rainfall–runoff model using an artificial neural network. J Hydrol 216:32–35
See L, Openshaw S (1999) Applying soft computing approaches to river level forecasting. Hydrol Sci J 44(5):763–779
Shamseldin AY, Nasr AE, O’Connor KM (2002) Comparison of different forms of the multi-layer feed-forward neural network method used for river flow forecasting. Hydrol Earth Syst Sci 6:671–684
Singer AC, Wornell G, Oppenheim A (1992) Codebook prediction: a nonlinear signal modeling paradigm. In: Proceedings of the international conference on acoustics, speech and signal processing, San Francisco, vol 5. IEEE, pp 325–328
Sudheer KP (2005) Knowledge extraction from trained neural network river flow models. J Hydrol Eng ASCE 10(4):264–269
Sudheer KP, Gosain AK, Ramasastri KS (2002) A data-driven algorithm for constructing artificial neural network rainfall–runoff models. Hydrol Process 16:1325–1330
Sudheer KP, Nayak PC, Ramasastri KS (2003) Improving peak flow estimates in artificial neural network river flow models. Hydrol Process 17(1):671–686
Takagi T, Sugeno M (1985) Fuzzy identification of systems and its application to modeling and control. IEEE Trans Syst Man Cybern 15(1):116–132
Tayfur G (2006) Fuzzy, ANN, and regression models to predict longitudinal dispersion coefficient in natural streams. Nord Hydrol 37(2):143–164
Tayfur G, Singh VP (2006) ANN and fuzzy logic models for simulating event-based rainfall–runoff. J Hydraul Eng 132(12):1321–1330
Tayfur G, Singh VP (2011) Predicting mean and bankfull discharge from channel cross-sectional area by expert and regression methods. Water Resour Manag 25(5):1253–1267
Tokar AS, Markus M (2000) Precipitation-runoff modeling using artificial neural network and conceptual models. J Hydrol Eng Am Soc Civil Eng 5(2):156–161
Vernieuwe H, Georgieva O, De Baets B, Pauwels VRN, Verhoest NEC, De Troch FP (2005) Comparison of data-driven Takagi–Sugeno models of rainfall–discharge dynamics. J Hydrol 302(1–4):173–186
Wilby RL, Abrahart RJ, Dawson CW (2003) Detection of conceptual model rainfall–runoff processes inside an artificial neural network. Hydrol Sci J 48(2):163–181
Xiong LH, Shamseldin AY, O’Connor KM (2001) A nonlinear combination of the forecasts of rainfall–runoff models by the first order Takagi–Sugeno fuzzy system. J Hydrol 245(1–4):196–217
Yager R, Filev D (1994) Generation of fuzzy rules by Mountain clustering. J Intell Fuzzy Syst 2(3):209–219
Zhang B, Govindaraju RS (2000) Prediction of watershed runoff using Bayesian concepts and modular neural networks. Water Resour Res 36(3):753–762
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nayak, P.C., Sudheer, K.P. & Jain, S.K. River flow forecasting through nonlinear local approximation in a fuzzy model. Neural Comput & Applic 25, 1951–1965 (2014). https://doi.org/10.1007/s00521-014-1684-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1684-z