Hydrology and Earth System Sciences www.hydrol-earth-syst-sci.net 1027-5606 1607-7938 12 1 2008 10.5194/hess-12-123-2008 http://www.hydrol-earth-syst-sci.net/12/123/2008/ http://www.hydrol-earth-syst-sci.net/12/123/2008/hess-12-123-2008.html http://www.hydrol-earth-syst-sci.net/12/123/2008/hess-12-123-2008.pdf 123 139 2008-01-30 Comparison of Artificial Intelligence Techniques for river flow forecasting M. Firat mfirat@pamukkale.edu.tr Research Assistant (PhD), Pamukkale University Civil Engineering Department, Denizli, Turkey The use of Artificial Intelligence methods is becoming increasingly common in the modeling and forecasting of hydrological and water resource processes. In this study, applicability of Adaptive Neuro Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN) methods, Generalized Regression Neural Networks (GRNN) and Feed Forward Neural Networks (FFNN), and Auto-Regressive (AR) models for forecasting of daily river flow is investigated and Seyhan River and Cine River was chosen as case study area. For the Seyhan River, the forecasting models are established using combinations of antecedent daily river flow records. On the other hand, for the Cine River, daily river flow and rainfall records are used in input layer. For both stations, the data sets are divided into three subsets, training, testing and verification data set. The river flow forecasting models having various input structures are trained and tested to investigate the applicability of ANFIS and ANN and AR methods. The results of all models for both training and testing are evaluated and the best fit input structures and methods for both stations are determined according to criteria of performance evaluation. Moreover the best fit forecasting models are also verified by verification set which was not used in training and testing processes and compared according to criteria. The results demonstrate that ANFIS model is superior to the GRNN and FFNN forecasting models, and ANFIS can be successfully applied and provide high accuracy and reliability for daily river flow forecasting. Arena, C., Cannarozzo, M., and Mazzola, M. R.: Multi-year drought frequency analysis at multiple sites by operational hydrology – A comparison of methods, Phys. Chem. Earth, 31, 1146–1163, 2006. ASCE Task Committee.: Artificial neural networks in hydrology-II: Hydrologic applications, J. Hydrol. Eng., ASCE, 5(2), 124–137, 2000. Box, G. E. P. and Jenkins, G.: Time Series Analysis, Forecasting and Control, Holden-Day, San Francisco, CA, 1970. BuHamra, S., Smaoui, N., and Gabr, M.: The Box–Jenkins analysis and neural networks: prediction and time series modeling, Appl. Math. Model., 27, 805–815, 2003. Celikoglu, H. B.: Application of radial basis function and generalized regression neural networks in non-linear utility function specification for travel mode choice modeling, Math. Comput. Model., 44, 640–658, 2006. Celikoglu, H. B. and Cigizoglu, H. K.: Public transportation trip flow modeling with generalized regression neural Networks, Adv. Eng. Softw., 38, 71–79, 2007. Chen, S. H., Lin, Y. H., Chang, L. C., and Chang, F. J.: The strategy of building a flood forecast model by neuro-fuzzy network, Hydrol. Process., 20, 1525–1540, 2006. Chang, F. J. and Chang, Y. T.: Adaptive neuro-fuzzy inference system for prediction of water level in reservoir, Adv. Water Res., 29, 1–10, 2006. Chang, F. J, Hu, H. F, and Chen, Y.C.: Counter propagation fuzzy–neural network for river flow reconstruction, Hydrol. Process., 15, 219–232, 2001. Chang, F. J., Chang, L. C., and Huang, H. L.: Real-time recurrent learning neural network for stream-flow forecasting, Hydrol. Process., 16, 2577–2588, 2002. Cigizoglu, H. K.: Generalized regression neural network in monthly flow forecasting, Civ. Eng. Environ. Syst., 22(2), 71–84, 2005. Cigizoglu, H. K. and Alp, M.: Generalized regression neural network in modeling river sediment yield, Adv. Eng. Softw., 37, 63–68, 2006. Dawson, C. W., Harpham, C., Wilby, R. L., and Chen, Y.: Evaluation of artificial neural network techniques for flow forecasting in the River Yangtze, China, Hydrol. Earth Syst. Sci., 6, 619–626, 2002. Dibike, Y. B. and Solomatine, D. P.: River Flow forecasting Using Artificial Neural Networks, Phys, Chem. Earth (B), 26, 1–7, 2001. Firat, M. and Güngör, M.: Estimation of the Suspended Concentration and Amount by using Artificial Neural Networks, IMO Technical Journal, 15(3), 3267–3282, 2004. Firat, M. and Güngör, M.: River flow estimation using adaptive neuro fuzzy inference system, Math. Comput. Simulat., 75(3–4), 87–96, 2007. Firat, M.: Watershed modeling by adaptive Neuro- fuzzy inference system approach. Doctor of Philosophy Thesis, Pamukkale University, Turkey, 2007 (in Turkish). Jain, A. and Kumar, A. M.: Hybrid neural network models for hydrologic time series forecasting, Appl. Soft Comput., 7, 585–592, 2007. Jang, J. S. R., Sun, C. T, and Mizutani, E.: Neuro-Fuzzy and Soft Computing, PrenticeHall, ISBN 0-13-261066-3, 607 s., United States of America, 1997. Kim, B., Lee, D.W ., Parka, K. Y., Choi, S. R., and Choi, S.: Prediction of plasma etching using a randomized generalized regression neural network, Vacuum, 76, 37–43, 2004. Kisi, Ö.: Daily pan evaporation modelling using a model-fuzzy computing technique, J. Hydrol., 329(3–4), 636–646, 2006. Komornik, J., Komornikova, M., Mesiar, R., Szökeova, D., and Szolgay, J.: Comparison of forecasting performance of nonlinear models of hydrological time series, Phys. Chem. Earth., 31, 1127–1145, 2006. Liong, S. Y., Lim, W. H, Kojiri, T., and Hori, T.: Advance Flood forecasting for Flood stricken Bangladesh with a fuzzy reasoning method, Hydrol. Process., 14, 431–448, 2000. Mahabir, C., Hicks, F. E, and Fayek, A. R.: Application of fuzzy logic to the seasonal runoff, Hydrol. Process., 17, 3749–3762, 2000. Mohammadi, K., Eslami, H. R., and Kahawita, R.: Parameter estimation of an ARMA model for river flow forecasting using goal programming, J. Hydrol., 331, 293–299, 2006. Nagy, H. M., Watanabe, K., and Hirano, M.: Prediction of Sediment Load concentration in Rivers using Artificial Neural Network Model, J. Hydr. Eng., 128, 588–595, 2002. Nayak, P. C., Sudheer, K. P., and Ramasastri, K. S.: Fuzzy computing based rainfall-runoff model for real time flood forecasting, Hydrol. Process., 17, 3749–3762, 2004a. Nayak, P. C., Sudheer, K. P., Rangan, D. M, Ramasastri, K. S.: A Neuro Fuzzy computing technique for modeling hydrological time series, J. Hydrol., 29, 52–66, 2004b. Owen, J. S., Eccles, B. J., Choo, B. S., and Woodings, M. A.: The application of auto–regressive time series modeling for the time-frequency analysis of civil engineering structures, Eng. Struct., 23, 521–536, 2001. Ramadhas, A. S., Jayaraja, S., Muraleedharan, C., and Padmakumar, K.: Artificial neural networks used for the prediction of the cetane number of biodiesel, Renew. Ener., 31, 2524–2533, 2006. Sajikumar, N. and Thandaveswara, B.S.: A non-linear rainfall–runoff model using an artificial neural network, J. Hydrol., 216, 32–55, 1999. Sudheer, K. P. and Jain, A.: Explaining the internal behaviour of artificial neural network river flow models, Hydrol. Process., 18, 833–844, 2004. Tingsanchali, T. and Guatam, M. R.: Application of tank, NAM, ARMA and neural network models to flood forecasting, Hydrol. Process., 14, 2473–2487, 2000. Thomas, H. A. and Fiering, M. B.: Mathematical synthesis of streamflow sequences for the analysis of river basin by simulation, in: Design of Water Resources Systems, edited by: Mass, A., Harvard University Press, Cambridge, MA, 459–493, 1962. Toth, E., Brath, A., and Montanari, A.: Comparison of short-term rainfall prediction models for real-time flood forecasting, J. Hydrol., 239, 132–147, 2000. Şen Z.: Fuzzy Logic and Foundation", ISBN 9758509233, Bilge Kültür Sanat Publisher, Istabul, 172 pp., 2001. Şen, Z. and Altunkaynak, A.: A comparative fuzzy logic approach to runoff coefficient and runoff estimation, Hydrol. Process., 20, 1993–2009, 2006. Yevjevich, V.: Fluctuations of Wet and Dry Years. Part-I. Research Data Assembly and Mathematical Models, Hydrology Paper 1, Colorado State University, Fort Collins, CO, 1963. Zadeh, L. A.: Fuzzy sets, Information and Control, 8(3), 338–353, 1965. Zhang, G. P.: Time series forecasting using a hybrid ARIMA and neural network model, Neurocomputing, 50, 159–175, 2003.