Forecasting Annual Streamflow Using Autoregressive Integrated Moving Average Model and Fuzzy Regression

Document Type : Research Paper

Authors

Abstract

By Increasing population and the limitation of water resources, forecasting of streamflow using new methods in planning and  management of water resources such  as reservoirs operation has an outstanding importance. For this aim, over the past years time series models have been considered by hydrologists. The goal of this research was to investigate stochastic model (ARIMA) and fuzzy regression performance for the annual streamflow forecasting. The parameter estimation methods of ARIMA model were conditional and unconditional likelihoods. In fuzzy regression model the symmetric and non-symmetric triangular memberships were used regarding the uncertainties of the real systems. For the comparison of ARIMA and fuzzy regression performance, streamflow data  of some  tributaries  of  Urmia  lake  basin  were employed. Results indicated that the unconditional likelihood was the best method among the parameter estimation methods. Comparison between the forecasted and observed streamflow series using the two models revealed that the fuzzy regression had the best fit to the observed streamflow data. The performance of the symmetric triangular membership was better than that of the non- symmetric.

Keywords

Main Subjects


جلال کمالی ا، محمودیان شوشتری م و جلال کمالی ن، 1385. پیش بینی جریان ماهانه ورودی به مخزن سد شهید عباسپور با استفاده از مدل های سری زمانی Box-Jenkins . هفتمین سمینار بین المللی مهندسی رودخانه. دانشگاه شهید چمران اهواز.1-7.
کوره پزان ا،1384. اصول تئوری مجموعه های فازی و کاربردهای آن در مدلسازی مسایل مهندسی منابع آب. انتشارات جهاد دانشگاهی واحد صنعتی امیر کبیر.
مشکانی م، 1371. تحلیل سری زمانی :پیش بینی و کنترل (ترجمه). انتشارات دانشگاه شهید بهشتی .
Box EP and Jenkins GM, 1976. Time Series Analysis: Forecasting and Control. Prentice-Hall, Englewood Cliffs,NJ.
Brockwell PJ and Davis RA, 1987. Time series: Theory and Method. Springer-Verlag, New York.
Carlson RF, MacCormick AJA and Watts DG, 1970. Applications of linear models to four annual streamflow series. Water Resoure Research 6: 1070-1078.
Chang Y and Ayyub B, 2001. Fuzzy  regression methods- a comparative  assessment. Fuzzy Sets and  Systems 119: 187-203.
Delleur JW, Tao  PC and Kavvar ML, 1976. An evaluation of the practically and complexity of some rainfall and  runoff time series models. Water Resoure Research 12 (5), 953-970.
Hojati M, Bector CR and Smimou K, 2005. A simple method for computation of fuzzy linear regression. European  Journal  of  Operational  Research 166:172-184.
Kurunc A, Yurekli K and Cevik O, 2005. Performance of two stochastic approaches for forecasting water quality and streamflow data Yesilrmak River, Turkey. Environmental Modeling & Software. 20: 1195-1200. 
Montanari A, Rosso R and Taqqu S, 1997 .Fractionally differenced ARIMA models applied to hydrologic time series: Identification, estimation, and  simulation. Water  Resources  Research 3(5): 1035-1044.
Myung I, 2003. Tutorial on maximum likelihood estimation. Journal of Mathematical Psychology 47: 90-100.
ObadageAS and Harnpornchai N, 2006. Determination of point maximum likelihood in failure domain using genetic algorithm. International Journal of Pressure Vessels and Piping 83: 276-282.
Radden DT and Woodall WH, 1994. Properties of certain fuzzy linear regression methods. Fuzzy Sets and Systems 64: 361-375.
Salas JD, Delleur JW, Yevjevich V  and  Lane WL, 1988. Applied Modeling of  Hydrologic Time  Series, Water  Resource  Publication (WRP) 192-194.
Shine DW and Lee JH, 2000. Consistency of the maximum likelihood estimators for nonstationary ARMA regressions with time trends. Journal of Statistical Planning and Inference 87: 55-68.
Tanaka H and Uejima S, 1982. Linear regression analysis with fuzzy model. IEEE Trans. Systems, Man, Cybernet 12:903-907.
Toly C and Wang MJ, 1999. Forecasting methods using fuzzy concepts. Fuzzy sets and systems. 105 (3): 339-352 .
Tseng YH, Durbin P and Tzeng GH,  2001. Using fuzzy piecewise regression analysis to predict the nonlinear time series of turbulent flows with automatic chang- point detection. Flow, Turbulence and Combustion. 67: 81-106.
Valenzuela O, Marquez L, Pasadas M and Rojas I, 2004. Automatic  identification  of  ARIMA time series by expert systems using paradigms of artificial intelligence. Mongrafias del  Seminaro Garcia  de Galdeeano 31:425-435.
Wu, HCH, 2003. Fuzzy estimates of regression parameters in linear regression models for imprecise input and output data. Computational Statistics & Data Analysis 42: 203-217.
Wu JS, ASCE PEM, Han J, Annambhotla S and Bryant S, 2005. Artificial neural networks for forecasting watershed runoff and streamflows. Journal of Hydrology Engineering. 10 (3):216-222.
Yen KK, Ghoshary S and Roig G, 1999.A linear model using triangular fuzzy number coefficients. Fuzzy sets and systems 106:167-177.
Zadeh LA, 1965. Fuzzy sets and information. Control 8, 338-353.