Caspian Sea Level Predication Based on Fuzzy Regressor System

Document Type : Research Paper


1 Ph.D. Student, Dept. of Cumputer Eng., Sari Branch, Islamic Azad University, Sari

2 Assist. Prof., Dept. of Camputer Eng., Mashhad Branch, Islamic Azad University, Mashad

3 Assist. Prof. and Manger of Enironmental Sea Protection Group, Caspian Sea National Research Center, Sari


The level of the Caspian Sea as the world's largest limited river basin is constantly fluctuating. The Importance of forecasting the Caspian Sea water level, in order to few meters fluctuation in recent decades and preventing future loss is considered to be essential. The agentes of water level regulator in Caspian sea are hydro climatology factors such as input series including rivers, rainfall and underground water and output including evaporation and discharge to Ghareboghaz gulf. Statistical techniques were used for modeling processes. Fuzzy techniques were also used for identification of the system and the time series prediction. In this article, a prediction of level fluctuating of this water area was suggested using combination of statistical combining statistical techniques and Fuzzy Systems. The Results of prediction experiments is exerted on the past data and advantage of the proposed method was shown according to the accuracy. Finally a 10-year forecast of the Caspian Sea level was presented.


Aladin, N., and Plotnikov, I. (2004). The Caspian sea, Lake Basin Management Initiative. The Caspian sea, Lake Basin Management Initiative, Russia.. Ghangherme, A. (2004). The oscillatory behavior of the water level in the Caspian sea water balance. Workshop on Caspian Sea Issues, Particulary the Management Governors and Mayors of the Coastal Province of Gilan, Rasht.. Ghangherme, A., and Ramesht, M. H. (2005). Can the fluctuations of the Caspian sea be controlled?. Isfahan Univerisity, Isfahan. Malinin, V. M. (2004). The problem of the Caspian sea level forescast. Caspian Sea Natioanl Research Center, Sari. Klige, R. K. (1992). The history of variations in the level of the caspian sea. Caspian Sea National Research Center, Sari. Bolgov, M. V., Trubetskova, M. D., and Filimonova, M. K. (2004). On the problem of the Caspian sea level forecasting. Water Problems Institute, Russian Academy of Sciences, Russia. Bolgov, M.V. (2005). Stochastic models in a problem of the Caspian sea level forecasting. ISSH International Symposium on Stochastic Hydraulics, Nijmegen, Netherlands. , 23-27 Ghangherme, A. (1997). Continental changing and behavior of Caspian sea level. Armed Forces Geographical Organization, Tehran. Montgomeri, D. C., and Peck, E. A. (2003). Introduction to linear regression analysis. 2nd Ed., Translated by Razavi Parizi, Shahid Bahonar University, Kerman.. Box, G.P., and Jenkins, G.M. (1976). Time series analysis: Forecasting and control. Holden-day Inc., San Francisco, CA.. Tseng, F., Tzeng, G., Yu, H., and Yuan, B. (2001). Fuzzy ARIMA model for forecasting the foreign exchange market. Fuzzy Sets and Systems. 118, 9-19 Jones, A. J. (2004). New tools in non-linear modelling and prediction. Computational Management Science. 1, 109-149 Tanaka, H., Uejima, H., and Asai, K. (1982). Linear regression analysis with fuzzy model. IEEE Trans. Systems Man Cabernet. 12, 903-907 Pouzols, M., Lendasse, A., and Barriga, A. (2008). Fuzzy inference based autoregressors for time series prediction using nonparametric residual variance estimation. International Conference on Fuzzy Systems (IEEE), Sofia, Bulgaria. , 613-618 Ramezai Mozirji, F., and Yaghoobi, M. (2009). New method in time series predication based on fuzzy autoregressors. 3rd Joint Congress on Fuzzy and Intelligent System, Yazd. Bargiela, A., Pedrycz, W., and Nakashima, T. (2007). Multiple regression with fuzzy data.. Fuzzy Sets and Systems. 158, 2169-2188 Wang, L., and Mendel, J. M. (1992). Generating fuzzy rules by learning from examples. IEEE Transactions on Systems, Man, and Cybernetics. 22 (4), 1414-1427 CSNR. (2009). Water and meterological databases.