Forecasting of Inflow to Kamal Saleh Reservoir using Soft Computing

Document Type : Original Article

Authors

1 Assistant Professor of civil engineering, Arak University

2 Ph.D Student of Water Engineering, Young Researcher club, Tabriz Branch, Islamic Azad University, Tabriz, Iran

3 Manager of surface water, Markazi Regional Water Authority

Abstract

Forecasting of inflow to reservoirs is essential in efficient planning and operation of water resources. In this research, the application of two different intelligent models including Artificial Neural Networks (ANNs) and Adaptive Neuro-fuzzy Inference System (ANFIS) technique based on subtractive clustering method are investigated  for forecasting inflow to Kamal Saleh reservoir in Markazi province, Iran. For this purpose precipitation and discharge data in a 31-year statistic period (1981-2011) were used and forecasting of inflow was done in the daily and monthly time steps. The amount of discharge and precipitation in previous time steps were used as input patterns for models.Both ANNs and ANFIS models had very acceptable performances at daily and monthly forecasts of inflow based on the error measures; R, RMSE and MAE, however ANFIS model performance was better than ANNs (less than 3%). Using seasonality coefficient (α) improved the performance of models in monthly forecasts. In the following, the effect of large scale climate variables including North Atlantic Oscillation (NAO) index and Southern Oscillation Index (SOI) examined on monthly forecast that was resulted from the best input pattern in optimized model of the previous section. The results showed that using climatic indices in input combination can improve the performance of model to forecast the inflow. Although SOI had greater impact on improving the monthly inflow forecast. So that the statistical indices to evaluate the error of ANFIS model including R, RMSE and MAE obtained as 0.91, 3.56 and 3.73 respectively, this shows the potential of this way to increase the precision by improving the evaluation criteria about 11%, 9% and 11%, respectively.

Keywords


 
انوری تفتی، ص.، ب. ثقفیان و س. مرید. 1390. پیش­بینی جریان رودخانه با مدل­های ANN و بررسی عملکرد آن با ورودی های SIO. مجله پژوهش­های حفاظت آب و خاک. سال هجدهم، شماره اول، ص 180-163.
عبداله­پور آزاد، م. ر. و م. ت. ستاری. 1394. پیش­بینی جریان روزانه رودخانه اهرچای با استفاده از روش­های شبکه‌های عصبی مصنوعی (ANN) و مقایسه آن با سیستم استنتاج فازی-عصبی تطبیقی (ANFIS). مجله پژوهش‌های حفاظت آب و خاک. جلد بیست و دوم، شماره اول، ص 298-287.
Chang F. J. and Y. C. Chen. 2001. Counter propagation fuzzy-neural network modelling approach to real time streamflow prediction. Journal of Hydrology, 245:153-164.
Chiu, S., 1994. Fuzzy model identification based on cluster estimation. Journal of Intelligent and Fuzzy Systems 2 (3): 267–278.
Haykin, S., 1999. Neural Networks: A Comprehensive Foundation, Prentice-Hall, Upper Saddle River, New Jersey, 842pp.
Hsu K., H. V.Gupta and S. Sorooshian. 1995. Artificial neural network modelling of the rainfall-runoff process. Water Resources Research, 31(10):2517-2530.
Imrie, C. E., S. Durucan and A. Korre. 2000. River flow prediction using artificial neural networks: generalisation beyond the calibration range. Journal of Hydrology, 233(1): 138-153.
Jang J. S. R. 1993. ANFIS: adaptive-network-based fuzzy inference system IEEE. Trans System Manage Cybernet. 23(3):665–685.
Karayiannis, N. B., and A. N.Venetsanopoulos. 1993.Artifical Neural Network: Learning Algorithms, Performance Evaluation, and Application. Kluwer Academic Publisher, Boston.
Kisi, O. 2004. River flow modelling using artificial neural networks. Journal of HydrologicEngineering, 9(1): 60-63.
Kisi O. 2007. Streamflow forecasting using different artificial neural network algorithms. ASCE Journal of Hydrologic Engineering, 12 (5):532-539.
Kisi O. 2008. River flow forecasting and estimation using different artificial neural network techniques. Hydrology Research, 39(1):27-40.
Kisi, O. and H. Kerem Cigizoglu. 2007. Comparison of different ANN techniques in river flow prediction. Civil Engineering and Environmental Systems, 24(3): 211-231.
Lohani A. K., R. Kumar and R. D. Singh. 2012. Hydrological time series modelling: A comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques. Journal of Hydrology, 442–443: 23–35.
Maier H. R. and G. Dandy. 2000. Neural networks for prediction and forecasting of water resources variables: areview of modelling issues and applications. Environmental Modelling and Software, 15(10):1-124.
Nayak, P. C., K. P.Sudheer, D.M.Rangan and K.S. Ramasastri. 2004. A neuro-fuzzy computing technique for modelling hydrological time series. Journal of Hydrology, 29:52-66.
Sanikhani H. and O. Kisi. 2012. River flow estimation and forecasting by using two different adaptive neuro-fuzzy approaches. Water Resources Management, 26:1715-1729.
Sattari M. T., K. Yurekli, M. Pal. 2012. Performance evaluation of artificial neural network approaches in forecasting reservoir inflow. Applied Mathematical Modeling, 36:2649-2657.
Tamea, S., F. Laio and L. Ridolfi. 2005. Probabilistic nonlinear prediction of river flows. Water resources research, 41(9).
Vernieuwe H., O. Georgieva, B. De Baets, V. Pauwels, N. E.Verhoest, and F.P. De Troch. 2005. Comparison of data-driven Takagi–Sugeno models of rainfall–discharge dynamics. Journal of Hydrology, 302(1):173-186.
Wang, W. C., K. W.Chau.C. T. Cheng and L. Qiu. 2009. A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. Journal of Hydrology, 374: 294–306.