Prediction of Monthly River Flow Using Hybridization of Linear Time Series Models and Bayesian network (Case Study: Bakhtiari River)

Document Type : Research Paper

Authors

1 Assistant Professor, Hydrology & Water Resources Engineering Department, Faculty of Water & Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran

2 Technical office expert at West Azarbayjan Regional Water Authority, Urmia, Iran

Abstract

One of the most important issues in water resources management is the preparation and development of appropriate models in order to predict the streamflow more accurately. For this purpose, in the present study, linear time series models (ARMA), intelligent Bayesian network (BN) and BN-ARMA hybrid model have been developed for forecasting the monthly river flow of Bakhtiari River in 1955-2016. The performance of the developed models was evaluated based on statistical indices such as root mean square error (RMSE), correlation coefficient (CC) and Kling-Gupta index (KGE). Among the time series models fitted to the data, the AR (3) model was selected as the appropriate model for monthly stream flow series, with the lowest value of the modified Akaike information criterion equal to 1089.3. The results showed that the AR (3) model with an error of 47.786 (m3/s) has acceptable performance. The monthly river flow from the previous month, two months and five months ago was used to model the monthly river flow using the BN model. The results indicated that with three months intervals, the model performance is optimized and its performance is weakened by increasing the number of inputs. The correlation coefficient, root mean square error and KGE in the best case of BN model in the test stage are 0.826, 45.303 and 0.789 (m3/s), respectively. Next, the combination of BN and ARMA(3.0) models was performed. The results showed that the BN-ARMA hybrid model significantly increases the accuracy of the modeling and reduces the prediction error from 45.303 (m3/s) to 15.021 (m3/s).

Keywords

References

1. احمدی، ف.، دین پژوه، ی.، فاخری فرد، ا و خلیلی، ک. (1393). مقایسه مدل‌های خطی و غیرخطی سری‌زمانی در پیش‌بینی جریان رودخانه (مطالعه موردی: رودخانه باراندوزچای ارومیه). علوم و مهندسی آبیاری. 37 (1): 105-93.
2. احمدی، ف.، رادمنش، ف و میرعباسی نجف آبادی، ر. (1395). کاربرد شبکه‌های بیزین و برنامه‌ریزی ژنتیک در پیش‌بینی جریان روزانه رودخانه (مطالعه موردی: رودخانه باراندوزچای). علوم و مهندسی آبیاری. 39 (4):  223-231.
3. چمنی، م. و روشنگر، ک. (1398). ارزیابی مدل‌ تلفیقی تجزیه‌ی مد تجربی یکپارچه کامل- گاوسی در پیش‌بینی زمانی و مکانی دبی رودخانه. مدیریت آب و آبیاری. 9 (2): 277-289.
4. خلیلی، ک.، احمدی، ف.، بهمنش، ج و وردی نژاد، و. (1391). بررسی تأثیر تغییر اقلیم بر روی دمای هوا و جریان رودخانه‌‌ شهرچای واقع در غرب دریاچه ارومیه با استفاده از تحلیل روند و ایستایی. علوم و مهندسی آبیاری. 35 (4): 108-97.
5. خلیلی، ک.، احمدی، ف.، دین پژوه، ی و بهمنش، ج. (1393). تحلیل رفتار خطی و غیرخطی سری‌های زمانی هیدرولوژیک (مطالعه موردی رودخانه‌های غرب دریاچه ارومیه). تحقیقات منابع آب ایران. 10 (2): 20-12.
6. داننده مهر، ع و مجدزاده طباطبائی، م. (1389). بررسی تأثیر توالی دبی روزانه در پیش­بینی جریان رودخانه­ها با استفاده از برنامه­ریزی ژنتیک. آب و خاک. 24 (2): 333-325.
7. عباسی، ع.، خلیلی، ک.، بهمنش، ج و شیرزاد، ا. (1398). پیش‌بینی خشکسالی با استفاده از مدل ترکیبی GEP-GARCH (مطالعه موردی: ایستگاه سینوپتیک سلماس). تحقیقات آب و خاک ایران. 50 (6): 1317-1329.
8. کاردان مقدم، ح و روزبهانی، ع. (1394). ارزیابی مدل شبکه های بیزین در پیش بینی ماهانل سطح آب زیرزمینی (مطالعۀ موردی: آبخوان بیرجند). مدیریت آب و آبیاری. 5 (2): 151-139.
9. منتصری، م و زمان زاد قویدل، ق. (1393). پیش بینی جریان رودخانه با محاسبات نرم. آب و خاک. 28 (2): 405-394.
10. نبی زاده، م.، مساعدی، ا. و دهقانی، ا. (1391). تخمین هوشمند دبی روزانه با بهره‌گیری از سامانه استنباط فازی- عصبی تطبیقی. مدیریت آب و آبیاری. 2 (1): 80-69.
11. Anupam, S., & Pani, P. (2020). Flood forecasting using a hybrid extreme learning machine-particle swarm optimization algorithm (ELM-PSO) model. Modeling Earth Systems and Environment, 6(1), 341-347.
12. Cain, J. (2001). Planning improvements in natural resource management. Guidelines for using Bayesian networks to support the planning and management of development programmers in the water sector and beyond. Centre for Ecology and Hydrology, Crowmarsh Gifford, Wallingford Press.
13. Chen, Y., Marek, G. W., Marek, T. H., Moorhead, J. E., Heflin, K. R., Brauer, D. K., & Srinivasan, R. (2019). Simulating the impacts of climate change on hydrology and crop production in the Northern High Plains of Texas using an improved SWAT model. Agricultural Water Management, 221, 13-24.
14. Desta, Y., Goitom, H., & Aregay, G. (2019). Investigation of runoff response to land use/land cover change on the case of Aynalem catchment, North of Ethiopia. Journal of African Earth Sciences, 153, 130-143.
15. Dickey, D. A., & Fuller, W. A. (1979). Distribution of the estimators for autoregressive time series with a unit root. Journal of the American statistical association, 74(366), 427-431.
16. Fathian, F., Mehdizadeh, S., Sales, A. K., & Safari, M. J. S. (2019). Hybrid models to improve the monthly river flow prediction: Integrating artificial intelligence and non-linear time series models. Journal of Hydrology, 575, 1200-1213.
17. Gupta, A., Himanshu, S. K., Gupta, S., & Singh, R. (2020). Evaluation of the SWAT Model for Analysing the Water Balance Components for the Upper Sabarmati Basin. In Advances in Water Resources Engineering and Management (pp. 141-151). Springer, Singapore.
18. Kong, X., Zeng, X., Chen, C., Fan, Y., Huang, G., Li, Y., & Wang, C. (2019). Development of a maximum entropy-Archimedean copula-based Bayesian network method for streamflow frequency analysis (A case study of the Kaidu river basin, china). Water, 11(1), 42.
19. Kuikka, S., & Varis, O. (1997). Uncertainties of climatic change impacts in Finnish watersheds: a Bayesian network analysis of expert knowledge. Boreal Environment Research, 2, 109-109.
20. McCann, R. K., Marcot, B. G., & Ellis, R. (2006). Bayesian belief networks: applications in ecology and natural resource management. Canadian Journal of Forest Research, 36(12), 3053-3062.
21. Mehdizadeh, S., & Sales, A. K. (2018). A comparative study of autoregressive, autoregressive moving average, gene expression programming and Bayesian networks for estimating monthly streamflow. Water Resources Management, 32(9), 3001-3022.
22. Mehdizadeh, S., Fathian, F., & Adamowski, J. F. (2019). Hybrid artificial intelligence-time series models for monthly streamflow modeling. Applied Soft Computing, 80, 873-887.
23. Mohammady, M., Moradi, H. R., Zeinivand, H., Temme, A. J. A. M., Yazdani, M. R., & Pourghasemi, H. R. (2018). Modeling and assessing the effects of land use changes on runoff generation with the CLUE-s and WetSpa models. Theoretical and Applied Climatology, 133(2), 459-471.
24. Pollino, C. A., & Hart, B. T. (2007). Bayesian network model in natural resources management. Information sheet prepared by the Integrated Catchment Assessment and Management Centre, Australian National University.
25. Ravindranath, A., Devineni, N., Lall, U., Cook, E. R., Pederson, G., Martin, J., & Woodhouse, C. (2019). Streamflow Reconstruction in the Upper Missouri River Basin Using a Novel Bayesian Network Model. Water Resources Research, 55(9), 7694-7716.
26. Sadoddin, A., Letcher, R. A., Jakeman, A. J., & Newham, L. T. (2005). A Bayesian decision network approach for assessing the ecological impacts of salinity management. Mathematics and Computers in Simulation, 69(2), 162-176.
27. Salas, J. D. (1993). Analysis and modeling of hydrological time series. In: Handbook of Hydrology, Edited by David R, Maidment, McGraw-Hill, New York, 19, 1-19.
28. Wagena, M. B., Goering, D., Collick, A. S., Bock, E., Fuka, D. R., Buda, A., & Easton, Z. M. (2020). Comparison of short-term streamflow forecasting using stochastic time series, neural networks, process-based, and Bayesian models. Environmental Modelling & Software, 126, 104669.
Water and Irrigation Management
Volume 10, Issue 2
October 2020
Pages 233-245

Files

Share

How to cite

Statistics