Document Type : Research Article

Authors

1 Shahid Chamran University

2 Shahrekord University

Abstract

Accurate estimation of river flow can have a significant importance in water resources management. In this study, Genetic programming (GP) and Support Vector Machine (SVM) methods were used to forecast daily discharge of Barandoozchay River. The daily discharge data of Barandoozchay River measured at the Dizaj hydrometric station during 2007 to 2011 was used for modeling, which 80% of the data used for training and remaining 20% used for testing of models. The results showed that in the both of considered methods, the models including discharges of one, two and three days ago had higher accuracy in verification step and the accuracy of models decreased with increasing discharge values. Comparing the performance of GP and SVM methods indicated that, however the accuracy of the GP method with the R=0.978 and RMSE=1.66 (m3/s) was slightly more than SVM method with R=0.976 and RMSE=1.80 (m3/s), but the SVM is easier than GP method. Thus, the SVM method can be used as an alternative method in forecasting daily river discharge.

Keywords

1- داننده مهر ع. و مجدزاده طباطبائی م.ر. 1389. بررسی تأثیر توالی دبی روزانه در پیش بینی جریان رودخانه ها با استفاده از برنامه ریزی ژنتیک. -نشریه آب و خاک دانشگاه فردوسی مشهد. 24(2): 325-333.
2- فربودنام ن.، قربانی م.ع. و اعلمی م.ت. 1388. پیش بینی جریان رودخانه با استفاده از برنامه ریزی ژنتیک (مطالعه موردی: رودخانه لیقوان). مجله دانش آب و خاک (دانشگاه تبریز). 19(4): 123-107.
3- قبادیان ر.، قربانی م.ع. و خلج م. 1392. بررسی عملکرد روش برنامه ریزی بیان ژن در روندیابی سیلاب رودخانه زنگمار در مقایسه باروش موج دینامیکی. نشریه اب و خاک. 27 (3): 602-592.
4- قربانی م.ع.، شیری ج. و کاظمی ه. 1389. تخمین بیشینه، متوسط و کمینه دمای شهر تبریز با استفاده از روش های هوش مصنوعی. مجله دانش آب و خاک (دانشگاه تبریز). 20(1): 104-87.
5- نیک بخت شهبازی ع.ر. 1388. کاربرد ماشین بردار پشتیبان در پیش بینی جریان رودخانه. هشتمین کنفرانس هیدرولیک ایران. دانشکده فنی دانشگاه تهران.
6- Adamowski J., and Prasher S.O. 2012. Comparison of machine learning methods for runoff forecasting in mountainous watersheds with limited data. Journal of Water and Land Development, 17(7-8): 89–97 .
7- Alvisi S., Mascellani G., Franchini M., and Bardossy A. 2005. Water level forecasting through fuzzy logic and artificial neural network approaches. J Hydrol Earth Sys Sci., 2:1107-1145.
8- Aytek A., and Kisi O. 2008. A genetic programming approach to suspended sediment modeling. Journal of Hydrology 351: 288-298.
9- Chen S.T., and P.S. Yu .2007. Real-time probabilistic forecasting of flood stages. Journal of Hydrology, 340: 63-77.
10- Ferreira C. 2001. Gene expression programming: a new adaptive algorithm for solving problems.Complex Syst 13: 87-129.
11- Ghorbani M.A., Kisi O. and Aalinezhad M. 2010. A probe into the chaotic nature of daily streamflow time series by correlation dimension and largest Lyapunov methods Applied Mathematical Modelling, 34: 4050–4057
12- Guven A. 2009. Linear genetic programming for time-series modeling of daily flow rate. J. Earth Syst. Sci, 118(2):157-173.
13- Hamel L. 2009. Knowledge Discovery with Support Vector Machines, Hoboken, N.J. John Wiley.
14- Khu S.T., Liong S.Y., Babovic V., Madsen H., and Muttil N. 2001. Genetic programming and its application in real- time runoff forming. Journal of American Water Resources Association, 37 (2): 439-451.
15- Koza J.R. 1992. Genetic Programming: on the programming of computers by means of natural selection. Cambridge, MA: MIT Press.
16- Pai P.F., and Hong W.C. 2007. A recurrent support vector regression model in rainfall forecasting. Hydrological Process, 21:819-827.
17- Vapnik V.N. 1998. Statistical Learning Theory. Wiley, New York.
18- Yu P.S., Chen S.T., and Chang I.F. 2005. Flood stage forecasting using support vector machines. Geophysical Research Abstracts,Vol.7,04176.
19- Yu P.S, Chen S.T., and Chang I.F. 2006. Support vector regression for real-time flood stage forecasting. Hydrology, 328: 704-716.
20- Zahiri A., and Azamathulla H.Md. 2014. Comparison between linear genetic programming and M5 tree models to predict flow discharge in compound channels. Neural Comput & Applic, 24:413–420.
CAPTCHA Image