Evaluation of the efficiency of custom and computerized methods for reconstruction of monthly flow time series in the hydrometric stations

Document Type : Technical Note (5 pages)

Authors

1 Assistant Professor, Water Science and Engineering Department, Faculty of Agriculture, Bu-Ali Sina University, Hamedan. Email: hanozari@yahoo.com

2 M.Sc. Student in Water Resources Engineering, Faculty of Agriculture, Bu-Ali Sina University, Hamedan

Abstract

The lack of complete data should not be the cause for disregarding the hydrological condition and the long-term forecasts for performing a hydrological project in one region. Therefore, various researchers have used different methods such as Ratio Analysis, Fragment, and Thomas-fiering for the reconstruction of incomplete flow data in hydrometric stations. So, in this study, the accuracy of these methods and computerized methods such as, artificial neural network, hybrid wavelet-neural network and support vector machine have been investigated and compared. The results showed that the computerized methods have the higher accuracy than the other three methods. Comparison amongst the computerized methods shows that the artificial neural network method (R^2=0.98,RMSE=6.18,SE=0.476), the support vector machine method (R^2=0.902,RMSE=6.074,SE=0.486) and the hybrid wavelet-neural method (R^2=0.889,RMSE=6.96,SE=0.54) ranking first, second and third, respectively. Although, these three methods of artificial neural network, hybrid wavelet-neural network and support vector machine have not significant difference in comparison with each other's, but the support vector machine constructed the data in the less time and with the more ease and hence has an advantage in comparison with the other methods.

Keywords

Main Subjects

References

Abdollah Pour Azad M, Sattari M T (2015) Forecasting daily river flow of ahar chay river using artificial neural networks (ANN) and comparison with adaptive neuro fuzzy inference system (ANFIS). Journal of Water and Soil Conservation 22(1):287-298 (In Persian)
Ahmadi F, Radmanesh F, Mirabbasi Najaf Abadi R (2015) Comparison between genetic programming and support vector machine methods for daily River flow forecasting. Journal of Water and Soil 28(6):1162-1171 (In Persian)  
Coulibaly P, Evora N D (2007) Comparison of neural network methods for infilling missing daily weather records .Journal of Hydrology 341:27–41
Ghafari GH, Vafakhah M (2013) Simulation of rainfall-runoff process using artificial neural network and adaptive neuro fuzzy interface system. Journal of Watershed Management Research 4(8):120-136 (In Persian)
Jalilian H , Rostamizad GH , Arekhi S (2012) Applicability of various reconstruction methods of hydrometric data (case study: sefidroud basin). Journal of Range and Watershed Management 65(3):329-340 (In Persian)
Matinzadeh M M , Fattahi R, Shahyan Nejad M, Abdollahi KH (2011) Reconstruction of annual maximum 24-h rainfall data using fuzzy regression in ch&b province. Journal of Iran Water Research 5(8):186-179 (In Persian)
Montaseri M, Heydari J (2016) A comparison among the performance of the stochastic models in generating the monthly streamflow and rainfall data. Iran-Water Resources Research 11(3):69-84 (In Persian)
Naghadi R, Shayan Nejad M, Sadati Nejad S J (2010) Comparison of different methods for estimating of monthly discharge missing data in grand karoon river basin. Journal of Watershed Management Research 1(1):59-73 (In Persian)
Nozari H, Kadkhodahoseini M (2014) Neural network and test performance ratios and differences in data reconstruction of the stations. In: 5th National Conference on Water Resources Management
Pourreza Bilondi M, Khashei Siuki A, Sadeghi Tabas S (2015) Daily rainfall-runoff modeling with least square support vector machine(ls-svm). Journal of Water and Soil Conservation 21(6):293-304 (In Persian)
Roushangar K, Zarghmi M, Tarlani Azar M (2015) Forecasting daily urban water consumption using conjunctive evolutionary algorithm and wavelet transform analysis. Journal of Water and Wastewater 26(4):110-120 (In Persian)
Sadati Nejad S J, Naghadi R, Shayan Nejad M (2011) Application of fuzzy linear regression for predicting annual discharge missing data in hydrometric station compared with other conventional method. Journal of Water and Soil Conservation 17(4):67-86 (In Persian)
Sattari M T, Joudi A R, Nahrein F (2014) Monthly rainfall prediction using artificial neural networks and M5 model tree (case study: station of ahar). Physical Geography Research Quarterly 46(2):247-260 (In Persian)
Silva AT, Portela M M (2012) Disaggregation modeling of monthly stream flows using a new approach of the method of fragments. Hydrological Sciences Journal 57(5):942-955
Tfwala S, Min Wang Y, Chieh Lin Y (2013) Prediction of missing flow records using multilayer perceptron and coactive neurofuzzy inference system. Scientific World Journal 2013:1-7
Iran-Water Resources Research
Volume 13, Issue 4
January 2018
Pages 174-178

Files

History

  • Receive Date: 09 October 2016
  • Revise Date: 23 April 2017
  • Accept Date: 26 April 2017

Share

How to cite

Statistics