Predicting monthly streamflow using artificial neural networks and wavelet neural networks models

被引:13
作者
Yilmaz, Muhammet [1 ]
Tosunoglu, Fatih [1 ]
Kaplan, Nur Huseyin [2 ]
Unes, Fatih [3 ]
Hanay, Yusuf Sinan [4 ]
机构
[1] Erzurum Tech Univ, Dept Civil Engn, Erzurum, Turkey
[2] Erzurum Tech Univ, Dept Elect & Elect Engn, Erzurum, Turkey
[3] Iskenderun Tech Univ, Dept Civil Engn, Antakya, Turkey
[4] Akdeniz Univ, Dept Comp Engn, Antalya, Turkey
关键词
Additive wavelet transform; Discrete wavelet transform; Artificial neural networks; Monthly streamflow; Prediction; SUSPENDED SEDIMENT DATA; DOMINANT PERIODICITIES; IMAGE FUSION; SHORT-TERM; TRANSFORMS; FUZZY; TRENDS; ANN; PRECIPITATION; TEMPERATURE;
D O I
10.1007/s40808-022-01403-9
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Improving predicting methods for streamflow series is an important task for the water resource planning, management, and agriculture process. This study demonstrates the development and effectiveness of a new hybrid model for streamflow predicting. In the present study, artificial neural networks (ANNs) coupled with wavelet transform, namely Additive Wavelet Transform (AWT), are proposed. Comparative analyses of Discrete wavelet transform (DWT) based ANN and conventional ANN techniques with the proposed method were presented. The analysis of these models was performed with monthly streamflow series for four stations on the coruh Basin, which is located in northeastern Turkey. The Bayesian regularization backpropagation training algorithm was employed for the optimization of the ANN network. The predicted results of the models were analyzed by the root mean square error (RMSE), Akaike information criterion (AIC), and coefficient of determination (R-2). The obtained revealed that the proposed hybrid model represents significant accuracy compared to other models, and thus it can be a useful alternative approach for predicting studies.
引用
收藏
页码:5547 / 5563
页数:17
相关论文
共 57 条
[51]  
2
[52]   Determination of Trends and Dominant Modes in 7-Day Annual Minimum Flows: Additive Wavelet Transform-Based Approach [J].
Tosunoglu, Fatih ;
Kaplan, Nur Huseyin .
JOURNAL OF HYDROLOGIC ENGINEERING, 2018, 23 (12)
[53]   Prediction of Millers Ferry Dam Reservoir Level in USA Using Artificial Neural Network [J].
Unes, Fatih ;
Demirci, Mustafa ;
Kisi, Ozgur .
PERIODICA POLYTECHNICA-CIVIL ENGINEERING, 2015, 59 (03) :309-318
[54]   Generalized daubechies wavelet families [J].
Vonesch, Cedric ;
Blu, Thierry ;
Unser, Michael .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2007, 55 (09) :4415-4429
[55]  
Wang W., 2003, NAT SCI, V1, P67
[56]   Predicting monthly streamflow using data-driven models coupled with data-preprocessing techniques [J].
Wu, C. L. ;
Chau, K. W. ;
Li, Y. S. .
WATER RESOURCES RESEARCH, 2009, 45
[57]   Evaluation of Trends and Dominant Modes in Maximum Flows in Turkey Using Discrete and Additive Wavelet Transforms [J].
Yilmaz, Muhammet ;
Tosunoglu, Fatih ;
Kaplan, Nur Huseyin .
JOURNAL OF HYDROLOGIC ENGINEERING, 2020, 25 (11)