Daily streamflow prediction using support vector machine-artificial flora (SVM-AF) hybrid model
- PDF / 2,425,447 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 10 Downloads / 205 Views
RESEARCH ARTICLE - HYDROLOGY
Daily streamflow prediction using support vector machine‑artificial flora (SVM‑AF) hybrid model Reza Dehghani1 · Hassan Torabi Poudeh2 · Hojatolah Younesi2 · Babak Shahinejad2 Received: 15 May 2020 / Accepted: 8 August 2020 © Institute of Geophysics, Polish Academy of Sciences & Polish Academy of Sciences 2020
Abstract Precise estimation of river flow in catchment areas has a significant role in managing water resources and, particularly, making firm decisions during flood and drought crises. In recent years, different procedures have been proposed for estimating river flow, among which hybrid artificial intelligence models have garnered notable attention. This study proposes a hybrid method, so-called support vector machine–artificial flora (SVM-AF), and compares the obtained results with outcomes of wavelet support vector machine models and Bayesian support vector machine. To estimate discharge value of the Dez river basin in the southwest of Iran, the statistical daily watering data recorded by hydrometric stations located at upstream of the dam over the years 2008–2018 were investigated. Four performance criteria of coefficient of determination (R2), rootmean-square error, mean absolute error, and Nash–Sutcliffe efficiency were employed to evaluate and compare performances of the models. Comparison of the models based on the evaluation criteria and Taylor’s diagram showed that the proposed hybrid SVM-AF with the correlation coefficient R2 = 0.933–0.985, root-mean-square error RMSE = 0.008–0.088 m3/s, mean absolute error MAE = 0.004–0.040 m 3/s, and Nash-Sutcliffe coefficient NS = 0.951–0.995 had the best performance in estimating daily flow of the river. The estimation results showed that the proposed hybrid SVM-AF model outperformed other models in efficiently predicting flow and daily discharge. Keywords Artificial flora · Prediction · Streamflow · Support vector machine
Introduction Precise estimation of river flow is the most important factor in managing flood and preventing economic losses. Therefore, it is of necessity to secure a viable method for estimating river flow (Beven and Kirkby 1979; Duan et al. 1992, 1994; Cameron et al. 1999; Dolling and Eduardo 2002; Guven and Kisi 2011a, b; Coken et al. 2016). Prediction models of river flow are appropriate tools for managing water resources. Predicting the probability of surface runoff and having prior information of available water amount can be put into good use, e.g., (a) facilitating irrigation, production of electricity, and flood control; (b) ensuring better water allocations to industries and agriculture; (c)
* Hassan Torabi Poudeh [email protected] 1
Lorestan University, Khorramabad, Iran
Department of Water Engineering, Lorestan University, Khorramabad, Iran
2
controlling water pollution and expanding recreational and green areas; and (d) reaping economic profits (Jakeman and Hornberger 1993; Hsu et al. 1995; Haykin 1998; Guven and Kisi 2011a, b; Kumar and Jothiprakash 2013). Statistical models and r
Data Loading...
