Daily streamfow prediction using support vector machine artifcial fora (SVM AF) hybrid model

Precise estimation of river fow in catchment areas has a signifcant role in managing water resources and, particularly, mak ing frm decisions during food and drought crises. In recent years, diferent procedures have been proposed for estimating river fow, among which hybrid artifcial intelligence models have garnered notable attention. This study proposes a hybrid method, so-called support vector machine–artifcial fora (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 coefcient of determination (R2 ), rootmean-square error, mean absolute error, and Nash–Sutclife efciency 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 coefcient R2 = 0.933–0.985, root-mean-square error RMSE = 0.008–0.088 m3 /s, mean absolute error MAE = 0.004–0.040 m3 /s, and Nash-Sutclife coefcient NS = 0.951–0.995 had the best performance in estimating daily fow of the river. The estimation results showed that the proposed hybrid SVM-AF model outperformed other models in efciently predicting fow and daily discharge.