Predicting Daily Streamflow in a Cold Climate Using a Novel Data Mining Technique: Radial M5 Model Tree

In this study, the viability of radial M5 model tree (RM5Tree) is investigated in prediction and estimation daily streamflow a cold climate. The RM5Tree compared with (M5Tree), artificial neural networks (ANN), basis function (RBFNN), multivariate adaptive regression spline (MARS) using data two stations from Sweden. accuracy methods assessed based on root mean square errors (RMSE), absolute (MAE), percentage (MAPE), Nash Sutcliffe Efficiency (NSE) are graphically time variation scatter graphs. benchmark results show that offers better predicting to other four models by respectively improving M5Tree respect RMSE, MAE, MAPE, NSE 26.5, 17.9, 5.9, 10.9%. also acts than M5Tree, ANN, RBFNN, MARS estimating downstream station only upstream data.