The publisher regrets that a correction was not incorporated before publication. This resulted in an error in Figure 2 of the original paper. The correct Figure 2 can be found below. We wish to apologise to the authors and to the readers for any inconvenience caused. The corrections have now been incorporated on the online version of this paper.
Figure 2

Hydrographs of the observed and forecasted streamflows by the random forest (RF), artificial neural networks (ANN), support vector regression (SVR), and M5 model tree (M5T) models, fitted with the total set of variables and sets selected by the genetic algorithm (GA) and recursive feature elimination (RFE), validation periods, for the Sono (a), Manuel Alves da Natividade (b) and Palma (c) River basins.

Figure 2

Hydrographs of the observed and forecasted streamflows by the random forest (RF), artificial neural networks (ANN), support vector regression (SVR), and M5 model tree (M5T) models, fitted with the total set of variables and sets selected by the genetic algorithm (GA) and recursive feature elimination (RFE), validation periods, for the Sono (a), Manuel Alves da Natividade (b) and Palma (c) River basins.

Close modal
This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence (CC BY 4.0), which permits copying, adaptation and redistribution, provided the original work is properly cited (http://creativecommons.org/licenses/by/4.0/).