Assessing machine learning models for streamflow estimation: a case study in Oued Sebaou watershed (Northern Algeria). Issue 9 (4th July 2022)

• Record Type: Journal Article
• Authors: Abda, Zaki; Zerouali, Bilel; Chettih, Mohamed; Guimarães Santos, Celso Augusto; de Farias, Camilo Allyson Simões; Elbeltagi, Ahmed
• Is Part Of: Hydrological sciences journal. Volume 67:Issue 9(2022)
• Page Start: 1328
• Page End: 1341
• Publication Date: 2022-07-04
• Subjects: runoff -- machine learning -- training algorithms -- neural networks -- random forest -- Algeria; Hydrology -- Periodicals; 551.4805
• DOI: 10.1080/02626667.2022.2083511
• Languages: English
• ISSNs: 0262-6667

Abstract

ABSTRACT: This paper proposes runoff models based on machine learning to estimate daily streamflows in Oued Sebaou watershed, a Mediterranean coastal basin located in northern Algeria. Therefore, we applied random forest (RF), artificial neural networks (ANN – under different training algorithms), and locally weighted linear regression (LWLR) using as input combinations of current and past rainfall amounts and previous values of streamflow. We selected streamflow and rainfall records to calibrate and validate the stated approaches. We used root mean square error (RMSE) and correlation coefficient (R) to evaluate the accuracy of the models. Analyses of the results show that RF provided the best outcomes for both training (RMSE = 4.7458 and R = 0.9834) and validation (RMSE = 2.3617 and R = 0.9719). The ANN calibrated with the Levenberg-Marquardt algorithm presented the second-best result, outperforming its counterparts and LWLR. Graphical Abstract: uf0001