Employing Machine Learning Algorithms for Streamflow Prediction: A Case Study of Four River Basins with Different Climatic Zones in the United States

• Published in: Water resources management Vol. 34; no. 13; pp. 4113 - 4131
• Main Authors: Parisouj, Peiman, Mohebzadeh, Hamid, Lee, Taesam
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.10.2020; Springer Nature B.V
• Subjects: administrative management; Algorithms; Artificial neural networks; Atmospheric Sciences; Back propagation networks; basins; case studies; Civil Engineering; Climatic zones; Computer simulation; Daily; Drought; Earth and Environmental Science; Earth Sciences; Environment; flood control; Flood management; Geotechnical Engineering & Applied Earth Sciences; Hydrogeology; Hydrology/Water Resources; Learning algorithms; Learning theory; Machine learning; Mitigation; Model accuracy; Monthly; Neural networks; prediction; regression analysis; Reservoir operation; River basins; Rivers; Simulation; Snowmelt; Statistical analysis; Statistical methods; Stream discharge; Stream flow; Support vector machines; water; Water resources; Water resources management; United States > US; Streamflow prediction; Support vector regression; Extreme learning machine; Artificial neural networks
• ISSN: 0920-4741; 1573-1650
• DOI: 10.1007/s11269-020-02659-5

Streamflow estimation plays a significant role in water resources management, especially for flood mitigation, drought warning, and reservoir operation. Hence, the current study examines the prediction capability of three well-known machine learning algorithms (Support Vector Regression (SVR), Artificial Neural Network with backpropagation (ANN-BP), and Extreme Learning Machine (ELM)) for the monthly and daily streamflows of four rivers in the United States. For model development, three main predictor variables ( P , T max , and T min ) and their antecedent values were considered. The SVM-RFE feature selection method was used to select the most appropriate predictor variable.The performance of the developed models was tested using four evaluation statistics. The results indicate that (1) except some improvements, the accuracy of all models decreases at the daily scale compared to that at the monthly scale; (2) the SVR has the best performance among the three models at the monthly and daily scales, while the ANN-BP model has the worse performance; (3) the ELM has better generalization performance than the ANN-BP for streamflow simulation at the monthly and daily scales; and (4) all models fail to predict the streamflow for the Carson River as a snowmelt-dominated basin. Generally, findings of the current study indicate that the SVR model produces better results than the ELM and ANN-BP for streamflow simulation at the monthly and daily scales.