Employing Machine Learning Algorithms for Streamflow Prediction: A Case Study of Four River Basins with Different Climat
- PDF / 3,185,865 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 85 Downloads / 287 Views
Employing Machine Learning Algorithms for Streamflow Prediction: A Case Study of Four River Basins with Different Climatic Zones in the United States Peiman Parisouj 1 & Hamid Mohebzadeh 1
& Taesam Lee
1
Received: 25 March 2020 / Accepted: 31 August 2020/ # Springer Nature B.V. 2020
Abstract
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, Tmax, and Tmin) 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 snowmeltdominated 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. Keywords Streamflow prediction . Support vector regression . Artificial neural networks . Extreme learning machine
* Hamid Mohebzadeh [email protected] * Taesam Lee [email protected]
1
Department of Civil Engineering, ERI, Gyeongsang National University, 501 Jinju-daero, Jinju, Gyeongnam 52828, South Korea
Parisouj P. et al.
1 Introduction The accurate prediction of a streamflow is challenging task due to the complex nonlinearity and stochastic characteristics of hydrological processes such as precipitation, temperature, evapotranspiration, and characteristics of the watershed (Adnan et al. 2019; Meng et al. 2019; Niu et al. 2019). However, due to their great importance for optimal management of water resources, the monthly and daily streamflow estimations have received considerable attention in the past decades (Wang et al. 2019; Adnan et al. 2019; Hadi and Tombul 2018). Streamflow prediction methods can be grouped into two categories (Wang 2006): physically based models and data-driven models. For example, conceptually hydrological models are considered a type of physically based models (Cheng et al. 2006); artificial neural network and support vector machine are categorized as data-driven models (Belayneh et al. 2014; Wu et al. 2010). Physically based models require specific
Data Loading...
