A comparative study of wavelet and empirical mode decomposition-based GPR models for river discharge relationship modeling at consecutive hydrometric stations
The river stage–discharge relationship has an important impact on modeling, planning, and management of river basins and water resources. In this study, the capability of the Gaussian Process Regressions (GPR) kernel-based approach was assessed in predicting the daily river stage–discharge (RSD) rel...
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
IWA Publishing
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/041be1ee94714725a9bef2be425a3e42 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | The river stage–discharge relationship has an important impact on modeling, planning, and management of river basins and water resources. In this study, the capability of the Gaussian Process Regressions (GPR) kernel-based approach was assessed in predicting the daily river stage–discharge (RSD) relationship. Three successive hydrometric stations of the Housatonic River were considered, and based on the flow characteristics during the period of 2002–2006 several models were developed and tested via GPR. To enhance the applied model efficiency, two pre-processing techniques, namely Wavelet Transform (WT) and Ensemble Empirical Mode Decomposition (EEMD), were used. Also, two states of the RSD modeling were investigated. In state 1, each station's own data was used and in state 2, the upstream stations’ datasets were used as input to model the RSD downstream of the river. The single and integrated model results showed that the integrated WT- and EEMD-GPR models resulted in more accurate outcomes. Data processing enhanced the models' capability between 25% and 40%. The results showed that the RSD modeling in state 1 led to better results; however, when the station's own data were not available the integrated methods could be applied successfully for the RSD modeling using the previous stations’ data. HIGHLIGHTS
The advantages of two WT and EEMD pre-processing techniques and kernel-based model were merged for RSD modeling.;
Two states of modeling based on station's own data or previous stations’ data were investigated.;
Integrated hybrid techniques outperformed the single GPR method.; |
|---|