Intercomparing the robustness of machine learning models in simulation and forecasting of streamflow
The intercomparison of streamflow simulation and the prediction of discharge using various renowned machine learning techniques were performed. The daily streamflow discharge model was developed for 35 observation stations located in a large-scale river basin named Cauvery. Various hydrological indi...
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
IWA Publishing
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/15d1237f55504149ba753cb71a61f845 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | The intercomparison of streamflow simulation and the prediction of discharge using various renowned machine learning techniques were performed. The daily streamflow discharge model was developed for 35 observation stations located in a large-scale river basin named Cauvery. Various hydrological indices were calculated for observed and predicted discharges for comparing and evaluating the replicability of local hydrological conditions. The model variance and bias observed from the proposed extreme gradient boosting decision tree model were less than 15%, which is compared with other machine learning techniques considered in this study. The model Nash–Sutcliffe efficiency and coefficient of determination values are above 0.7 for both the training and testing phases which demonstrate the effectiveness of model performance. The comparison of monthly observed and model-predicted discharges during the validation period illustrates the model's ability in representing the peaks and fall in high-, medium-, and low-flow zones. The assessment and comparison of hydrological indices between observed and predicted discharges illustrate the model's ability in representing the baseflow, high-spell, and low-spell statistics. Simulating streamflow and predicting discharge are essential for water resource planning and management, especially in large-scale river basins. The proposed machine learning technique demonstrates significant improvement in model efficiency by dropping variance and bias which, in turn, improves the replicability of local-scale hydrology. HIGHLIGHTS
The credibility of machine learning models in representing the regional-scale hydrology is performed.;
Evaluation to prioritize model selection for river basin management.;
Season-based approach in evaluating model performance in local hydrology.;
Hydrological indices were inter-compared for high-, medium-, and low-flow zones.;
Outcome delivers valuable suggestions to decision-makers in the planning of future water resources.; |
|---|