A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Development of a Stepwise-Clustered Hydrological Inference Model
Flow prediction is one of the most important issues in modern hydrology. In this study, a statistical tool, stepwise-clustered hydrological inference (SCHI) model, was developed for daily streamflow forecasting. The SCHI model uses cluster trees to represent the nonlinear and complex relationships between streamflow and multiple factors related to climate and watershed conditions. It allows a great deal of flexibility in watershed configuration. The proposed model was applied to the daily streamflow forecasting in the Xiangxi River watershed, China. The correlation coefficient for calibration (1991–1995) was 0.881, and that for validation (1996–1998) was 0.771. Nash–Sutcliffe efficiencies for calibration and validation were 0.768 and 0.577, respectively. The results were compared to those of a conventional process-based model, and it was found that the SCHI model had a superior performance. The results indicate that the proposed model could provide not only reliable and efficient daily flow prediction but also decision alternatives through analyzing the end nodes of the cluster tree under uncertainties. This study is a first attempt to predict daily flow using stepwise-cluster analysis.
Development of a Stepwise-Clustered Hydrological Inference Model
Flow prediction is one of the most important issues in modern hydrology. In this study, a statistical tool, stepwise-clustered hydrological inference (SCHI) model, was developed for daily streamflow forecasting. The SCHI model uses cluster trees to represent the nonlinear and complex relationships between streamflow and multiple factors related to climate and watershed conditions. It allows a great deal of flexibility in watershed configuration. The proposed model was applied to the daily streamflow forecasting in the Xiangxi River watershed, China. The correlation coefficient for calibration (1991–1995) was 0.881, and that for validation (1996–1998) was 0.771. Nash–Sutcliffe efficiencies for calibration and validation were 0.768 and 0.577, respectively. The results were compared to those of a conventional process-based model, and it was found that the SCHI model had a superior performance. The results indicate that the proposed model could provide not only reliable and efficient daily flow prediction but also decision alternatives through analyzing the end nodes of the cluster tree under uncertainties. This study is a first attempt to predict daily flow using stepwise-cluster analysis.
Development of a Stepwise-Clustered Hydrological Inference Model
Li, Zhong (author) / Huang, Guohe (author) / Han, Jingcheng (author) / Wang, Xiuquan (author) / Fan, Yurui (author) / Cheng, Guanhui (author) / Zhang, Hua (author) / Huang, Wendy (author)
2015-01-23
Article (Journal)
Electronic Resource
Unknown
Development of a Stepwise-Clustered Hydrological Inference Model
| Online Contents | 2015
Development of a Stepwise-Clustered Hydrological Inference Model
| British Library Online Contents | 2015
Groundwater level prediction using a SOM-aided stepwise cluster inference model
| Online Contents | 2016