Abstract
Abstract. Streamflow forecasting is a crucial component in the management and control of water resources. Decomposition-based approaches have particularly demonstrated improved forecasting performance. However, direct decomposition of entire streamflow data with calibration and validation subsets is not practical for signal component prediction. This impracticality is due to the fact that the calibration process uses some validation information that is not available in practical streamflow forecasting. Unfortunately, independent decomposition of calibration and validation sets leads to undesirable boundary effects and less accurate forecasting. To alleviate such boundary effects and improve the forecasting performance in basins lacking meteorological observations, we propose a two-stage decomposition prediction (TSDP) framework. We realize this framework using variational mode decomposition (VMD) and support vector regression (SVR) and refer to this realization as VMD-SVR. We demonstrate experimentally the effectiveness, efficiency and accuracy of the TSDP framework and its VMD-SVR realization in terms of the boundary effect reduction, computational cost, and overfitting, in addition to decomposition and forecasting outcomes for different lead times. Specifically, four comparative experiments were conducted based on the ensemble empirical mode decomposition (EEMD), singular spectrum analysis (SSA), discrete wavelet transform (DWT), boundary-corrected maximal overlap discrete wavelet transform (BCMODWT), autoregressive integrated moving average (ARIMA), SVR, backpropagation neural network (BPNN) and long short-term memory (LSTM). The TSDP framework was also compared with the wavelet data-driven forecasting framework (WDDFF). Results of experiments on monthly runoff data collected from three stations at the Wei River show the superiority of the VMD-SVR model compared to benchmark models.
Highlights
Reliable and accurate streamflow forecasting is of great significance for water resource management (Woldemeskel et al, 2018)
This demonstrates that the mixing-and-shuffling step does not improve the generalization performance if the validation samples are not generated from appended decompositions
Similar results were obtained for the normalized root-mean-square error (NRMSE) and peak percentage of threshold statistics (PPTS) criteria
Summary
Reliable and accurate streamflow forecasting is of great significance for water resource management (Woldemeskel et al, 2018). Streamflow forecasting models have been progressively developed through the analysis of relevant physical processes and the incorporation of key hydrological terms into those models (Kratzert et al, 2018). The investigated hydrological terms include physical characteristics and boundary conditions of catchments as well as spatial and temporal variabilities of hydrological processes (Kirchner, 2006; Paniconi and Putti, 2015). Physics-based models have been largely developed by harnessing high computational power and exploiting hydrometeorological and remote sensing data (Singh, 2018; Clark et al, 2015). Modeling hydrological processes with spatial and temporal variabilities at the catchment scale requires a lot of input meteorological data, information on boundary conditions and physical properties, as well as high-performance computational resources (Binley et al, 1991; Devia et al, 2015).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
