English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

. Streamflow forecasting is a crucial component in themanagement and control of water resources. Decomposition-based approacheshave particularly demonstrated improved forecasting performance. However,direct decomposition of entire streamflow data with calibration andvalidation subsets is not practical for signal component prediction. Thisimpracticality is due to the fact that the calibration process uses somevalidation information that is not available in practical streamflow forecasting. Unfortunately, independent decomposition of calibration andvalidation sets leads to undesirable boundary effects and less accurate forecasting. To alleviate such boundary effects and improve the forecastingperformance in basins lacking meteorological observations, we propose atwo-stage decomposition prediction (TSDP) framework. We realize thisframework using variational mode decomposition (VMD) and support vectorregression (SVR) and refer to this realization as VMD-SVR. We demonstrate experimentally the effectiveness, efficiency and accuracy of the TSDPframework and its VMD-SVR realization in terms of the boundary effectreduction, computational cost, and overfitting, in addition to decomposition and forecasting outcomes for different lead times. Specifically, fourcomparative experiments were conducted based on the ensemble empirical modedecomposition (EEMD), singular spectrum analysis (SSA), discrete wavelettransform (DWT), boundary-corrected maximal overlap discrete wavelettransform (BCMODWT), autoregressive integrated moving average (ARIMA), SVR,backpropagation neural network (BPNN) and long short-term memory (LSTM). TheTSDP framework was also compared with the wavelet data-driven forecastingframework (WDDFF). Results of experiments on monthly runoff data collectedfrom three stations at the Wei River show the superiority of the VMD-SVRmodel compared to benchmark models.

Two-stage variational mode decomposition and support vector regression for streamflow forecasting