气候变化领域集成服务门户(CCPortal): Two-stage variational mode decomposition and support vector regression for streamflow forecasting

CCPortal

DOI	10.5194/hess-24-5491-2020
	Two-stage variational mode decomposition and support vector regression for streamflow forecasting
	Zuo G.; Luo J.; Wang N.; Lian Y.; He X.
发表日期	2020
ISSN	1027-5606
起始页码	5491
结束页码	5518
卷号	24 期号:11
英文摘要	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 datadriven 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. © Author(s) 2020.
语种	英语
scopus关键词	Autoregressive moving average model; Backpropagation; Calibration; Discrete wavelet transforms; Forecasting; Long short-term memory; Signal reconstruction; Spectrum analysis; Stream flow; Water resources; Wavelet decomposition; Auto-regressive integrated moving average; Back-propagation neural networks; Calibration and validations; Ensemble empirical mode decompositions (EEMD); Maximal overlap discrete wavelet transforms; Meteorological observation; Singular spectrum analysis; Support vector regression (SVR); Support vector regression; decomposition; forecasting method; streamflow; support vector machine; vector autoregression
来源期刊	Hydrology and Earth System Sciences
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/159254
作者单位	Zuo, G., State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi'an University of Technology, Xi'an, Shaanxi, 710048, China; Luo, J., State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi'an University of Technology, Xi'an, Shaanxi, 710048, China; Wang, N., State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi'an University of Technology, Xi'an, Shaanxi, 710048, China; Lian, Y., State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi'an University of Technology, Xi'an, Shaanxi, 710048, China; He, X., State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi'an University of Technology, Xi'an, Shaanxi, 710048, China
推荐引用方式 GB/T 7714	Zuo G.,Luo J.,Wang N.,et al. Two-stage variational mode decomposition and support vector regression for streamflow forecasting[J],2020,24(11).
APA	Zuo G.,Luo J.,Wang N.,Lian Y.,&He X..(2020).Two-stage variational mode decomposition and support vector regression for streamflow forecasting.Hydrology and Earth System Sciences,24(11).
MLA	Zuo G.,et al."Two-stage variational mode decomposition and support vector regression for streamflow forecasting".Hydrology and Earth System Sciences 24.11(2020).