[1]甘 容,马超鑫,高 勇,等.基于二次分解和支持向量机的月径流预测方法[J].郑州大学学报(工学版),2024,45(06):32-39.[doi:10.13705/j.issn.1671-6833.2024.06.003]
　GAN Rong,MA Chaoxin,GAO Yong,et al.Monthly Runoff Prediction Method Based on Secondary Decomposition and SupportVector Machine[J].Journal of Zhengzhou University (Engineering Science),2024,45(06):32-39.[doi:10.13705/j.issn.1671-6833.2024.06.003]
点击复制

基于二次分解和支持向量机的月径流预测方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
45
期数:
2024年06期
页码:
32-39
栏目:
出版日期:
2024-09-25

文章信息/Info

Title:
Monthly Runoff Prediction Method Based on Secondary Decomposition and SupportVector Machine
文章编号:
1671-6833(2024)06-0032-08
作者:
甘 容1; 2;  马超鑫1; 2;  高 勇3;  郭 林3;  侯晓丽4;  路学永5
1. 郑州大学 水利与交通学院,河南 郑州 450001;2. 河南省地下水污染防治与修复重点实验室,河南 郑州 450001;3. 河南省地质研究院,河南 郑州 450001;4. 河南省豫东水利保障中心,河南 开封 475000; 5. 中国南水北调集团中线有限公司渠首分公司,河南 南阳 473000
Author(s):
GAN Rong1; 2;  MA Chaoxin1; 2;  GAO Yong3;  GUO Lin3;  HOU Xiaoli4;  LU Xueyong5
1. School of Water Resources and Transportation, Zhengzhou University, Zhengzhou 450001, China; 2. Henan Key Laboratory of Groundwater Pollution Prevention and Rehabilitation, Zhengzhou 450001, China; 3. Henan Provincial Geological Research Institute,Zhengzhou 450001, China; 4. Henan Province Yudong Water Resources Guarantee Center, Kaifeng 475000, China;5. Canal Head Branch Company of China South-to-North Water Diversion Middle Route Corporation Limited, Nanyang 473000, China
关键词:
月径流预测;  二次分解;  STL;  VMD;  SVM;  神经网络
Keywords:
monthly runoff prediction;  secondary decomposition;  STL;  VMD;  SVM;  neural network
分类号:
P338TV121
DOI:
10.13705/j.issn.1671-6833.2024.06.003
文献标志码:
A
摘要:
针对径流序列的非线性和非平稳性特征,提出了一种基于加权回归的季节趋势分解( STL) 和变分模态分解(VMD)组合的二次分解,结合支持向量机( SVM)的月径流预测模型 STL-VMD-SVM。 该模型利用 STL 将原始径流序列分解为不同频率的季节项、趋势项和残差项,并通过 VMD 将残差项分解为 IMFs。 建立 SVM 模型预测季节项、趋势项和 IMFs,所有 IMFs 的预测值之和为残差项的预测值,季节项、趋势项和残差项之积为原始径流序列的最终预测值。 基于伊洛河流域黑石关站及黄河干流高村站的月径流时间序列进行了实例应用及普适性评价,并与BP 神经网络模型和长短期记忆神经网络模型( LSTM) 进行对比。 结果表明:对于伊洛河黑石关站径流预测,所提模型验证期的 NSE、MAPE、RMSE、R 分别为 0. 977,13. 705%,0. 327,0. 991,其预测精度均优于单一模型和一次分解模型,STL-VMD 二次分解可以有效提高模型预测精度;在黄河干流高村站径流预测中验证期的 NSE、MAPE、RMSE、R 分别为 0. 979,8. 509%,3. 263,0. 989,也达到了很好的预测效果。
Abstract:
A monthly runoff prediction model( STL-VMD-SVM) based on a secondary decomposition using loess( STL) and variational mode decomposition (VMD) combined with a support vector machine( SVM) was proposed to address the nonlinear and non-stationary characteristics of runoff sequences. This model utilized STL to decompose the original runoff sequence into seasonal, trend, and residual terms of different frequencies and decomposedthe residual term into IMFs through VMD. An SVM model was established to predict seasonal, trend, and IMFs.The sum of the predicted values of all IMFs was the predicted value of the residual term, and the product of seasonal, trend, and residual terms was the final predicted value of the original runoff series. Based on the monthly runofftime series of Heishiguan Station and Gaocun Station on the mainstream of the Yellow River in the Yiluo River Basin, an example application and universality evaluation were conducted, and compared with the BP neural networkmodel and the long shortterm memory neural network model( LSTM) . The results showed that for the runoff prediction of Heishiguan Station in the Yiluo River Basin, the NSE, MAPE, RMSE, and R in the validation period of theproposed model were 0. 977, 13. 705%, 0. 327 and 0. 991, respectively, and their prediction accuracy was betterthan that of the single model and the primary decomposition model. The secondary decomposition of STL-VMDcould effectively improve the prediction accuracy of the model. The NSE, MAPE, RMSE, and R during the validation period in the runoff prediction at Gaocun Station on the mainstream of the Yellow River were 0. 979, 8. 509%,3. 263, and 0. 989, respectively, which also achieved good prediction results.

参考文献/References:

[1] HIRABAYASHI Y, MAHENDRAN R, KOIRALA S, etal. Global flood risk under climate change [ J] . NatureClimate Change, 2013, 3(9) : 816-821.

[2] DEY P, MISHRA A. Separating the impacts of climatechange and human activities on streamflow: a review ofmethodologies and critical assumptions [ J ] . Journal ofHydrology, 2017,548:278-290.
[3] KOTTA J, HERKÜL K, JAAGUS J, et al. Linking atmospheric, terrestrial and aquatic environments: regimeshifts in the Estonian climate over the past 50 years[ J] .PLoS One, 2018, 13(12) : e0209568.
[4] HE X X, LUO J G, LI P, et al. A hybrid model basedon variational mode decomposition and gradient boostingregression tree for monthly runoff forecasting [ J] . WaterResources Management, 2020, 34(2) : 865-884.
[5] 雷庆文, 高培强, 李建林. 时序分解和 CNN-LSTM 相融合的月径流预报模型[ J] . 长江科学院院报, 2023,40(6) : 49-54.
LEI Q W, GAO P Q, LI J L. A monthly runoff forecastmodel combining time series decomposition and CNNLSTM [ J ] . Journal of Changjiang River Scientific Research Institute, 2023, 40(6) : 49-54.
[6] 王文川, 杜玉瑾, 和吉, 等. 基于 CEEMDAN-VMD-BP模型的月径流量预测研究[ J] . 华北水利水电大学学报(自然科学版) , 2023, 44(1) : 32-40, 48.
WANG W C, DU Y J, HE J, et al. Research on monthlyrunoff prediction based on CEEMDAN-VMD-BP model[ J] . Journal of North China University of Water Resources and Electric Power ( Natural Science Edition ) ,2023, 44(1) : 32-40, 48.
[7] YANG H, LI W D. Data decomposition, seasonal adjustment method and machine learning combined for runoffprediction: a case study [ J] . Water Resources Management, 2023, 37(1) : 557-581.
[8] 朱得胜, 吕锡芝, 倪用鑫, 等. 2001—2018 年伊洛河流域产 水 系 数 演 变 分 析 [ J] . 中 国 农 村 水 利 水 电,2022(9) : 139-145.
ZHU D S, LYU X Z, NI Y X, et al. An analysis of thechanges in the water yield coefficient in the Yiluo RiverBasin from 2001 to 2018[ J] . China Rural Water and Hydropower, 2022(9) : 139-145.
[9] HOU J, QIN T L, YAN D H, et al. Evaluation of waterland resources regulation potential in the Yiluo River Basin,China[J]. Ecological Indicators, 2023, 153: 110410.
[10] 张艺馨. 基于改进 BP 神经网络模型的采空区特殊下垫面条件下径流预报研究[D]. 太原: 太原理工大学, 2021.
ZHANG Y X. Study on runoff prediction of goaf with special underlying surface based on improved BP neural network model[D] . Taiyuan: Taiyuan University of Technology, 2021.
[11] 邢珊珊. 基于时空关联的城市快速路短时交通流预测方法研究[D] . 北京: 北京交通大学, 2017.
XING S S. Study on short-term traffic flow forecastingmethod of urban expressway based on spatial-temporal correlation[D]. Beijing: Beijing Jiaotong University, 2017.
[12] 薛联青, 周天文, 刘远洪, 等. 基于两阶段分解和可解释机器学习的中长期径流预测[ J] . 中国农村水利水电, 2023(7) : 1-7, 18.
XUE L Q, ZHOU T W, LIU Y H, et al. Medium andlong-term runoff forecasting based on two-stage decomposition and interpretable machine learning[ J] . China Rural Water and Hydropower, 2023(7) : 1-7, 18.
[13] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition [ J] . IEEE Transactions on Signal Processing, 2014, 62(3) : 531-544.
[14] SHARMA V, PAREY A. Extraction of weak fault transients using variational mode decomposition for fault diagnosis of gearbox under varying speed [ J ] . EngineeringFailure Analysis, 2020, 107: 104204.
[15] 廖晓辉, 陈川川. 改进的 VMD-HT 在电能质量扰动检测中的应用[ J] . 郑州大学学报( 工学版) , 2021, 42(1) : 21-27.
LIAO X H, CHEN C C. Application of improved VMDHT in power quality disturbance detection[ J] . Journal ofZhengzhou University ( Engineering Science) , 2021, 42(1) : 21-27.
[16] TOMAR D, AGARWAL S. Twin support vector machine:a review from 2007 to 2014 [ J ] . Egyptian InformaticsJournal, 2015, 16(1) : 55-69.
[17] 张颖超, 成金杰, 邓华, 等. 基于相似日和特征提取的短期风电功率预测[ J] . 郑州大学学报( 工学版) ,2020, 41(5) : 44-49.
ZHANG Y C, CHENG J J, DENG H, et al. Short-termwind power prediction based on similar day and featureextraction [ J] . Journal of Zhengzhou University ( Engineering Science) , 2020, 41(5) : 44-49.
[18] CHEN S, REN M M, SUN W. Combining two-stage decomposition based machine learning methods for annualrunoff forecasting [ J ] . Journal of Hydrology, 2021,603: 126945.
[19] 纪昌明, 周婷, 向腾飞, 等. 基于网格搜索和交叉验证的支持向量机在梯级水电系统隐随机调度中的应用[ J] . 电力自动化设备, 2014, 34(3) : 125-131.
JI C M, ZHOU T, XIANG T F, et al. Application ofsupport vector machine based on grid search and crossvalidation in implicit stochastic dispatch of cascaded hydropower stations[ J] . Electric Power Automation Equi

更新日期/Last Update: 2024-09-29