张金萍,靳有来

• 1:郑州大学水利科学与工程学院
• 2:郑州大学黄河生态保护与区域协调发展研究院

摘要(Abstract)：

为提高径流预测精度,采用径向基神经网络(RBFNN)数据延拓技术处理完全集合经验模态分解(CEEMDAN)方法中的端点效应问题,并根据分解结果特点构建RBFNN-ARIMA组合预测模型。以1957—2013年黄河源区唐乃亥水文站年径流数据为例,先将选定的序列采用RBFNN进行延拓,然后进行CEEMDAN分解,对得到的分解分量运用RBFNN-ARIMA组合模型进行预测重构得到年径流量预测结果。研究表明,原始序列经过RBFNN数据延拓后再进行CEEMDAN分解,其所得分量可以有效反映不同时间尺度上的波动特征;ARIMA模型对高频IMF1分量的拟合效果较差,对其他中低频分量拟合效果较好;RBFNN-ARIMA组合模型预测结果的平均相对误差为5.23%,相较于RBFNN模型和ARIMA模型预测精度分别提高了9.88%和5.62%。因此,运用基于CEEMDAN方法的"分解-预测-重构"模式进行水文预测,对原始序列进行合理延拓并针对各分量特点进行组合预测可有效提高预测精度。

关键词(KeyWords)： 径流预测;完全集合经验模态分解;数据延拓;神经网络;黄河源区

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划项目(2018YFC0406501);; 2018年河南省高校科技创新人才支持计划项目(18HASTIT014);; 河南省高等学校青年骨干教师培养计划项目(2017GGJS006)

作者(Author): 张金萍,靳有来

DOI: 10.13928/j.cnki.wrahe.2022.01.006

参考文献(References)：

• [1] BIRIKUNDAVYI S,LABIB R,TRUNG H T,et al.Performance of neural networks in daily streamflow forecasting[J].Journal of Hydrologic Engineering,2002,7(5):392-398.
• [2] RAJIB M,PARAG P B,ASHISH B.Potential of support vector regression for prediction of monthly streamflow using endogenous property[J].Hydrological Processes,2010,24(7):917-923.
• [3] NORDEN E H.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J].Proceedings:Mathematical,Physical and Engineering Sciences,1998,454:903-995.
• [4] WU Z,HUANG N E.Ensemble empirical mode decomposition:a noise-assisted data analysis method[J].Advances in Adaptive Data Analysis,2009,1(1):1-41.
• [5] OKKAN U,SERBES Z A.The combined use of wavelet transform and black box models in reservoir inflow modeling[J].Journal of Hydrology and Hydromechanics,2013,61(2):112-119.
• [6] 张洪波，王斌，兰甜，等.基于经验模态分解的非平稳水文序列预测研究[J].水力发电学报，2015,34(12):42-53.ZHANG Hongbo,WANG Bin,LAN Tian,et al.A modified method for non-stationary hydrological time series forecasting based on empirical mode decomposition [J] Advances in Science and Technology of Water Resources,2015,34(12):42-53.
• [7] 刘艳，杨耘，聂磊，等.玛纳斯河出山口径流EEMD-ARIMA预测[J].水土保持研究，2017,24(6):273-280.LIU Yan,YANG Yun,NIE Lei,et al.The EEMD-ARIMA prediction of runoff at mountain pass of Manas River[J].Research of Soil and Water Conservation,2017,24(6):273-280.
• [8] JUAN B C,JULIANA V A,MAURICIO O A.Rainfall forecasting based on ensemble empirical mode decomposition and neural networks [J].Advances in Computational Intelligence,2013,7902:471-480.
• [9] ZHANG H,SINGH V P,WANG B,et al.CEREF:a hybrid data-driven model for forecasting annual streamflow from a socio-hydrological system[J].Journal of Hydrology,2016,540:246-256.
• [10] PRASAD R,DEO R C,LI Y,et al.Soil moisture forecasting by a hybrid machine learning technique:ELM integrated with ensemble empirical mode decomposition[J].Geoderma,2018,330:136-161.
• [11] FANG Y,GUAN B,WU S,et al.Optimal forecast combination based on ensemble empirical mode deamposition for agricultural commodity future prices[J].Journal of Forecasting,2020,39(6):877-886.
• [12] YEH J S,HUANG N E.Complementary ensemble empirical mode decomposition:a novel noise enhanced data analysis method[J].Advances in Adaptive Data Analysis,2010,2(2):135-156.
• [13] TORRES M E,COLOMINAS M A,SCHLOTTHAUER G,et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//IEEE International Conference on Acoustics.New York:IEEE,2011.
• [14] COLOMINAS M A,SCHLOTTHAUER G,TORRES M E.Improved complete ensemble EMD:a suitable tool for biomedical signal processing[J].Biomedical Signal Processing and Control,2014,14:19-29.
• [15] 姜锋，丁志宏，赵焱.基于CEEMDAN的黑河莺落峡年径流量多时间尺度变化特征研究[J].中国农村水利水电，2018(2):64-67.JIANG Feng,DING Zhihong,ZHAO Yan.Multiple time-scale analysis of annual runoff time series at Yingluoxia Station of the Heihe River based on CEEMDAN [J].China Rural Water and Hydropower,2018(2):64-67.
• [16] ZHANG J P,XIAO H L,ZHANG X,et al.Impact of reservoir operation on runoff and sediment load at multi-time scales based on entropy theory[J].Journal of Hydrology,2019,569:809-815.
• [17] 张金萍，许敏，张鑫，等.基于CEEMDAN-ARMA模型的年径流量预测研究[J].人民黄河，2021,43(1):35-39.ZHANG Jinping,XU Min,ZHANG Xin,et al.Annual runoff prediction based on CEEMDAN-ARMA model [J].Yellow River,2021,43(1):35-39.
• [18] 陈忠，郑时雄.EMD信号分析方法边缘效应的分析[J].数据采集与处理，2003,18(1):114-118.CHEN Zhong,ZHENG Shixiong.Analysis on end effects of EMD method [J].Joumal of Data Acquisition & Processing,2003,18 (1):114-118.
• [19] ZHAO J P,HUANG D J.Mirror extending and circular spline function for empirical mode decomposition method [J].Journal of Zhejiang University,2001,2(3):247-252.
• [20] 胡劲松，杨世锡.EMD方法基于径向基神经网络预测的数据延拓与应用[J].机械强度，2007,29(6):894-899.HU Jingsong,YANG Shixi.Application of EMD method with data extension technique based on RBF neural network to time-frequency analysis [J].Journal of Mechanical Strength,2007,29(6):894-899.