A wavelet-neural network hybrid modelling approach for estimating and predicting river monthly flows

被引:67
|
作者
Wei, Shouke [1 ,2 ,3 ]
Yang, Hong [1 ]
Song, Jinxi [4 ]
Abbaspour, Karim [1 ]
Xu, Zongxue [5 ]
机构
[1] Swiss Fed Inst Aquat Sci & Technol EAWAG, CH-8600 Dubendorf, Switzerland
[2] Emodlog Technol Inc, Vancouver, BC V5P 3R1, Canada
[3] Univ British Columbia, Dept Forest Resources Management, Vancouver, BC V6T 1Z4, Canada
[4] NW Univ Xian, Coll Urban & Environm Sci, Xian 710069, Peoples R China
[5] Beijing Normal Univ, Coll Water Sci, Beijing 100875, Peoples R China
基金
中国国家自然科学基金;
关键词
instream flow; wavelet-neural network; Levenberg-Marquardt; Bayesian regularization; SUSPENDED SEDIMENT DATA; MONTHLY RAINFALL; STOCHASTIC GENERATION; CONJUNCTION MODEL; ANN; SIMULATION; TRANSFORMS;
D O I
10.1080/02626667.2012.754102
中图分类号
TV21 [水资源调查与水利规划];
学科分类号
081501 ;
摘要
A wavelet-neural network (WNN) hybrid modelling approach for monthly river flow estimation and prediction is developed. This approach integrates discrete wavelet multi-resolution decomposition and a back-propagation (BP) feed-forward multilayer perceptron (FFML) artificial neural network (ANN). The Levenberg-Marquardt (LM) algorithm and the Bayesian regularization (BR) algorithm were employed to perform the network modelling. Monthly flow data from three gauges in the Weihe River in China were used for network training and testing for 48-month-ahead prediction. The comparison of results of the WNN hybrid model with those of the single ANN model show that the former is able to significantly increase the prediction accuracy.
引用
收藏
页码:374 / 389
页数:16
相关论文
共 50 条
  • [1] Simulating and predicting river discharge time series using a wavelet-neural network hybrid modelling approach
    Wei, Shouke
    Song, Jinxi
    Khan, Nasreen Islam
    [J]. HYDROLOGICAL PROCESSES, 2012, 26 (02) : 281 - 296
  • [2] Forecasting river water temperature time series using a wavelet-neural network hybrid modelling approach
    Graf, Renata
    Zhu, Senlin
    Sivakumar, Bellie
    [J]. JOURNAL OF HYDROLOGY, 2019, 578
  • [3] Predicting water sorptivity coefficient in calcareous soils using a wavelet-neural network hybrid modeling approach
    Moosavi, Ali Akbar
    Nematollahi, Mohammad Amin
    Rahimi, Mehrzad
    [J]. ENVIRONMENTAL EARTH SCIENCES, 2021, 80 (06)
  • [4] Hybrid wavelet-neural network models for time series
    Kilic, Deniz Kenan
    Ugur, Omur
    [J]. APPLIED SOFT COMPUTING, 2023, 144
  • [5] Predicting Monthly Streamflow Using a Hybrid Wavelet Neural Network: Case Study of the coruh River Basin
    Gunes, Mehmet Samil
    Parim, Coskun
    Yildiz, Dogan
    Buyuklu, Ali Hakan
    [J]. POLISH JOURNAL OF ENVIRONMENTAL STUDIES, 2021, 30 (04): : 3065 - 3075
  • [6] Rainfall-Runoff Forecasting with Wavelet-Neural Network Approach: A Case Study of Kizilirmak River
    Terzi, Ozlem
    Barak, Melike
    [J]. JOURNAL OF AGRICULTURAL SCIENCES-TARIM BILIMLERI DERGISI, 2015, 21 (04): : 546 - 557
  • [7] Exchange rate prediction: a wavelet-neural approach
    Sindelarova, Irena
    [J]. PROCEEDINGS OF 30TH INTERNATIONAL CONFERENCE MATHEMATICAL METHODS IN ECONOMICS, PTS I AND II, 2012, : 875 - 878
  • [8] The FPGA Implementation of Wavelet-Neural Network Based On DSP Builder
    Liu, Bing Qian
    Gong, Mao Fa
    Wang, Wen Shuo
    Lin, Yu Qing
    Xu, Yi Sheng
    Yin, Fan Jiao
    Li, Mei Rong
    [J]. PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS RESEARCH AND MECHATRONICS ENGINEERING, 2015, 121 : 900 - 903
  • [9] Application of wavelet-neural network in rolling bearings fault diagnosis
    Li, M
    Lu, SA
    Chen, DM
    Ma, WX
    [J]. ICEMI 2005: CONFERENCE PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON ELECTRONIC MEASUREMENT & INSTRUMENTS, VOL 4, 2005, : 604 - 608
  • [10] A numerical modelling and neural network approach to estimate the impact of groundwater abstractions on river flows
    Parkin, G.
    Birkinshaw, S. J.
    Younger, P. L.
    Rao, Z.
    Kirk, S.
    [J]. JOURNAL OF HYDROLOGY, 2007, 339 (1-2) : 15 - 28