Header menu link for other important links
X
A nonlinear data-driven model for synthetic generation of annual streamflows
, Kasthrirengan Srinivasan
Published in
2008
Volume: 22
   
Issue: 12
Pages: 1831 - 1845
Abstract
A hybrid model that blends two non-linear data-driven models, i.e. an artificial neural network (ANN) and a moving block bootstrap (MBB), is proposed for modelling annual streamflows of rivers that exhibit complex dependence. In the proposed model, the annual streamflows are modelled initially using a radial basis function ANN model. The residuals extracted from the neural network model are resampled using the non-parametric resampling technique MBB to obtain innovations, which are then added back to the ANN-modelled flows to generate synthetic replicates. The model has been applied to three annual streamflow records with variable record length, selected from different geographic regions, namely Africa, USA and former USSR. The performance of the proposed ANN-based non-linear hybrid model has been compared with that of the linear parametric hybrid model. The results from the case studies indicate that the proposed ANN-based hybrid model (ANNHM) is able to reproduce the skewness present in the streamflows better compared to the linear parametric-based hybrid model (LPHM), owing to the effective capturing of the non-linearities. Moreover, the ANNHM, being a completely data-driven model, reproduces the features of the marginal distribution more closely than the LPHM, but offers less smoothing and no extrapolation value. It is observed that even though the preservation of the linear dependence structure by the ANNHM is inferior to the LPHM, the effective blending of the two non-linear models helps the ANNHM to predict the drought and the storage characteristics efficiently. Copyright © 2007 John Wiley & Sons, Ltd.
About the journal
JournalHydrological Processes
ISSN08856087
Open AccessNo
Concepts (47)
  •  related image
    AUTOMATIC TRAIN CONTROL
  •  related image
    Blending
  •  related image
    Drought
  •  related image
    Eigenvalues and eigenfunctions
  •  related image
    Feedforward neural networks
  •  related image
    Food preservation
  •  related image
    Hybrid sensors
  •  related image
    Image classification
  •  related image
    Mathematical models
  •  related image
    Neural networks
  •  related image
    Radial basis function networks
  •  related image
    Real time systems
  •  related image
    Stream flow
  •  related image
    ARTIFICIAL NEURAL NETWORK (ANN) MODELS
  •  related image
    ARTIFICIAL NEURAL NETWORK (ANNS)
  •  related image
    Case studies
  •  related image
    DATA DRIVEN (DD)
  •  related image
    Data-driven modeling
  •  related image
    GEOGRAPHIC REGIONS
  •  related image
    HYBRID MODEL (HM)
  •  related image
    LINEAR DEPENDENCES
  •  related image
    MARGINAL DISTRIBUTIONS
  •  related image
    NEURAL NETWORK (NN) MODELS
  •  related image
    NON LINEAR MODELING
  •  related image
    Non-linear
  •  related image
    Non-linearities
  •  related image
    Non-parametric
  •  related image
    NONLINEAR DATA
  •  related image
    RADIAL-BASIS FUNCTION (RBF)
  •  related image
    RE SAMPLING
  •  related image
    STORAGE CHARACTERISTICS
  •  related image
    STREAM FLOW RECORDS
  •  related image
    SYNTHETIC GENERATION
  •  related image
    Backpropagation
  •  related image
    Artificial neural network
  •  related image
    Bootstrapping
  •  related image
    Hydrological modeling
  •  related image
    Parameterization
  •  related image
    Radial flow
  •  related image
    River flow
  •  related image
    Sampling
  •  related image
    Smoothing
  •  related image
    Streamflow
  •  related image
    Africa
  •  related image
    North america
  •  related image
    United states
  •  related image
    USSR