River flow forecasting using different artificial neural network algorithms and wavelet transform

Partal T.

Canadian Journal of Civil Engineering, cilt.36, sa.1, ss.26-39, 2009 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 36 Sayı: 1
  • Basım Tarihi: 2009
  • Doi Numarası: 10.1139/l08-090
  • Dergi Adı: Canadian Journal of Civil Engineering
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.26-39
  • Anahtar Kelimeler: Feed-forward back-propagation neural network, Forecasting, Generalized regression neural network, Monthly flow, Radial basis neural network, Wavelet transform
  • Ondokuz Mayıs Üniversitesi Adresli: Hayır

Özet

In this study, the wavelet-neural network structure that combines wavelet transform and artificial neural networks has been employed to forecast the river flows of Turkey. Discrete wavelet transforms, which are useful to obtain to the periodic components of the measured data, have significantly positive effects on artificial neural network modeling performance. Generally, the feed-forward back-propagation method was studied with respect to artificial neural network applications to water resources data. In this study, the performance of generalized neural networks and radial basis neural networks were compared with feed-forward back-propagation methods. Six different models were studied for forecasting of monthly river flows. It was seen that the wavelet and feed-forward back-propagation model was superior to the other models in terms of selected performance criteria.