Rainfall-runoff forecasting with wavelet-neural network approach: A case study of Kızılırmak river Dalgacık-sinir ağı yaklaşımı ile yağış-akış tahmini: Kızılırmak nehri örneği

TERZİ Ö., Barak M.

Tarim Bilimleri Dergisi, vol.21, no.4, pp.546-557, 2015 (SCI-Expanded, Scopus, TRDizin) identifier

  • Publication Type: Article / Article
  • Volume: 21 Issue: 4
  • Publication Date: 2015
  • Doi Number: 10.1501/tarimbil_0000001356
  • Journal Name: Tarim Bilimleri Dergisi
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, TR DİZİN (ULAKBİM)
  • Page Numbers: pp.546-557
  • Keywords: Artificial neural networks, Kızılırmak river, Rainfall, Runoff, Wavelet transform
  • Isparta University of Applied Sciences Affiliated: No

Abstract

The models have been developed by using the wavelet transform technique (W) and artificial neural networks (ANN) methods for the forecasting of runoff which is an important factor in the planning of water resources. The rainfall data of Sivas meteorological station were used to develop the runoff forecasting models for Söğütlühan runoff station on Kızılırmak River. Firstly, the ANN models were developed by using the measured original rainfall series. Then, the measured rainfall data was decomposed into sub-series by the wavelet transform. The wavelet-artificial neural network (D-ANN) models were developed by using the rainfall sub-series. When the developed models were compared with the measured values, it was shown that the D-ANN models have better performance than the ANN models obtained with the original rainfall series.