A multivariate ANN-wavelet approach for rainfall-runoff modeling

Vahid Nourani, Mehdi Komasi, Akira Mano

Research output: Contribution to journalArticlepeer-review

222 Citations (Scopus)

Abstract

Without a doubt the first step in any water resources management is the rainfall-runoff modeling over the watershed. However considering high stochastic property of the process, many models are being still developed in order to define such a complex phenomenon in the field of hydrologic engineering. Recently Artificial Neural Network (ANN) as a non-linear inter-extrapolator is extensively used by hydrologists for rainfall-runoff modeling as well as other fields of hydrology. In the current research, the wavelet analysis was linked to the ANN concept for modeling Ligvanchai watershed rainfall-runoff process at Tabriz, Iran. For this purpose the main time series of two variables, rainfall and runoff, were decomposed to some multi-frequently time series by wavelet theory, then these time series were imposed as input data to the ANN to predict the runoff discharge 1 day ahead. The obtained results show the proposed model can predict both short and long term runoff discharges because of using multi-scale time series of rainfall and runoff data as the ANN input layer.

Original languageEnglish
Pages (from-to)2877-2894
Number of pages18
JournalWater Resources Management
Volume23
Issue number14
DOIs
Publication statusPublished - 2009 Feb 12

Keywords

  • Artificial neural network
  • Black box model
  • Ligvanchai watershed
  • Rainfall-runoff modeling
  • Wavelet transform

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Water Science and Technology

Fingerprint Dive into the research topics of 'A multivariate ANN-wavelet approach for rainfall-runoff modeling'. Together they form a unique fingerprint.

Cite this