Modelling the rainfall-runoff data of susurluk basin

  • Authors:

  • Atila Dorum;Alpaslan Yarar;M. Faik Sevimli;Mustafa Onüçyildiz

  • Affiliations:

  • Gazi University, Faculty of Technical Education, Construction Education Department, 06500 Besevler, Ankara, Turkey;Selcuk University, Engineering and Architecture Faculty, Civil Engineering Department Hydraulics Division, 42031 Konya, Turkey;Selcuk University, Engineering and Architecture Faculty, Environmental Engineering Department, 42031 Konya, Turkey;Selcuk University, Engineering and Architecture Faculty, Civil Engineering Department Hydraulics Division, 42031 Konya, Turkey

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2010

Quantified Score

Hi-index 12.05

Visualization

Abstract

In this study, rainfall-runoff relationship was tried to be set up by using Artificial Neural Networks (ANN) and Adaptive Neuro Fuzzy Interference Systems (ANFIS) models at Flow Observation Stations (FOS) on seven streams where runoff measurement has been made for long years in Susurluk Basin. A part of runoff data was used for training of ANN and ANFIS models and the other part was used to test the performance of the models. The performance comparison of the models was made with decisiveness coefficient (R^2) and Root Mean Squared Errors (RMSE) values. In addition to this, a comparison of ANN and ANFIS with traditional methods was made by setting up Multi-regressional (MR) model. Except some stations, acceptable results such as R^2 value for ANN model and R^2 value for ANFIS model were obtained as 0.7587 and 0.8005, respectively. The high values of predicted errors, belonging to peak values at stations where multi variable flow is seen, affected R^2 and RMSE values negatively.