Neuro-fuzzy modelling of suspended sediment load: The need for a sound comparison with established methods

  • Authors:
  • Robert J. Abrahart;Ngahzaifa Ab Ghani

  • Affiliations:
  • School of Geography, University of Nottingham, Nottingham NG7 2RD, United Kingdom;School of Geography, University of Nottingham, Nottingham NG7 2RD, United Kingdom

  • Venue:
  • Advances in Engineering Software
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper questions the correctness of two bias-corrected sediment rating curve models that were used to compare and contrast traditional counterparts against state-of-the-art computational tools in a recent article on ''Adaptive neuro-fuzzy computing technique for suspended sediment estimation'' by Kisi et al. (2009). Mathematical and graphical procedures are used to demonstrate substantial and unexplained shortcomings in the reported equations. The superior performance of more advanced computational methods - such as neural network and neuro-fuzzy system solutions in the reported scenario - is thus brought into question.