Prediction of suspended sediment in river using fuzzy logic and multilinear regression approaches

Demirci M., Baltaci A.

Neural Computing and Applications, vol.23, no.SUPPL1, pp.145-151, 2013 (SCI-Expanded, Scopus) identifier identifier

  • Publication Type: Article / Article
  • Volume: 23 Issue: SUPPL1
  • Publication Date: 2013
  • Doi Number: 10.1007/s00521-012-1280-z
  • Journal Name: Neural Computing and Applications
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.145-151
  • Keywords: Forecasting, Fuzzy logic, Multilinear regression, Sediment rating curve, Suspended sediment
  • Hatay Mustafa Kemal University Affiliated: Yes

Abstract

Prediction of sediment concentration in a river is very important for many water resource projects. Conventional sediment rating curves (SRC), however, are not able to provide sufficiently accurate results. In this paper, a fuzzy logic approach is proposed to estimate suspended sediment concentration from streamflow. A comparison was performed between fuzzy logic (FL), SRC and multilinear regression models. It was based on a 5-year period of continuous streamflow, suspended sediment concentration and mean water temperature data of Sacremento Freeport Station operated by the United States Geological Survey. Based on the comparison of the results, it is found that the FL model gives better estimates than the other techniques. © 2012 Springer-Verlag London.