IAHR Document Library

« Back to Library Homepage « Proceedings of the 4th IAHR European Congress (Liege, 2016)

Rainfall Data Regression Model Using Fuzzy Set Logic

Author(s): Christos Tzimopoulos; Chris Evangelides; Basilios Papadopoulos

Linked Author(s):

Keywords: No keywords

Abstract: Classical linear regression has been used to measure the relationship between rainfall data in different meteorological stations, in order to evaluate a linear relation and to predict the values of rainfall in one station (dependent variables), from the rainfall values of an other station (independent variables). Classical linear regression makes rigid assumptions about the statistical properties of the model, accepting the error terms as random variables, and the violation of this assumption could affect the validity of the classical linear regression. Fuzzy regression assumes ambiguous, imprecise parameters and data and may be more effective than classical regression. In this paper, we evaluate the relation between rainfall data of Aggistron and Ano Vrontou meteorological stations, which are located in the region of Central Macedonia (Northern Greece), using fuzzy regression. The proposed model is a slight modification of Tanaka-Ishibuchi model with quadratic membership function and interactive fuzzy parameters. In this model, the dependent observed rainfall values are crisp, and the independent observed rainfall values as well as the parameters of the model are fuzzy. The results are presented with two credibility degrees h=0 and h=0.5.


Year: 2016

Copyright © 2022 International Association for Hydro-Environment Engineering and Research. All rights reserved. | Terms and Conditions