University of Tabriz Water and Soil Science 2008-5133 24 1 2014 06 21 Fuzzy Logic Model for Estimation of Aquifers Transmissivity Case study: Tasuj Plain Fuzzy Logic Model for Estimation of Aquifers Transmissivity Case study: Tasuj Plain 209 223 1546 FA A Klantari A Hosseinpour H Abghari A Klantari A Hosseinpour A Habibzadeh Journal Article 2014 06 24 This study presents a supervised committee fuzzy logic (SCFL) model to estimate transmissivity in the aquifer of the Tasuj Plain, Iran. The estimation of transmissivity especially in a heterogeneous aquifer is expensive and time consuming. In this study, fuzzy logic models such as Mamdani fuzzy logic (MFL), Larsen fuzzy logic (LSL) and Sugeno fuzzy logic (SFL) were applied to estimate transmissivity using hydrogeological and geophysical survey data. The results showed that all of these models have a similar fitting to the transmissivity data in the Tasuj Plain. The SCFL model was adopted to combine output of the three single fuzzy models instead of the selecting superior single model. To reap the advantage of considering single models, the SCFL proposes a nonlinear combination of individual FL model outputs through a committee fuzzy logic model. The SCFL method uses an artificial neural network (ANN) model to re-estimate transmissivity based on the output of the three FL models. The result showed improvement to the committee machine with a linear combination of FL models estimations. The results also showed significant fitting improvement to individual FL models. This study presents a supervised committee fuzzy logic (SCFL) model to estimate transmissivity in the aquifer of the Tasuj Plain, Iran. The estimation of transmissivity especially in a heterogeneous aquifer is expensive and time consuming. In this study, fuzzy logic models such as Mamdani fuzzy logic (MFL), Larsen fuzzy logic (LSL) and Sugeno fuzzy logic (SFL) were applied to estimate transmissivity using hydrogeological and geophysical survey data. The results showed that all of these models have a similar fitting to the transmissivity data in the Tasuj Plain. The SCFL model was adopted to combine output of the three single fuzzy models instead of the selecting superior single model. To reap the advantage of considering single models, the SCFL proposes a nonlinear combination of individual FL model outputs through a committee fuzzy logic model. The SCFL method uses an artificial neural network (ANN) model to re-estimate transmissivity based on the output of the three FL models. The result showed improvement to the committee machine with a linear combination of FL models estimations. The results also showed significant fitting improvement to individual FL models. https://water-soil.tabrizu.ac.ir/article_1546_7549584a1aae69b958771a4110838264.pdf