Mustafa Erkan Turan

Predicting Monthly River Flows by Genetic Fuzzy Systems

Reliable flow forecasts are key to developing river regulation schemes such as reservoirs. River flow prediction has conventionally been undertaken by physical and black-box models. Several black-box type models have been employed to achieve this end. Of these, genetic fuzzy systems have been used in this study as they have relatively attracted limited attention to date. Genetic-fuzzy systems are the fuzzy systems that have the capability of learning and tuning by Genetic Algorithms. Employing two different fuzzy inference systems, a case study on Gediz river basin has been performed in an attempt to find a suitable genetic fuzzy system for flow prediction.

Generalized regression neural networks for municipal water consumption prediction

This statement of retraction refers to the iFirst version of the paper that has since been removed from this site. A PDF version of the retracted article can be viewed in the Supplementary Content section of this article

Fuzzy Systems Tuned By Swarm Based Optimization Algorithms for Predicting Stream flow

River flow prediction is an important phenomenon in water resources for which different methods and perspective have been used. Using fuzzy system with black box perspective is one of them. Fuzzy systems have some parameters and properties that have to be determined. This is an optimization problem that can be solved by swarm optimization techniques among several techniques. Swarm optimization are developed by inspiring from the behavior of the animals living as swarm. The study presents two achievements fuzzy system that tuned by swarm optimization algorithms can be used for prediction of monthly mean streamflow and which swarm optimization algorithm is better than the others for tuning fuzzy systems. Three swarm optimization algorithms, hunter search, firefly, artificial bee colony are used in this study. These algorithms are compared with mean performance values and convergence speed. Monthly streamflow data of three stream gauging stations in Susurluk Basin are used for the case study. The results show, swarm optimization algorithms can be used for prediction of monthly mean streamflow and ABC algorithm has better performance values than other optimization algorithms.

Fuzzy Conceptual Hydrological Model for Water Flow Prediction

Reliability in flow prediction is key to designing water resources projects. Over prediction may result in overdesign whereas under prediction brings about insufficient capacity solutions. While the former means insufficient use of financial resources, the latter may result in some water demand unmet. Therefore, so many techniques have been developed and used to make better flow prediction. In this study, this traditional problem is revisited in an attempt to improve the modeling performance of long used conceptual hydrological models. This is attained by incorporating fuzzy systems into a presently used conceptual model. The fuzzy integration process is carried out through the replacement of the storage elements of conceptual model by fuzzy systems. The case study undertaken has proved that the fuzzy conceptual model developed is quite competitive with ordinary conceptual model and promises improved predictions.

Akarçay Nehri Aylık Akımlarının Yapay Sinir Ağları ile Tahmini

Akarsulardaki duzenlemeler ve uygulamalar projelendirilirken, guvenilir akim tahminlerinin yapilmasi buyuk bir onem tasimaktadir. Geleneksel akim tahmini yontemleri, sistemin icerdigi dogrusal olmayan yapisi dolayisi ile etkin tahminler yapmada yetersiz kalabilmektedir. Bunun icin alternatif tahmin yontemlerine ihtiyac duyulmaktadir. Bu calismada tahmin uygulamalarinda sikca kullanilan yapay sinir aglari yontemi kullanilarak Akarcay kapali havzasindaki aylik akimlarin, yagis ve akim gozlemlerinden tahmin edilmesi ele alinmistir. Havzada mevcut bulunan yagis gozlem istasyonlarinin yerlesimi, gozlem araligi gibi parametreler bagli olarak 4 ayri kategoride model tasarlanmistir. Elde edilen sonuclar cok degiskenli regresyon analizi sonuclari ile kiyaslanarak Yapay Sinir Aglarinin, akim ve yagis gozlemlerinden, akis tahmini problemine basarili bir sekilde uygulanabilecegi ve guvenli tahminler urettigi ortaya konmustur