Artificial Neural Network Approaches For Inflow Estimation At Adiguzel Dam, Turkey

Küçük Resim



Dergi Başlığı

Dergi ISSN

Cilt Başlığı


Beykent Üniversitesi

Erişim Hakkı


Accurate modeling and forecasting of hydrological processes such as rainfall, rainfall run off relationship, runoff, is important for management and planning of water resources. In this study, applicability of Artificial Neural Network (ANN) methods for inflow forecasting at Adıgüzel dam on the Büyük Menderes River catchment was investigated. For this purpose, daily river flow data points were obtained from two river flow gauge stations on the Büyük Menderes river, Çıtak Köprü (713), Dört Değirmen (735), over 12 years, 1988 - 2000, and models having various input structures were constructed. The two different types of ANN, Feed Forward Neural Networks and Radial Basis Neural Networks, have been used to forecast daily river flow. The models were trained and tested by FFNN and RBNN and the results of models were compared with field observation data. Criteria for performance evaluation were identified in order to evaluate and compare the performances of FFNN and RBNN models. Then the best fit model and network structure were determined according to these criteria.


Anahtar Kelimeler

Inflow, ANN, Feed Forward Neural Networks, Radial Basis Neural Networks, Adıgüzel Dam, Büyük Menderes Catchment


WoS Q Değeri

Scopus Q Değeri




Journal of Science and Technology 2 (2), 2008, 278-292