Yazar "Sevimli, M. Faik" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    FORECASTING THE RAINFALL DATA BY ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM
    (INT SCIENTIFIC CONFERENCE SGEM, 2009) Yarar, Alpaslan; Onucyildiz, Mustafa; Sevimli, M. Faik
    Konya is the biggest city of Turkey in terms of area and agricultural land, on the other hand sixth biggest city in terms of population. Because of the decrease of rainfall and increase in temperature, the agricultural production and daily water consumption are effected negatively in last years. Rainfall, one of the basic parameters of the hydrological cycle, has a big importance to determine the water budgets and to improve the water supply policy. In this study, monthly total rainfall data belong to Konya between 1970-2002 years, have been studied to forecast by Adaptive Neuro-Fuzzy Inference System (ANFIS). And model's performance has been evaluated by comparison with the Lineer Regression (LR) as one of the traditional methods.
  • Küçük Resim
    Öğe
    Modelling the Rainfall-Runoff Data of Susurluk Basin
    (PERGAMON-ELSEVIER SCIENCE LTD, 2010) Dorum, Atila; Yarar, Alpaslan; Sevimli, M. Faik; Onüçyıdız, Mustafa
    In this study, rainfall runoff relationship was tried to be set up by using Artificial Neural Networks (ANN) and Adaptive Neuro Fuzzy Interference Systems (ANFIS) models at Flow Observation Stations (FOS) on seven streams where runoff measurement has been made for long years in Susurluk Basin. A part of runoff data was used for training of ANN and ANFIS models and the other part was used to test the performance of the models. The performance comparison of the models was made with decisiveness coefficient (R(2)) and Root Mean Squared Errors (RMSE) values. In addition to this, a comparison of ANN and ANFIS with traditional methods was made by setting up Multi-regressional (MR) model. Except some stations, acceptable results such as R(2) value for ANN model and R(2) value for ANFIS model were obtained as 0.7587 and 0.8005, respectively. The high values of predicted errors, belonging to peak values at stations where multi variable flow is seen, affected R(2) and RMSE values negatively.