2016 Cilt 21 Sayı 2

Permanent URI for this collectionhttps://hdl.handle.net/11452/11720

Browse

Browsing by Subject "ANN"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Evaluation of empirical modelling techniques for the estimation of sediment amount in rivers
    (Uludağ Üniversitesi, 2016-11-17) Güven, Başak; Akdoğan, Zeynep
    The sediment transport processes of streams have been the subject of research for many years. Sediment amount carried by a river is strongly correlated with the river’s flow rate and sediment concentration. This study aims to represent this correlation and to estimate the sediment amount using four different modelling techniques: MLR, PLS, SVM, and ANN. Records of river flow, sediment concentration and sediment amount obtained from the Göksu River, located in the Eastern Mediterranean region of Turkey, are used as input data in the models. The aim of is this study is to evaluate the effectiveness of ANN modelling in the estimation of sediment amount carried by river flow. Fifty percent of the data are used as training set to develop the models. The other half of the data is used for verification set. The performance of the four models is evaluated by determination coefficient of prediction set (r 2 pred). The results indicate that ANN is the most effective method (r2 pred = 0.94), followed by SVM (r 2 pred = 0.72). MLR and PLS methods are the least effective techniques (r 2 pred = 0.67) for estimating sediment amount in the Göksu River. Therefore, ANN approach is further studied to propose the best configuration for the prediction of river sediment amount.
  • Thumbnail Image
    Item
    On the calibration of multigene genetic programming to simulate low flows in the Moselle River
    (Uludağ Üniversitesi, 2016-11-27) Mehr, Ali Danandeh; Demirel, Mehmet C.
    The aim of this paper is to calibrate a data-driven model to simulate Moselle River flows and compare the performance with three different hydrologic models from a previous study. For consistency a similar set up and error metric are used to evaluate the model results. Precipitation, potential evapotranspiration and streamflow from previous day have been used as inputs. Based on the calibration and validation results, the proposed multigene genetic programming model is the best performing model among four models. The timing and the magnitude of extreme low flow events could be captured even when we use root mean squared error as the objective function for model calibration. Although the model is developed and calibrated for Moselle River flows, the multigene genetic algorithm offers a great opportunity for hydrologic prediction and forecast problems in the river basins with scarce data issues.