2018 Cilt 23 Sayı 2

Permanent URI for this collectionhttps://hdl.handle.net/11452/12466

Browse

Browsing by Subject "Artificial neural networks"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Streamflow and sediment load prediction using linear genetic programming
    (Uludağ Üniversitesi, 2018-07-17) Mehr, Ali Danandeh; Şorman, Ali Ünal
    Daily flow and suspended sediment discharge are two major hydrological variables that affect rivers’ morphology and ecosystem, particularly during flood events. Artificial neural networks (ANNs) have been successfully used to model and predict these variables in recent studies. However, these are implicit and cannot be simply used in practice. In this paper, linear genetic programming (LGP) approach has been suggested to develop explicit models to predict these variables in two rivers in Iran. The explicit relationships (prediction rules) evolved by LGP take the form of equations or program codes, which can be checked for its physical consistency. The results showed that the LGP outperforms ANNs to get global maximum and minimum discharges providing lowest root mean squared error and higher coefficient of efficiency both for training and validation periods.