MODELLING SNOWMELT RUNOFF USING AN ARTIFICIAL NEURAL NETWORK (ANN) APPROACH

Abstract eng:
The use of artificial neural networks (ANNs) is becoming increasingly common in the analysis of hydrology and water resources problems. In this research, an ANN was developed and used to model the snowmelt runoff, in a catchment located in a semiarid climate in Turkey. The multilayer perceptron (MLP) neural network was chosen for use in the current study. The one year data (2009) obtained from the stations, located in Erzurum Kırkgoze (Cipak) basin, are integrated into daily average time series of temperature (T), solar radiation (R), snow-covered area (S), snow water equivalent (SWE), runoff coefficient for snow (Cs). The results indicate that the artificial neural network method is suitable to predict the river discharges by using some variables and parameters of snowmelt for the Kırkgoze Basin.

• Export as: BibTeX | MARC | MARCXML | DC | EndNote | NLM | RefWorks
• Add to your basket