Dağlık Havzalarda Uydu Kar Verisi ve Dalgacık Sinir Ağı Tabanlı Olasılıklı Akım Modelleme Yaklaşımı

Abstract

Streamflow prediction is often a challenging issue for snow dominated basins where proper in-situ snow data might be limited and the snow physics is highly complex. The main aim of this study is to propose an alternative modeling solution by considering both accessibility of the inputs and simplicity of the model structure. We propose Wavelet Neural Network (WNN) model approach which takes probabilistic snow cover area in order to produce probabilistic streamflow in the mountainous basins. For the sake of the accessibility of the input data, snow probability maps are produced from cloud-free images of MODIS. The WNN model is trained and tested with observed hydro-meteorological data. Also, MultiLayer Perceptron Model (MLP) is used as a benchmark model. The approach is tested in a snow-dominated headwater (in altitude from 1559 to 3508 m) of Murat River which has a great importance as being one of the main tributaries of Euphrates River. According to the results, the approach is capable of detecting snow distribution in the area of interest and WNN is promising to generate probabilistic streamflow predictions.