TY  - JOUR
TI  - PROBABILISTIC RUNOFF MODELING APPROACH IN MOUNTAINOUS BASINS BASED ON SATELLITE SNOW DATA AND WAVELET NEURAL NETWORK
AB  - Streamflow prediction is often a challenging issue for snow dominated basins where properin-situ snow data might be limited and the snow physics is highly complex. The main aim of this study isto propose an alternative modeling solution by considering both accessibility of the inputs and simplicityof the model structure. We propose Wavelet Neural Network (WNN) model approach which takesprobabilistic snow cover area in order to produce probabilistic streamflow in the mountainous basins. Forthe sake of the accessibility of the input data, snow probability maps are produced from cloud-free imagesof 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-dominatedheadwater (in altitude from 1559 to 3508 m) of Murat River which has a great importance as being one ofthe main tributaries of Euphrates River. According to the results, the approach is capable of detecting snowdistribution in the area of interest and WNN is promising to generate probabilistic streamflow predictions.
AU  - Sensoy, Aynur
AU  - Uysal, Gökçen
DO  - 10.17482/uumfd.787147
PY  - 2020
JO  - Uludağ Üniversitesi Mühendislik Fakültesi Dergisi
VL  - 25
IS  - 3
SN  - 2148-4147
SP  - 1139
EP  - 1154
DB  - TRDizin
UR  - http://search/yayin/detay/444795
ER  -