THE FLOW-RATE PREDICTION IN ERGENE WATERSHED
Küçük Resim Yok
Tarih
2021
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Carpathian Assoc Environment And Earth Sciences
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
This paper presents an experimental study about prediction of the highest monthly average flow-rate of the Ergene River. Hydro-meteorological data from Luleburgaz Meteorology Station (MS) and Luleburgaz Flow Observation Station (FOS) have been used for prediction. Ergene watershed has point and non-point sources pollution and has seasonal floods. The study area is located in the middle of the watershed. First of all, hydro-meteorological data of all months between 1995 and 2017 were obtained from Luleburgaz FOS. After that, the relationship between the data were modeled by Artificial Neural Network (ANN), Multiple Linear Regression (MLR) and Support Vector Machine (SVM). Also, the monthly flow-rate of Ergene River Luleburgaz Station is predicted annually for the years 2017 and 2018. The results demonstrate that the ANN, MLR and SVM models can predict the flow-rate with high accuracy, but the ANN is the most appropriate model to the Ergene watershed data set.
Açıklama
Anahtar Kelimeler
Artificial Neural Networks, Ergene Watershed, Flow-Rate Prediction, Multiple Linear Regression, Support Vector Machine, Artificial Neural-Network, Support Vector Regression, Short-Term, River-Basin, Model, Ann, Management
Kaynak
Carpathian Journal Of Earth And Environmental Sciences
WoS Q Değeri
Q4
Scopus Q Değeri
Q3
Cilt
16
Sayı
2
