THE FLOW-RATE PREDICTION IN ERGENE WATERSHED
Abstract
DOI: 10.26471/cjees/2021/016/175
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.
- artificial
- neural
- networks
- Ergene
- watershed
- flow-rate
- prediction
- multiple
- linear
- regression
- support
- vector
- machine
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of CJEES and/or the editor(s). CJEES and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
© 2021 by the author(s). Licensee CJEES, Carpathian Association of Environment and Earth Sciences. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
How to cite
Checking for open citations...