Evaluation of Empirical Modelling Techniques for the Estimation of Sediment Amount in Rivers
<p>The sediment transport processes of streams have been the subject of research for many years. Sediment amount carried by a river is strongly correlated with the river’s flow rate and sediment concentration. This study aims to represent this correlation and to estimate the sediment amount us...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bursa Uludag University
2016-12-01
|
| Series: | Uludağ University Journal of The Faculty of Engineering |
| Subjects: | |
| Online Access: | http://mmfdergi.uludag.edu.tr/article/view/5000196482 |
| _version_ | 1797908022976053248 |
|---|---|
| author | Başak GÜVEN Zeynep AKDOĞAN |
| author_facet | Başak GÜVEN Zeynep AKDOĞAN |
| author_sort | Başak GÜVEN |
| collection | DOAJ |
| description | <p>The sediment transport processes of streams have been the subject of research for many years. Sediment amount carried by a river is strongly correlated with the river’s flow rate and sediment concentration. This study aims to represent this correlation and to estimate the sediment amount using four different modelling techniques: MLR, PLS, SVM, and ANN. Records of river flow, sediment concentration and sediment amount obtained from the Göksu River, located in the Eastern Mediterranean region of Turkey, are used as input data in the models. The aim of is this study is to evaluate the effectiveness of ANN modelling in the estimation of sediment amount carried by river flow. Fifty percent of the data are used as training set to develop the models. The other half of the data is used for verification set. The performance of the four models is evaluated by determination coefficient of prediction set (r<sup>2</sup><sub>pred</sub>). The results indicate that ANN is the most effective method (r<sup>2</sup><sub>pred</sub> = 0.94), followed by SVM (r<sup>2</sup><sub>pred</sub> = 0.72). MLR and PLS methods are the least effective techniques (r<sup>2</sup><sub>pred</sub> = 0.67) for estimating sediment amount in the Göksu River. Therefore, ANN approach is further studied to propose the best configuration for the prediction of river sediment amount.</p> |
| first_indexed | 2024-04-10T10:46:04Z |
| format | Article |
| id | doaj.art-ff87609f823f49f3b1ddddce747bc6b4 |
| institution | Directory Open Access Journal |
| issn | 2148-4147 2148-4155 |
| language | English |
| last_indexed | 2024-04-10T10:46:04Z |
| publishDate | 2016-12-01 |
| publisher | Bursa Uludag University |
| record_format | Article |
| series | Uludağ University Journal of The Faculty of Engineering |
| spelling | doaj.art-ff87609f823f49f3b1ddddce747bc6b42023-02-15T16:20:19ZengBursa Uludag UniversityUludağ University Journal of The Faculty of Engineering2148-41472148-41552016-12-0121230931810.17482/uujfe.393415000172460Evaluation of Empirical Modelling Techniques for the Estimation of Sediment Amount in RiversBaşak GÜVEN0Zeynep AKDOĞAN1Boğaziçi University Environmental Sciences InstituteBoğaziçi University Environmental Sciences Institute<p>The sediment transport processes of streams have been the subject of research for many years. Sediment amount carried by a river is strongly correlated with the river’s flow rate and sediment concentration. This study aims to represent this correlation and to estimate the sediment amount using four different modelling techniques: MLR, PLS, SVM, and ANN. Records of river flow, sediment concentration and sediment amount obtained from the Göksu River, located in the Eastern Mediterranean region of Turkey, are used as input data in the models. The aim of is this study is to evaluate the effectiveness of ANN modelling in the estimation of sediment amount carried by river flow. Fifty percent of the data are used as training set to develop the models. The other half of the data is used for verification set. The performance of the four models is evaluated by determination coefficient of prediction set (r<sup>2</sup><sub>pred</sub>). The results indicate that ANN is the most effective method (r<sup>2</sup><sub>pred</sub> = 0.94), followed by SVM (r<sup>2</sup><sub>pred</sub> = 0.72). MLR and PLS methods are the least effective techniques (r<sup>2</sup><sub>pred</sub> = 0.67) for estimating sediment amount in the Göksu River. Therefore, ANN approach is further studied to propose the best configuration for the prediction of river sediment amount.</p>http://mmfdergi.uludag.edu.tr/article/view/5000196482sediment amountrivermodellingANN |
| spellingShingle | Başak GÜVEN Zeynep AKDOĞAN Evaluation of Empirical Modelling Techniques for the Estimation of Sediment Amount in Rivers Uludağ University Journal of The Faculty of Engineering sediment amount river modelling ANN |
| title | Evaluation of Empirical Modelling Techniques for the Estimation of Sediment Amount in Rivers |
| title_full | Evaluation of Empirical Modelling Techniques for the Estimation of Sediment Amount in Rivers |
| title_fullStr | Evaluation of Empirical Modelling Techniques for the Estimation of Sediment Amount in Rivers |
| title_full_unstemmed | Evaluation of Empirical Modelling Techniques for the Estimation of Sediment Amount in Rivers |
| title_short | Evaluation of Empirical Modelling Techniques for the Estimation of Sediment Amount in Rivers |
| title_sort | evaluation of empirical modelling techniques for the estimation of sediment amount in rivers |
| topic | sediment amount river modelling ANN |
| url | http://mmfdergi.uludag.edu.tr/article/view/5000196482 |
| work_keys_str_mv | AT basakguven evaluationofempiricalmodellingtechniquesfortheestimationofsedimentamountinrivers AT zeynepakdogan evaluationofempiricalmodellingtechniquesfortheestimationofsedimentamountinrivers |