Data-intelligence approaches for comprehensive assessment of discharge coefficient prediction in cylindrical weirs : Insights from extensive experimental data sets
(2024) In Measurement: Journal of the International Measurement Confederation 233.- Abstract
The present study collected a wide range of experimental data samples, including 855 records from various types of cylindrical weirs under diverse hydraulic conditions, setting the stage for an in-depth analysis for modeling of discharge coefficient. For this purpose, the prediction capability of four kernel-based methods (SVM, GPR, KELM, and KRR) and four neural network-based methods (FFBP, CFBP, GRNN, and RBFN) was thoroughly investigated. Results reveal that among the neural network methods, FFBP demonstrates superior performance with a correlation coefficient (R) of 0.973, Nash-Sutcliffe Efficiency (NSE) of 0.942, and Mean Squared Error (RMSE) of 0.014, particularly excelling at high flow rates. Conversely, KRR emerges as the... (More)
The present study collected a wide range of experimental data samples, including 855 records from various types of cylindrical weirs under diverse hydraulic conditions, setting the stage for an in-depth analysis for modeling of discharge coefficient. For this purpose, the prediction capability of four kernel-based methods (SVM, GPR, KELM, and KRR) and four neural network-based methods (FFBP, CFBP, GRNN, and RBFN) was thoroughly investigated. Results reveal that among the neural network methods, FFBP demonstrates superior performance with a correlation coefficient (R) of 0.973, Nash-Sutcliffe Efficiency (NSE) of 0.942, and Mean Squared Error (RMSE) of 0.014, particularly excelling at high flow rates. Conversely, KRR emerges as the top-performing kernel-based method with R = 0.901, NSE = 0.811, and RMSE = 0.058. Moreover, the prediction process unveils challenges associated with hydraulic conditions, notably the presence of upstream ramps, which substantially diminish the accuracy of modeling results by 112 %.
(Less)
- author
- Roushangar, Kiyoumars ; Shahnazi, Saman LU and Mehrizad, Amir
- organization
- publishing date
- 2024-06
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Artificial neural networks, Cylindrical weir, Discharge coefficient, Discharge prediction, Kernel-based models
- in
- Measurement: Journal of the International Measurement Confederation
- volume
- 233
- article number
- 114673
- publisher
- Elsevier
- external identifiers
-
- scopus:85191334306
- ISSN
- 0263-2241
- DOI
- 10.1016/j.measurement.2024.114673
- language
- English
- LU publication?
- yes
- id
- 278aac1a-8745-45f4-88e3-e10064ef5c37
- date added to LUP
- 2024-05-07 15:24:01
- date last changed
- 2024-05-07 15:24:11
@article{278aac1a-8745-45f4-88e3-e10064ef5c37, abstract = {{<p>The present study collected a wide range of experimental data samples, including 855 records from various types of cylindrical weirs under diverse hydraulic conditions, setting the stage for an in-depth analysis for modeling of discharge coefficient. For this purpose, the prediction capability of four kernel-based methods (SVM, GPR, KELM, and KRR) and four neural network-based methods (FFBP, CFBP, GRNN, and RBFN) was thoroughly investigated. Results reveal that among the neural network methods, FFBP demonstrates superior performance with a correlation coefficient (R) of 0.973, Nash-Sutcliffe Efficiency (NSE) of 0.942, and Mean Squared Error (RMSE) of 0.014, particularly excelling at high flow rates. Conversely, KRR emerges as the top-performing kernel-based method with R = 0.901, NSE = 0.811, and RMSE = 0.058. Moreover, the prediction process unveils challenges associated with hydraulic conditions, notably the presence of upstream ramps, which substantially diminish the accuracy of modeling results by 112 %.</p>}}, author = {{Roushangar, Kiyoumars and Shahnazi, Saman and Mehrizad, Amir}}, issn = {{0263-2241}}, keywords = {{Artificial neural networks; Cylindrical weir; Discharge coefficient; Discharge prediction; Kernel-based models}}, language = {{eng}}, publisher = {{Elsevier}}, series = {{Measurement: Journal of the International Measurement Confederation}}, title = {{Data-intelligence approaches for comprehensive assessment of discharge coefficient prediction in cylindrical weirs : Insights from extensive experimental data sets}}, url = {{http://dx.doi.org/10.1016/j.measurement.2024.114673}}, doi = {{10.1016/j.measurement.2024.114673}}, volume = {{233}}, year = {{2024}}, }