Evaluation of ANN, GEP, and regression models to estimate the discharge coefficient for the rectangular broad-crested weir
Document Type
Article
Publication Date
1-1-2022
Abstract
Broad-crested weirs are structures used to measure and control the water flows in rivers, canals, and irrigation and drainage networks. Accurate estimation of spillway discharge is one of the most striking elements in measurement structures. So far, many researchers have studied this issue based on various experimental conditions and a specific range of optional variables. They also have presented several relations. In the present study, 113 data sets of Bos were used for applicability of Artificial Neural Network (ANN), Gene expression programming (GEP), regression models to estimate the discharge coefficient for the rectangular broad-crested weirs. The effectiveness of the models was calculated using statistical criteria, including the coefficient of determination (R2), Root Mean Square Error (RMSE), and mean absolute error ( MAE). Comparing the models showed that the ANN with the highest R-2 coefficient (0.9916), lowest RMSE = 0.0012, and MAE = 0.00052 has the best discharge coefficient estimation than GEP models, regression models, and other empirical relations for the rectangular broadcrested weirs.
Keywords
rectangular broad-crested weirs, discharge coefficient, ANN, GEP, regression model
Divisions
sch_civ
Funders
Faculty of Agriculture, Bu-Ali Sina University in Hamedan, HighEnd Foreign Expert Project Plan of College of Civil Engineering of Fuzhou University
Publication Title
POLISH JOURNAL OF ENVIRONMENTAL STUDIES
Volume
31
Issue
5
Publisher
HARD
Publisher Location
POST-OFFICE BOX, 10-718 OLSZTYN 5, POLAND