Abutment scour in clear-water and live-bed conditions by GMDH network

In the present study, the Group Method of Data Handling (GMDH) network has been utilized to predict abutments scour depth for both clear-water and live-bed conditions. The GMDH network was developed using a Back Propagation algorithm (BP). Input parameters that were considered as effective variables...

Full description

Saved in:
Bibliographic Details
Published in:Water science and technology 2013-01, Vol.67 (5), p.1121-1128
Main Authors: Najafzadeh, Mohammad, Barani, Gholam-Abbas, Kermani, Masoud Reza Hessami
Format: Article
Language:English
Subjects:
Abutments
Back propagation
Back propagation networks
Bridge abutments
Bridges
Data analysis
Datasets
Depth
Errors
Flow velocity
Geologic Sediments
Group method of data handling
Mathematical models
Parameters
Particle size
Properties
Root-mean-square errors
Scour
Scouring
Sediments
Support Vector Machine
Support vector machines
Testing
Training
Viscosity
Vortices
Water
Water depth
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the present study, the Group Method of Data Handling (GMDH) network has been utilized to predict abutments scour depth for both clear-water and live-bed conditions. The GMDH network was developed using a Back Propagation algorithm (BP). Input parameters that were considered as effective variables on abutment scour depth included properties of sediment size, geometry of bridge abutments, and properties of approaching flow. Training and testing performances of the GMDH network were carried out using dimensionless parameters that were collected from the literature. The testing results were compared with those obtained using the Support Vector Machines (SVM) model and the traditional equations. The GMDH network predicted the abutment scour depth with lower error (RMSE (root mean square error) = 0.29 and MAPE (mean absolute percentage of error) = 0.99) and higher (R = 0.98) accuracy than those performed using the SVM model and the traditional equations.
ISSN:0273-1223
1996-9732
DOI:10.2166/wst.2013.670