Bagged neural network for estimating the scour depth around pile groups. Issue 4 (2nd October 2018)

• Record Type: Journal Article
• Authors: Hosseini, Rashed; Fazloula, Ramin; Saneie, Mojtaba; Amini, Ata
• Is Part Of: International journal of river basin management. Volume 16:Issue 4(2018)
• Page Start: 401
• Page End: 412
• Publication Date: 2018-10-02
• Subjects: Pile group -- scour depth -- neural network -- overfitting -- bagging; Watershed management -- Periodicals; Water resources development -- Periodicals; Hydraulic engineering -- Periodicals; Watershed hydrology -- Periodicals; Water resources development; Watershed management; Watersheds; Periodicals; 551.483
• DOI: 10.1080/15715124.2017.1372449
• Languages: English
• ISSNs: 1814-2060

Abstract

ABSTRACT: Contrary to the single pier, due to the complexity of the scour mechanism around pile groups, empirical methods do not give a satisfactory prediction for the scour depth around pier with multiple piles. It was shown recently that artificial neural networks (NNs) have better prediction performance than empirical methods. In order to exploit the full potential of the NN procedure for predicting the scour depth around pile groups, a 'Bagging' technique is adopted in this paper. The comparison between several different approaches for improving the generalization performance of NNs shows that 'Bagging' is the most reliable method. Furthermore, the sensitivity analysis is performed on the data to determine the effect of different inputs on the scour depth around pile groups. This analysis shows that pile diameter and pile spacing are dominant contributors.