Estimation of scour depth at bridges with complex pier foundations using support vector regression integrated with feature selection

Hoang, Nhat‐Duc; Liao, Kuo‐Wei; Tran, Xuan-Linh

doi:10.1007/s13349-018-0287-2

Cited by 18 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, in the first method, the used algorithm also demonstrated outstanding predictive performance due to implementing the concept of systemic risk minimization. This algorithm considers both the training error and model generalization (Hoang et al 2018). The experiences of previous studies were also incorporated to estimate the values of constant parameters in the SVR algorithm.…”

Section: Svr Methodsmentioning

confidence: 99%

The effects of splitters on the downstream scour hole of overflow spillways: application of support vector regression

2021

View full text Add to dashboard Cite

One of the most effective ways to reduce the water jet erosion power during dam overflow is to use splitters on the lower side of spillway. The dimensions of scouring holes and their location in the dam basin should be accurately determined. Experimental models and data driven techniques can be effectively used for estimating the dimensions of scouring holes. The focus of this paper is evaluating the effects of splitters on the downstream scour hole of overflow spillways and providing an optimized splitter configuration. The Support Vector Regression (SVR) method performance in predicting the scour hole dimensions and its location downstream of the dam has been examined using 116 experimental data. In order to evaluate the efficiency of the proposed model, we used different statistical measures. The results show that the presence of splitters decreases the slope of downstream scouring in all situations. It is also shown that the SVR method can accurately estimate the dimensions of the scour hole and its location.

show abstract

Section: Svr Methodsmentioning

confidence: 99%

The effects of splitters on the downstream scour hole of overflow spillways: application of support vector regression

2021

View full text Add to dashboard Cite

show abstract

“…The parameters considered were the width and the shape factor of the pier, skew of the pier to approach flow, size of the grain in the bed, gradation of bed material, and depth and velocity of the flow. [121] used laboratory data which includes four datasets from the Hydrotech Research Institute of National Taiwan University. Complex pier foundation scour measurements were taken in a sand bed.…”

Section: Cluster 2-machine Learning-based Researchmentioning

confidence: 99%

“…They suggested future studies consider the efficiency, duration required for computation, stability of artificial intelligence methods, and techniques in between complements. In their research based on support vector regression, [121] obtained better predictions when support vector regressions are used together with algorithms for selecting features. The variable neighborhood search algorithm had the best performance when compared with sequential forward selection and sequential backward selection for parameter selection.…”

Section: Cluster 2-machine Learning-based Researchmentioning

confidence: 99%

Scour Detection with Monitoring Methods and Machine Learning Algorithms—A Critical Review

et al. 2023

View full text Add to dashboard Cite

Foundation scour is a widespread reason for the collapse of bridges worldwide. However, assessing bridges is a complex task, which requires a comprehensive understanding of the phenomenon. This literature review first presents recent scour detection techniques and approaches. Direct and indirect monitoring and machine learning algorithm-based studies are investigated in detail in the following sections. The approaches, models, characteristics of data, and other input properties are outlined. The outcomes are given with their advantages and limitations. Finally, assessments are provided at the synthesis of the research.

show abstract

“…However, due to many uncertainties in ANN modeling techniques, many attempts have been made by researchers to improve the model efficiency by applying optimization algorithms or developing other AI methods. The application of support vector regression (SVR) model in scour hole modeling has been significantly used in recent times (e.g., Goyal and Ojha 2011;Sharafi et al 2016;Hoang et al 2018;Sun et al 2021). It is imperative to note that the dimensionality of the input space in the SVR model does not affect the computational complexity.…”

Section: Introductionmentioning

confidence: 99%

Hybrid model of support vector regression and innovative gunner optimization algorithm for estimating ski-jump spillway scour depth

et al. 2022

View full text Add to dashboard Cite

Scour hole that occurs downstream of the hydraulic structures threatens the safety and stability of the hydraulic structures. The scour around the structures is a complex and important hydraulic phenomenon; hence, it requires a data extensive research for the accurate estimation of scour depth. Although many analytical models are available for scour depth estimation, they suffer from huge limitations. In this research, the support vector regression (SVR) model and SVR ensemble with the metaheuristic algorithm of innovative gunner (SVR-AIG) models have been developed for accurate prediction of scour depth downstream of the ski-jump spillways. Field measurements including head and discharge intensity are used for developing the models. The performances of the models are compared using root mean square error (RMSE), mean average error (MAE), and correlation coefficient (CC) criteria and some statistical plots. The results showed that the hybrid SVR-AIG-based estimations (with CC = 0.987, 0.991, RMSE = 2.839, 1.987, and MAE = 2.247, 1.201) are more accurate than the SVR standalone model estimations (with CC = 0.942, 0.975, RMSE = 5.686, 4.040, and MAE = 4.114, 3.201) at the training and testing phases. This study is an important reference for analyzing the high capability of the AIG as an optimization tool in improving scour estimations of a standalone model. Also, this algorithm eliminates the trial-and-error procedure to optimize the internal parameters during the model development. Graphical abstract

show abstract

Estimation of scour depth at bridges with complex pier foundations using support vector regression integrated with feature selection

Cited by 18 publications

References 43 publications

The effects of splitters on the downstream scour hole of overflow spillways: application of support vector regression

The effects of splitters on the downstream scour hole of overflow spillways: application of support vector regression

Scour Detection with Monitoring Methods and Machine Learning Algorithms—A Critical Review

Hybrid model of support vector regression and innovative gunner optimization algorithm for estimating ski-jump spillway scour depth

Contact Info

Product

Resources

About