Prediction of scour depth around bridge piers using Gaussian process

Rajesh Kumar Neerukatti, Inho Kim, Masoud Yekani Fard, Aditi Chattopadhyay

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A reliable prognostics framework is essential to prevent catastrophic failure of bridges due to scour. In the U.S., scour accounts for almost 60% of bridge failures. Currently available techniques in the literature for predicting scour are mostly based on empirical equations and deterministic regression models, like Neural Networks and Support Vector Machines, and do not predict the evolution of scour over time. In this paper, we will discuss a Gaussian process model, which includes Bayesian uncertainty for prediction of time-dependent scour evolution. We will validate the model on the experimental data conducted in four different flumes in different conditions. The robustness of the algorithm will also be demonstrated under different scenarios, like lack of training data and equilibrium scour conditions. The results indicate that the algorithm is able to predict the scour evolution with an error of less than 20% for most of the time, and 5% or less given enough training data.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume8692
DOIs
StatePublished - 2013
Event2013 SPIE Conference on Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2013 - San Diego, CA, United States
Duration: Mar 10 2013Mar 14 2013

Other

Other2013 SPIE Conference on Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2013
CountryUnited States
CitySan Diego, CA
Period3/10/133/14/13

Fingerprint

wharves
Bridge piers
Scour
Gaussian Process
Prediction
education
predictions
Predict
Gaussian Model
Deterministic Model
Process Model
regression analysis
Support Vector Machine
Regression Model
Experimental Data
Neural Networks
Robustness
Uncertainty
Scenarios
Support vector machines

Keywords

  • Gaussian process
  • Prediction of scour depth
  • Temporal scour

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Neerukatti, R. K., Kim, I., Yekani Fard, M., & Chattopadhyay, A. (2013). Prediction of scour depth around bridge piers using Gaussian process. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 8692). [86922Z] https://doi.org/10.1117/12.2009901

Prediction of scour depth around bridge piers using Gaussian process. / Neerukatti, Rajesh Kumar; Kim, Inho; Yekani Fard, Masoud; Chattopadhyay, Aditi.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8692 2013. 86922Z.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Neerukatti, RK, Kim, I, Yekani Fard, M & Chattopadhyay, A 2013, Prediction of scour depth around bridge piers using Gaussian process. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 8692, 86922Z, 2013 SPIE Conference on Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2013, San Diego, CA, United States, 3/10/13. https://doi.org/10.1117/12.2009901
Neerukatti RK, Kim I, Yekani Fard M, Chattopadhyay A. Prediction of scour depth around bridge piers using Gaussian process. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8692. 2013. 86922Z https://doi.org/10.1117/12.2009901
Neerukatti, Rajesh Kumar ; Kim, Inho ; Yekani Fard, Masoud ; Chattopadhyay, Aditi. / Prediction of scour depth around bridge piers using Gaussian process. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8692 2013.
@inproceedings{6603899bfb6445eaa75e900b09fc0f97,
title = "Prediction of scour depth around bridge piers using Gaussian process",
abstract = "A reliable prognostics framework is essential to prevent catastrophic failure of bridges due to scour. In the U.S., scour accounts for almost 60{\%} of bridge failures. Currently available techniques in the literature for predicting scour are mostly based on empirical equations and deterministic regression models, like Neural Networks and Support Vector Machines, and do not predict the evolution of scour over time. In this paper, we will discuss a Gaussian process model, which includes Bayesian uncertainty for prediction of time-dependent scour evolution. We will validate the model on the experimental data conducted in four different flumes in different conditions. The robustness of the algorithm will also be demonstrated under different scenarios, like lack of training data and equilibrium scour conditions. The results indicate that the algorithm is able to predict the scour evolution with an error of less than 20{\%} for most of the time, and 5{\%} or less given enough training data.",
keywords = "Gaussian process, Prediction of scour depth, Temporal scour",
author = "Neerukatti, {Rajesh Kumar} and Inho Kim and {Yekani Fard}, Masoud and Aditi Chattopadhyay",
year = "2013",
doi = "10.1117/12.2009901",
language = "English (US)",
isbn = "9780819494757",
volume = "8692",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Prediction of scour depth around bridge piers using Gaussian process

AU - Neerukatti, Rajesh Kumar

AU - Kim, Inho

AU - Yekani Fard, Masoud

AU - Chattopadhyay, Aditi

PY - 2013

Y1 - 2013

N2 - A reliable prognostics framework is essential to prevent catastrophic failure of bridges due to scour. In the U.S., scour accounts for almost 60% of bridge failures. Currently available techniques in the literature for predicting scour are mostly based on empirical equations and deterministic regression models, like Neural Networks and Support Vector Machines, and do not predict the evolution of scour over time. In this paper, we will discuss a Gaussian process model, which includes Bayesian uncertainty for prediction of time-dependent scour evolution. We will validate the model on the experimental data conducted in four different flumes in different conditions. The robustness of the algorithm will also be demonstrated under different scenarios, like lack of training data and equilibrium scour conditions. The results indicate that the algorithm is able to predict the scour evolution with an error of less than 20% for most of the time, and 5% or less given enough training data.

AB - A reliable prognostics framework is essential to prevent catastrophic failure of bridges due to scour. In the U.S., scour accounts for almost 60% of bridge failures. Currently available techniques in the literature for predicting scour are mostly based on empirical equations and deterministic regression models, like Neural Networks and Support Vector Machines, and do not predict the evolution of scour over time. In this paper, we will discuss a Gaussian process model, which includes Bayesian uncertainty for prediction of time-dependent scour evolution. We will validate the model on the experimental data conducted in four different flumes in different conditions. The robustness of the algorithm will also be demonstrated under different scenarios, like lack of training data and equilibrium scour conditions. The results indicate that the algorithm is able to predict the scour evolution with an error of less than 20% for most of the time, and 5% or less given enough training data.

KW - Gaussian process

KW - Prediction of scour depth

KW - Temporal scour

UR - http://www.scopus.com/inward/record.url?scp=84878735258&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878735258&partnerID=8YFLogxK

U2 - 10.1117/12.2009901

DO - 10.1117/12.2009901

M3 - Conference contribution

AN - SCOPUS:84878735258

SN - 9780819494757

VL - 8692

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -