A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Uncertainty analysis on extreme value analysis of significant wave height at eastern coast of Korea
Abstract In this study, we considered the problem of estimating long-term predictions of design wave height based on the observation data collected over 10–15 years along the eastern-coast of the Korean peninsula. We adopted a method that combines Bayesian method and extreme value theory. The conventional frequency analysis methods must be reconsidered in two ways. First, the conventional probability distributions used in the frequency analysis should be evaluated to determine whether they can accurately model the variation in extreme values. Second, the uncertainty in the frequency analysis should also be quantified. Therefore, we performed a comparative study of the Gumbel distribution and GEV distribution to show the higher efficiency of the latter. Further, we compared the Bayesian MCMC (Markov Chain Monte Carlo) scheme and the MLE (Maximum Likelihood Estimation) with asymptotic normal approximation for parameter estimation to confirm the advantage of the Bayesian MCMC with respect to uncertainty analysis.
Highlights ▸ We adopted a method that combines Bayesian method and extreme value theory. ▸ The conventional probability distributions were re-evaluated to determine whether the probability distribution can represent the effect of the extreme value. ▸ The uncertainty in the frequency analysis was quantified. ▸ We performed a comparative study of the Gumbel and GEV distributions to evaluate the efficiency. ▸ We compared the Bayesian MCMC scheme and the MLE with a quadratic approximation for parameter estimation to confirm the advantage of the Bayesian MCMC with respect to uncertainty analysis.
Uncertainty analysis on extreme value analysis of significant wave height at eastern coast of Korea
Abstract In this study, we considered the problem of estimating long-term predictions of design wave height based on the observation data collected over 10–15 years along the eastern-coast of the Korean peninsula. We adopted a method that combines Bayesian method and extreme value theory. The conventional frequency analysis methods must be reconsidered in two ways. First, the conventional probability distributions used in the frequency analysis should be evaluated to determine whether they can accurately model the variation in extreme values. Second, the uncertainty in the frequency analysis should also be quantified. Therefore, we performed a comparative study of the Gumbel distribution and GEV distribution to show the higher efficiency of the latter. Further, we compared the Bayesian MCMC (Markov Chain Monte Carlo) scheme and the MLE (Maximum Likelihood Estimation) with asymptotic normal approximation for parameter estimation to confirm the advantage of the Bayesian MCMC with respect to uncertainty analysis.
Highlights ▸ We adopted a method that combines Bayesian method and extreme value theory. ▸ The conventional probability distributions were re-evaluated to determine whether the probability distribution can represent the effect of the extreme value. ▸ The uncertainty in the frequency analysis was quantified. ▸ We performed a comparative study of the Gumbel and GEV distributions to evaluate the efficiency. ▸ We compared the Bayesian MCMC scheme and the MLE with a quadratic approximation for parameter estimation to confirm the advantage of the Bayesian MCMC with respect to uncertainty analysis.
Uncertainty analysis on extreme value analysis of significant wave height at eastern coast of Korea
Kim, Sang Ug (author) / Kim, Gunwoo (author) / Jeong, Weon Mu (author) / Jun, Kicheon (author)
Applied Ocean Research ; 41 ; 19-27
2013-02-09
9 pages
Article (Journal)
Electronic Resource
English
Uncertainty analysis on extreme value analysis of significant wave height at eastern coast of Korea
| Online Contents | 2013
On the Extreme Wave Height Analysis
| British Library Conference Proceedings | 1994