Uncertainty due to choice of measurement scale in extreme value modelling of North Sea storm severity

School Of Mathematical Sciences

Text available via DOI:

https://doi.org/10.1016/j.oceaneng.2012.07.001
Final published version

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Uncertainty due to choice of measurement scale in extreme value modelling of North Sea storm severity. / Reeve, D.T.; Randell, D.; Ewans, K.C. et al.
In: Ocean Engineering, Vol. 53, 2012, p. 164-176.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Author

Reeve, D.T. ; Randell, D. ; Ewans, K.C. et al. / Uncertainty due to choice of measurement scale in extreme value modelling of North Sea storm severity. In: Ocean Engineering. 2012 ; Vol. 53. pp. 164-176.

Bibtex

@article{44699b1271f045248906664011c262b6,

title = "Uncertainty due to choice of measurement scale in extreme value modelling of North Sea storm severity",

abstract = "Modelling extreme storm severity is critical to design and reliable operation of marine structures. Extreme hindcast storm peak significant wave heights (HS) for 816 locations throughout the North Sea are modelled, using the four parameter Poisson point process model of Wadsworth et al. (2010), incorporating measurement scale variability via a BoxCox transformation. The model allows estimation of the posterior distribution for measurement scale parameter and point process parameters within a Bayesian framework. The effect of measurement scale on return values of significant wave height (HS) is quantified by comparison with a three parameter Poisson point process model ignoring measurement scale uncertainty. It is found that the median value (over all locations) of the median posterior BoxCox parameter (per location) is approximately 0.7, suggesting that the appropriate measurement scale for extreme value analysis is HS0.7. The value of the median BoxCox parameter (per location) varies considerably between locations, with a 90% uncertainty band of approximately (0.2, 2.2) and quartiles of 0.4 and 1.2; the value of BoxCox parameter is also influenced by threshold choice for extreme value analysis in particular. The ratio (over all locations) of the (posterior median) return value from the four parameter model to the return value from the three parameter model (and a return period of 100 times the period of the hindcast) has a median value of 0.92, suggesting that median return values may be reduced for this data set by better modelling of measurement scale effects. The ratio of return values has a 90% uncertainty band of approximately (0.72, 1.37), illustrating the extra variability in return values that incorporation of measurement scale uncertainty introduces. {\textcopyright} 2012 Elsevier Ltd. All rights reserved.",

keywords = "Extreme value analysis, Measurement scale, Offshore design conditions, Bayesian frameworks, Box Cox transformation, Data sets, Effect of measurements, Extreme value, Four-parameter model, Hindcasts, Median value, North Sea, Offshore design, Point process, Poisson point process, Posterior distributions, Reliable operation, Return periods, Return value, Significant wave height, Three parameters, Three-parameter models, Threshold choice, Measurements, Offshore structures, Storms, Value engineering, Water waves, Uncertainty analysis, Bayesian analysis, hindcasting, modeling, severe weather, significant wave height, storm, uncertainty analysis, Atlantic Ocean",

author = "D.T. Reeve and D. Randell and K.C. Ewans and P. Jonathan",

year = "2012",

doi = "10.1016/j.oceaneng.2012.07.001",

language = "English",

volume = "53",

pages = "164--176",

journal = "Ocean Engineering",

issn = "0029-8018",

publisher = "Elsevier Ltd",

}

RIS

TY - JOUR

T1 - Uncertainty due to choice of measurement scale in extreme value modelling of North Sea storm severity

AU - Reeve, D.T.

AU - Randell, D.

AU - Ewans, K.C.

AU - Jonathan, P.

PY - 2012

Y1 - 2012

N2 - Modelling extreme storm severity is critical to design and reliable operation of marine structures. Extreme hindcast storm peak significant wave heights (HS) for 816 locations throughout the North Sea are modelled, using the four parameter Poisson point process model of Wadsworth et al. (2010), incorporating measurement scale variability via a BoxCox transformation. The model allows estimation of the posterior distribution for measurement scale parameter and point process parameters within a Bayesian framework. The effect of measurement scale on return values of significant wave height (HS) is quantified by comparison with a three parameter Poisson point process model ignoring measurement scale uncertainty. It is found that the median value (over all locations) of the median posterior BoxCox parameter (per location) is approximately 0.7, suggesting that the appropriate measurement scale for extreme value analysis is HS0.7. The value of the median BoxCox parameter (per location) varies considerably between locations, with a 90% uncertainty band of approximately (0.2, 2.2) and quartiles of 0.4 and 1.2; the value of BoxCox parameter is also influenced by threshold choice for extreme value analysis in particular. The ratio (over all locations) of the (posterior median) return value from the four parameter model to the return value from the three parameter model (and a return period of 100 times the period of the hindcast) has a median value of 0.92, suggesting that median return values may be reduced for this data set by better modelling of measurement scale effects. The ratio of return values has a 90% uncertainty band of approximately (0.72, 1.37), illustrating the extra variability in return values that incorporation of measurement scale uncertainty introduces. © 2012 Elsevier Ltd. All rights reserved.

AB - Modelling extreme storm severity is critical to design and reliable operation of marine structures. Extreme hindcast storm peak significant wave heights (HS) for 816 locations throughout the North Sea are modelled, using the four parameter Poisson point process model of Wadsworth et al. (2010), incorporating measurement scale variability via a BoxCox transformation. The model allows estimation of the posterior distribution for measurement scale parameter and point process parameters within a Bayesian framework. The effect of measurement scale on return values of significant wave height (HS) is quantified by comparison with a three parameter Poisson point process model ignoring measurement scale uncertainty. It is found that the median value (over all locations) of the median posterior BoxCox parameter (per location) is approximately 0.7, suggesting that the appropriate measurement scale for extreme value analysis is HS0.7. The value of the median BoxCox parameter (per location) varies considerably between locations, with a 90% uncertainty band of approximately (0.2, 2.2) and quartiles of 0.4 and 1.2; the value of BoxCox parameter is also influenced by threshold choice for extreme value analysis in particular. The ratio (over all locations) of the (posterior median) return value from the four parameter model to the return value from the three parameter model (and a return period of 100 times the period of the hindcast) has a median value of 0.92, suggesting that median return values may be reduced for this data set by better modelling of measurement scale effects. The ratio of return values has a 90% uncertainty band of approximately (0.72, 1.37), illustrating the extra variability in return values that incorporation of measurement scale uncertainty introduces. © 2012 Elsevier Ltd. All rights reserved.

KW - Extreme value analysis

KW - Measurement scale

KW - Offshore design conditions

KW - Bayesian frameworks

KW - Box Cox transformation

KW - Data sets

KW - Effect of measurements

KW - Extreme value

KW - Four-parameter model

KW - Hindcasts

KW - Median value

KW - North Sea

KW - Offshore design

KW - Point process

KW - Poisson point process

KW - Posterior distributions

KW - Reliable operation

KW - Return periods

KW - Return value

KW - Significant wave height

KW - Three parameters

KW - Three-parameter models

KW - Threshold choice

KW - Measurements

KW - Offshore structures

KW - Storms

KW - Value engineering

KW - Water waves

KW - Uncertainty analysis

KW - Bayesian analysis

KW - hindcasting

KW - modeling

KW - severe weather

KW - significant wave height

KW - storm

KW - uncertainty analysis

KW - Atlantic Ocean

U2 - 10.1016/j.oceaneng.2012.07.001

DO - 10.1016/j.oceaneng.2012.07.001

M3 - Journal article

VL - 53

SP - 164

EP - 176

JO - Ocean Engineering

JF - Ocean Engineering

SN - 0029-8018

ER -

Research

Links

Text available via DOI:

Keywords