Advances in surrogate modeling for storm surge prediction: storm selection and addressing characteristics related to climate change
This paper establishes various advancements for the application of surrogate modeling techniques for storm surge prediction utilizing an existing database of high-fidelity, synthetic storms (tropical cyclones). Kriging, also known as Gaussian process regression, is specifically chosen as the surroga...
id |
ftunivsthongkong:oai:repository.ust.hk:1783.1-114872 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
The Hong Kong University of Science and Technology: HKUST Institutional Repository |
op_collection_id |
ftunivsthongkong |
language |
English |
topic |
Gaussian process regression Kriging Sea level rise Storm selection Storm surge Surrogate model extrapolation |
spellingShingle |
Gaussian process regression Kriging Sea level rise Storm selection Storm surge Surrogate model extrapolation Zhang, Jize Taflanidis, Alexandros A. Nadal-Caraballo, Norberto C. Melby, Jeffrey A. Diop, Fatimata Advances in surrogate modeling for storm surge prediction: storm selection and addressing characteristics related to climate change |
topic_facet |
Gaussian process regression Kriging Sea level rise Storm selection Storm surge Surrogate model extrapolation |
description |
This paper establishes various advancements for the application of surrogate modeling techniques for storm surge prediction utilizing an existing database of high-fidelity, synthetic storms (tropical cyclones). Kriging, also known as Gaussian process regression, is specifically chosen as the surrogate model in this study. Emphasis is first placed on the storm selection for developing the database of synthetic storms. An adaptive, sequential selection is examined here that iteratively identifies the storm (or multiple storms) that is expected to provide the greatest enhancement of the prediction accuracy when that storm is added into the already available database. Appropriate error statistics are discussed for assessing convergence of this iterative selection, and its performance is compared to the joint probability method with optimal sampling, utilizing the required number of synthetic storms to achieve the same level of accuracy as comparison metric. The impact on risk estimation is also examined. The discussion then moves to adjustments of the surrogate modeling framework to support two implementation issues that might become more relevant due to climate change considerations: future storm intensification and sea level rise (SLR). For storm intensification, the use of the surrogate model for prediction extrapolation is examined. Tuning of the surrogate model characteristics using cross-validation techniques and modification of the tuning to prioritize storms with specific characteristics are proposed, whereas an augmentation of the database with new/additional storms is also considered. With respect to SLR, the recently developed database for the US Army Corps of Engineers’ North Atlantic Comprehensive Coastal Study is exploited to demonstrate how surrogate modeling can support predictions that include SLR considerations. © 2018, Springer Nature B.V. |
format |
Article in Journal/Newspaper |
author |
Zhang, Jize Taflanidis, Alexandros A. Nadal-Caraballo, Norberto C. Melby, Jeffrey A. Diop, Fatimata |
author_facet |
Zhang, Jize Taflanidis, Alexandros A. Nadal-Caraballo, Norberto C. Melby, Jeffrey A. Diop, Fatimata |
author_sort |
Zhang, Jize |
title |
Advances in surrogate modeling for storm surge prediction: storm selection and addressing characteristics related to climate change |
title_short |
Advances in surrogate modeling for storm surge prediction: storm selection and addressing characteristics related to climate change |
title_full |
Advances in surrogate modeling for storm surge prediction: storm selection and addressing characteristics related to climate change |
title_fullStr |
Advances in surrogate modeling for storm surge prediction: storm selection and addressing characteristics related to climate change |
title_full_unstemmed |
Advances in surrogate modeling for storm surge prediction: storm selection and addressing characteristics related to climate change |
title_sort |
advances in surrogate modeling for storm surge prediction: storm selection and addressing characteristics related to climate change |
publishDate |
2018 |
url |
http://repository.ust.hk/ir/Record/1783.1-114872 https://doi.org/10.1007/s11069-018-3470-1 http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=0921-030X&rft.volume=v. 94&rft.issue=(3)&rft.date=2018&rft.spage=1225&rft.aulast=Zhang&rft.aufirst=J.&rft.atitle=Advances+in+surrogate+modeling+for+storm+surge+prediction%3A+storm+selection+and+addressing+characteristics+related+to+climate+change&rft.title=Natural+Hazards http://www.scopus.com/record/display.url?eid=2-s2.0-85053444759&origin=inward http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000452733500013 |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_relation |
http://repository.ust.hk/ir/Record/1783.1-114872 Natural Hazards, v. 94, (3), December 2018, p. 1225-1253 0921-030X https://doi.org/10.1007/s11069-018-3470-1 http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=0921-030X&rft.volume=v. 94&rft.issue=(3)&rft.date=2018&rft.spage=1225&rft.aulast=Zhang&rft.aufirst=J.&rft.atitle=Advances+in+surrogate+modeling+for+storm+surge+prediction%3A+storm+selection+and+addressing+characteristics+related+to+climate+change&rft.title=Natural+Hazards http://www.scopus.com/record/display.url?eid=2-s2.0-85053444759&origin=inward http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000452733500013 |
op_doi |
https://doi.org/10.1007/s11069-018-3470-1 |
container_title |
Natural Hazards |
container_volume |
94 |
container_issue |
3 |
container_start_page |
1225 |
op_container_end_page |
1253 |
_version_ |
1766134325182464000 |
spelling |
ftunivsthongkong:oai:repository.ust.hk:1783.1-114872 2023-05-15T17:35:14+02:00 Advances in surrogate modeling for storm surge prediction: storm selection and addressing characteristics related to climate change Zhang, Jize Taflanidis, Alexandros A. Nadal-Caraballo, Norberto C. Melby, Jeffrey A. Diop, Fatimata 2018 http://repository.ust.hk/ir/Record/1783.1-114872 https://doi.org/10.1007/s11069-018-3470-1 http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=0921-030X&rft.volume=v. 94&rft.issue=(3)&rft.date=2018&rft.spage=1225&rft.aulast=Zhang&rft.aufirst=J.&rft.atitle=Advances+in+surrogate+modeling+for+storm+surge+prediction%3A+storm+selection+and+addressing+characteristics+related+to+climate+change&rft.title=Natural+Hazards http://www.scopus.com/record/display.url?eid=2-s2.0-85053444759&origin=inward http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000452733500013 English eng http://repository.ust.hk/ir/Record/1783.1-114872 Natural Hazards, v. 94, (3), December 2018, p. 1225-1253 0921-030X https://doi.org/10.1007/s11069-018-3470-1 http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=0921-030X&rft.volume=v. 94&rft.issue=(3)&rft.date=2018&rft.spage=1225&rft.aulast=Zhang&rft.aufirst=J.&rft.atitle=Advances+in+surrogate+modeling+for+storm+surge+prediction%3A+storm+selection+and+addressing+characteristics+related+to+climate+change&rft.title=Natural+Hazards http://www.scopus.com/record/display.url?eid=2-s2.0-85053444759&origin=inward http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000452733500013 Gaussian process regression Kriging Sea level rise Storm selection Storm surge Surrogate model extrapolation Article 2018 ftunivsthongkong https://doi.org/10.1007/s11069-018-3470-1 2022-01-28T01:04:29Z This paper establishes various advancements for the application of surrogate modeling techniques for storm surge prediction utilizing an existing database of high-fidelity, synthetic storms (tropical cyclones). Kriging, also known as Gaussian process regression, is specifically chosen as the surrogate model in this study. Emphasis is first placed on the storm selection for developing the database of synthetic storms. An adaptive, sequential selection is examined here that iteratively identifies the storm (or multiple storms) that is expected to provide the greatest enhancement of the prediction accuracy when that storm is added into the already available database. Appropriate error statistics are discussed for assessing convergence of this iterative selection, and its performance is compared to the joint probability method with optimal sampling, utilizing the required number of synthetic storms to achieve the same level of accuracy as comparison metric. The impact on risk estimation is also examined. The discussion then moves to adjustments of the surrogate modeling framework to support two implementation issues that might become more relevant due to climate change considerations: future storm intensification and sea level rise (SLR). For storm intensification, the use of the surrogate model for prediction extrapolation is examined. Tuning of the surrogate model characteristics using cross-validation techniques and modification of the tuning to prioritize storms with specific characteristics are proposed, whereas an augmentation of the database with new/additional storms is also considered. With respect to SLR, the recently developed database for the US Army Corps of Engineers’ North Atlantic Comprehensive Coastal Study is exploited to demonstrate how surrogate modeling can support predictions that include SLR considerations. © 2018, Springer Nature B.V. Article in Journal/Newspaper North Atlantic The Hong Kong University of Science and Technology: HKUST Institutional Repository Natural Hazards 94 3 1225 1253 |