File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A Gaussian Process-Based emulator for modeling pedestrian-level wind field

TitleA Gaussian Process-Based emulator for modeling pedestrian-level wind field
Authors
KeywordsGaussian process
Emulator
Pedestrian-level wind environment
Model evaluation
Lift-up building
Issue Date2021
PublisherPergamon. The Journal's web site is located at http://www.elsevier.com/locate/buildenv
Citation
Building and Environment, 2021, v. 188, p. article no. 107500 How to Cite?
AbstractWind tunnel tests and computational fluid dynamics (CFD) simulations remain the main modeling techniques in wind engineering despite being expensive, time-consuming, and requiring special facilities and expert knowledge. There is a clear need for a fast, accurate, but, at the same time, computationally economical substitute. This study proposes a Gaussian Process-based (GP-based) emulator to predict the pedestrian-level wind environment near a lift-up building – an isolated, unconventionally configured building. The proposed GP-based emulator transcends the limitations of previous emulators as it can handle many inputs (8) and output parameters (384) and a large dataset (150 CFD simulations). To increase computational efficiency, the current study proposes a data reduction method based on Principal Component Analysis (PCA) and a technique to estimate hyper-parameters based on optimization. The latter can efficiently compute 250 hyper-parameters and requires no prior knowledge of their probability distributions. The emulator is faster, by a factor of 107 than CFD simulations in predicting wind speeds, and its accuracy is substantiated using both qualitative and quantitative analyses, which reveal that the emulator's predictions of all-prominent flow features near a building have no systematic bias, are highly accurate, and have great reproductivity.
Persistent Identifierhttp://hdl.handle.net/10722/297158
ISSN
2023 Impact Factor: 7.1
2023 SCImago Journal Rankings: 1.647
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWeerasuriya, AU-
dc.contributor.authorZhang, X-
dc.contributor.authorLu, B-
dc.contributor.authorTse, KT-
dc.contributor.authorLiu, CH-
dc.date.accessioned2021-03-08T07:14:59Z-
dc.date.available2021-03-08T07:14:59Z-
dc.date.issued2021-
dc.identifier.citationBuilding and Environment, 2021, v. 188, p. article no. 107500-
dc.identifier.issn0360-1323-
dc.identifier.urihttp://hdl.handle.net/10722/297158-
dc.description.abstractWind tunnel tests and computational fluid dynamics (CFD) simulations remain the main modeling techniques in wind engineering despite being expensive, time-consuming, and requiring special facilities and expert knowledge. There is a clear need for a fast, accurate, but, at the same time, computationally economical substitute. This study proposes a Gaussian Process-based (GP-based) emulator to predict the pedestrian-level wind environment near a lift-up building – an isolated, unconventionally configured building. The proposed GP-based emulator transcends the limitations of previous emulators as it can handle many inputs (8) and output parameters (384) and a large dataset (150 CFD simulations). To increase computational efficiency, the current study proposes a data reduction method based on Principal Component Analysis (PCA) and a technique to estimate hyper-parameters based on optimization. The latter can efficiently compute 250 hyper-parameters and requires no prior knowledge of their probability distributions. The emulator is faster, by a factor of 107 than CFD simulations in predicting wind speeds, and its accuracy is substantiated using both qualitative and quantitative analyses, which reveal that the emulator's predictions of all-prominent flow features near a building have no systematic bias, are highly accurate, and have great reproductivity.-
dc.languageeng-
dc.publisherPergamon. The Journal's web site is located at http://www.elsevier.com/locate/buildenv-
dc.relation.ispartofBuilding and Environment-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectGaussian process-
dc.subjectEmulator-
dc.subjectPedestrian-level wind environment-
dc.subjectModel evaluation-
dc.subjectLift-up building-
dc.titleA Gaussian Process-Based emulator for modeling pedestrian-level wind field-
dc.typeArticle-
dc.identifier.emailWeerasuriya, AU: asiriuw@hku.hk-
dc.identifier.emailLiu, CH: chliu@hkucc.hku.hk-
dc.identifier.authorityLiu, CH=rp00152-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1016/j.buildenv.2020.107500-
dc.identifier.scopuseid_2-s2.0-85097462980-
dc.identifier.hkuros321529-
dc.identifier.volume188-
dc.identifier.spagearticle no. 107500-
dc.identifier.epagearticle no. 107500-
dc.identifier.isiWOS:000609486700007-
dc.publisher.placeUnited Kingdom-
dc.identifier.issnl0360-1323-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats