UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Performance Assessment of Buildings Subjected to Earthquake-Induced Landslides through Gaussian Process Regression

Miluccio, Giacomo; Gentile, Roberto; Galasso, Carmine; Parisi, Fulvio; (2022) Performance Assessment of Buildings Subjected to Earthquake-Induced Landslides through Gaussian Process Regression. In: 13th International Conference on Structural Safety & Reliability Program. International Association for Structural Safety & Reliability: Shanghai, China. Green open access

[thumbnail of ICOSSAR2021 Full-paper_Clean Version.pdf]
Preview
Text
ICOSSAR2021 Full-paper_Clean Version.pdf - Accepted Version

Download (1MB) | Preview

Abstract

Earthquake-induced landslides can significantly increase structural damage to buildings located on slopes with respect to the damage due to ground shaking only. Accordingly, multi-hazard vulnerability modelling of structures should account for the cumulative damage due to earthquake-induced ground motions and landslide-related actions. This paper presents a numerical procedure based on surrogate modelling for the computationally efficient prediction of structural response to earthquake shaking and resulting landslides if any. Specifically, discriminant classifiers and Gaussian process regression are used to develop metamodels mapping the main structural characteristics (e.g., geometric and material properties) to engineering demand parameters of interest. The proposed procedure is applied to an archetype reinforced concrete frame building designed only for gravity loads and located at the toe of a slope. Analysis results show that surrogate models allow a quick yet accurate prediction of structural performance.

Type: Proceedings paper
Title: Performance Assessment of Buildings Subjected to Earthquake-Induced Landslides through Gaussian Process Regression
Event: 13th International Conference on Structural Safety & Reliability (ICOSSAR 2021-22)
Location: Shanghai, China
Open access status: An open access version is available from UCL Discovery
Publisher version: http://www.icossar2021.org/Assets/userfiles/sys_eb...
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: buildings; earthquakes; landslides; Gaussian process regression; multi-hazard performance assessment.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Inst for Risk and Disaster Reduction
URI: https://discovery.ucl.ac.uk/id/eprint/10180482
Downloads since deposit
0Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item