Details
| Original language | English |
|---|---|
| Pages (from-to) | 2179-2195 |
| Number of pages | 17 |
| Journal | Earthquake Engineering and Structural Dynamics |
| Volume | 52 |
| Issue number | 7 |
| Publication status | Published - 9 May 2023 |
Abstract
A Bayesian framework to characterize ground motions even in the presence of missing data is developed. This approach features the combination of seismological knowledge (a priori knowledge) with empirical observations (even incomplete) via Bayesian inference. At its core is a Bayesian neural network model that probabilistically learns temporal patterns from ground motion data. Uncertainties are accounted for throughout the framework. Performance of the approach has been quantitatively demonstrated via various missing data scenarios. This framework provides a general solution to dealing with missing data in ground motion records by providing various forms of representation of ground motions in a probabilistic manner, allowing it to be adopted for numerous engineering and seismological applications. Notably, it is compatible with the versatile Monte Carlo simulation scheme, such that stochastic dynamic analyses are still achievable even with missing data. Furthermore, it serves as a complementary approach to current stochastic ground-motion models in data-scarce regions under the growing interests of PBEE (performance-based earthquake engineering), mitigating the data-model dependence dilemma due to the paucity of data, and ultimately, as a fundamental solution to the limited data problem in data scarce regions.
Keywords
- Bayesian model updating, earthquake ground motion, evolutionary power spectra, missing data, stochastic variational inference, uncertainty quantification
ASJC Scopus subject areas
- Engineering(all)
- Civil and Structural Engineering
- Earth and Planetary Sciences(all)
- Geotechnical Engineering and Engineering Geology
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Earthquake Engineering and Structural Dynamics, Vol. 52, No. 7, 09.05.2023, p. 2179-2195.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - A physics-informed Bayesian framework for characterizing ground motion process in the presence of missing data
AU - Chen, Yu
AU - Patelli, Edoardo
AU - Edwards, Benjamin
AU - Beer, Michael
N1 - Funding Information: This work was supported by the European Union Horizon 2020 Marie Skłodowska‐Curie Actions project URBASIS [Project no. 813137].
PY - 2023/5/9
Y1 - 2023/5/9
N2 - A Bayesian framework to characterize ground motions even in the presence of missing data is developed. This approach features the combination of seismological knowledge (a priori knowledge) with empirical observations (even incomplete) via Bayesian inference. At its core is a Bayesian neural network model that probabilistically learns temporal patterns from ground motion data. Uncertainties are accounted for throughout the framework. Performance of the approach has been quantitatively demonstrated via various missing data scenarios. This framework provides a general solution to dealing with missing data in ground motion records by providing various forms of representation of ground motions in a probabilistic manner, allowing it to be adopted for numerous engineering and seismological applications. Notably, it is compatible with the versatile Monte Carlo simulation scheme, such that stochastic dynamic analyses are still achievable even with missing data. Furthermore, it serves as a complementary approach to current stochastic ground-motion models in data-scarce regions under the growing interests of PBEE (performance-based earthquake engineering), mitigating the data-model dependence dilemma due to the paucity of data, and ultimately, as a fundamental solution to the limited data problem in data scarce regions.
AB - A Bayesian framework to characterize ground motions even in the presence of missing data is developed. This approach features the combination of seismological knowledge (a priori knowledge) with empirical observations (even incomplete) via Bayesian inference. At its core is a Bayesian neural network model that probabilistically learns temporal patterns from ground motion data. Uncertainties are accounted for throughout the framework. Performance of the approach has been quantitatively demonstrated via various missing data scenarios. This framework provides a general solution to dealing with missing data in ground motion records by providing various forms of representation of ground motions in a probabilistic manner, allowing it to be adopted for numerous engineering and seismological applications. Notably, it is compatible with the versatile Monte Carlo simulation scheme, such that stochastic dynamic analyses are still achievable even with missing data. Furthermore, it serves as a complementary approach to current stochastic ground-motion models in data-scarce regions under the growing interests of PBEE (performance-based earthquake engineering), mitigating the data-model dependence dilemma due to the paucity of data, and ultimately, as a fundamental solution to the limited data problem in data scarce regions.
KW - Bayesian model updating
KW - earthquake ground motion
KW - evolutionary power spectra
KW - missing data
KW - stochastic variational inference
KW - uncertainty quantification
UR - http://www.scopus.com/inward/record.url?scp=85150936833&partnerID=8YFLogxK
U2 - 10.1002/eqe.3877
DO - 10.1002/eqe.3877
M3 - Article
AN - SCOPUS:85150936833
VL - 52
SP - 2179
EP - 2195
JO - Earthquake Engineering and Structural Dynamics
JF - Earthquake Engineering and Structural Dynamics
SN - 0098-8847
IS - 7
ER -