Modeling spatial cross-correlation of multiple ground motion intensity measures (SAs, PGA, PGV, Ia, CAV, and significant durations) based on principal component and geostatistical analyses

The incorporation of machine learning (ML) algorithms in earthquake engineering can improve existing methodologies and enable new frameworks to solve complex problems. In the present study, the use of artificial neural networks (ANNs) for the derivation of seismic vulnerability models for building portfolios is explored. Large sets of ground motion records (GMRs) and structural models representing the building stock in the Balkan region were used to train ANNs for the prediction of structural response, damage and economic loss conditioned on a vector of ground shaking intensity measures. The structural responses and loss ratios (LRs) generated using the neural networks were compared with results based on traditional regression models using scalar intensity measures in terms of efficiency, sufficiency, bias and variability. The results indicate a superior performance of the ANN models over traditional approaches, potentially allowing a greater reliability and accuracy in scenario and probabilistic seismic risk assessment.

Section: Development Of An Ann Model For Vulnerability Assessmentmentioning

confidence: 99%

Section: Nonlinear Dynamic Analyses and Training Of The Ann Modelsmentioning

confidence: 99%

Seismic vulnerability modelling of building portfolios using artificial neural networks

Kalakonas

Silva

2021

“…24,26,27 Most previous studies have used recordings of well-recorded events assuming stationarity when developing spatial correlation models. [7][8][9][10][11]13,15,16,19,21,23,24,29 This means that the semivariogram, and thus the correlation between residuals at two different sites, do not depend on the site locations, but only on their separation distance. With this assumption, different station pairs with a given separation distance can be used to estimate the semivariogram, which is useful when there is a lack of station pairs with several simultaneous recordings.…”

Section: Introductionmentioning

confidence: 99%

“…The spatial correlation of residuals of ground‐motion intensities has been extensively studied for the last 20 years 3–31 . In general, these studies combine several earthquakes for developing their models, although different authors have found a significantly large event‐to‐event variability, 12,23 even when exploring different events of the same seismic sequence 26 .…”

Section: Introductionmentioning

confidence: 99%

“…Most previous studies have used recordings of well‐recorded events assuming stationarity when developing spatial correlation models 7–11,13,15,16,19,21,23,24,29 . This means that the semivariogram, and thus the correlation between residuals at two different sites, do not depend on the site locations, but only on their separation distance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Within‐event spatial correlation of peak ground acceleration and spectral pseudo‐acceleration ordinates in the Chilean subduction zone

Aldea

Heresi

Pastén

2022

A regional seismic risk assessment requires the estimation of ground‐motion intensities at multiple locations for a given event simultaneously. In this context, the spatial correlation of ground‐motion residuals plays an important role in characterizing the probability distribution of the field of shaking intensities. Over the last 20 years, the spatial correlation of ground‐motions has been widely studied and different models have been developed. In general, these models vary from each other depending on the ground‐motion database used to generate them, on the adopted intensity measure, on the selected ground‐motion model, and on the estimation methods, among others. This paper proposes a spatial correlation model for within‐event residuals of peak ground acceleration and spectral pseudo‐acceleration ordinates in the Chilean subduction zone. Although the database considered for this study has only a few well‐recorded earthquakes, it contains a large number of station pairs sharing several common events. Therefore, we compute non‐stationary correlations between station pairs and then fit a stationary spatial correlation model. Results of this paper are compared with previous models, concluding that, in general, subduction models show higher spatial correlations than those for active shallow crust events for long‐period spectral ordinates. Moreover, no evidence was found for a systematic effect of earthquake magnitude or site conditions on spatial correlation. Finally, the proposed model is compared with a model obtained assuming stationarity in spatial correlations, showing more reliable estimates when using the proposed model.

Accounting for earthquake‐induced ground‐motion duration in building‐portfolio loss assessment

Otárola

Gentile

Sousa³

et al. 2022

Earthquake-induced ground-motion duration can have a non-negligible impact on the nonlinear seismic performance of structures. However, in current seismic risk assessment practice, hazard and vulnerability analyses generally only consider ground motion's amplitude and frequency-content features, often relegating duration to implicit considerations. This study introduces a simulation-based framework to explicitly quantify the impact of ground-motion duration on building-portfolio direct economic losses. Case-study synthetic building portfolios located at different distances from a case-study seismic source (i.e., fault) are assembled considering -individually and in combinationthree building typologies representing distinct vulnerability classes in Southern Italy. Such typologies correspond to non-ductile moment-resisting reinforced concrete (RC) infilled frames designed to only sustain gravity loads (i.e., precode infilled frames), and ductile moment-resisting RC infilled and bare frames designed considering seismic provisions for high-ductility capacity (i.e., specialcode infilled and bare frames). Event-based probabilistic seismic hazard analysis is performed explicitly simulating duration jointly with spectral-shape-related intensity measures (IMs), accounting for their spatial and cross-correlation.Sets of ground-motion records are selected to conduct cloud-based nonlinear time-history analyses (NLTHAs) and derive fragility models for each considered building typology through archetype structures, simulating their structural response using computational models that account for stiffness and strength cyclic and in-cycle deterioration as well as destabilising 𝑃 − Δ effects. Fragility models are derived using average pseudo-spectral acceleration (in a range of periods of interest) as the primary IM and alternatively: (1) the dissipated hysteretic energy as an engineering demand parameter (EDP), implicitly accounting for duration given the cumulative nature of such an EDP and the adopted nonlinear modelling strategy, in a scalar format; (2) the dissipated hysteretic energy as an EDP, as before, explicitly considering duration as an IM together with spectral shape, in a vector-valued format. Vulnerability models are then derived usingThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.