Probabilistic blind identification of site effects from ground surface signals

Ghahari, S. Farid; Abazarsa, F.; Taciroğlu, Ertuǧrul

doi:10.1007/s10518-017-0253-0

Cited by 9 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The significant disparity in range of values between the input and output data poses challenges for the neural network to effectively discern meaningful relationships among features. In order to address this concern and enable the efficient acquisition of feature relationships between the input and output layers within our CNN, we employ a normalization technique by utilizing the following Equation (7). Figure 4B uses the normalized scales of sample input-layer feature data, which range in values between −0.5 and 0.5, as shown on the vertical axes.…”

Section: Data Preparationmentioning

confidence: 99%

Convolutional neural network for identifying effective seismic force at a DRM layer for rapid reconstruction of SH ground motions

Maharjan,

Guidio,

Jeong

2023

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

We introduce a novel data‐informed convolutional neural network (CNN) approach that utilizes sparse ground motion measurements to accurately identify effective seismic forces in a truncated two‐dimensional (2D) domain. Namely, this paper presents the first prototype of a CNN capable of inferring domain reduction method (DRM) forces, equivalent to incident waves, across all nodes in the DRM layer. It achieves this from sparse measurement data in a multidimensional setting, even in the presence of incoherent incident waves. The method is applied to shear (SH) waves propagating into a domain truncated by a wave‐absorbing boundary condition (WABC). By effectively training the CNN using input‐layer features (surface sensor measurements) and output‐layer features (effective forces at a DRM layer), we achieve significant reductions in processing time compared to PDE‐constrained optimization methods. The numerical experiments demonstrate the method's effectiveness and robustness in identifying effective forces, equivalent to incoherent incident waves, at a DRM layer.

show abstract

Section: Data Preparationmentioning

confidence: 99%

Convolutional neural network for identifying effective seismic force at a DRM layer for rapid reconstruction of SH ground motions

Maharjan,

Guidio,

Jeong

2023

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

show abstract

“…, which is much smaller than the number of samples needed to integrate via Monte Carlo methods. 89 Having the capability to calculate h f; e θ using Equation (38), the moments needed for the likelihood calculation can be estimated as follows.…”

Section: Moment Estimationmentioning

confidence: 99%

“…To quantify the estimation uncertainty, Bayesian inference techniques for parameter estimation have been extensively used in various fields, including earthquake engineering 37–47 . However, in all these classical Bayesian estimation studies, the model is assumed to be correct, and only the parameter uncertainty caused by measurement errors is quantified.…”

Section: Introductionmentioning

confidence: 99%

“…To quantify the estimation uncertainty, Bayesian inference techniques for parameter estimation have been extensively used in various fields, including earthquake engineering. [37][38][39][40][41][42][43][44][45][46][47] However, in all these classical Bayesian estimation studies, the model is assumed to be correct, and only the parameter uncertainty caused by measurement errors is quantified. Therefore, such solutions can introduce bias in the parameter estimation as well as predictions when there is significant modeling uncertainty.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Quantifying modeling uncertainty in simplified beam models for building response prediction

Ghahari

Sargsyan

Çelebi

et al. 2022

Structural Contr & Hlth

Self Cite

View full text Add to dashboard Cite

The use of simple models for response prediction of building structures is preferred in earthquake engineering for risk evaluations at regional scales, as they make computational studies more feasible. The primary impediment in their gainful use presently is the lack of viable methods for quantifying (and reducing upon) the modeling errors/uncertainties they bear. This study presents a Bayesian calibration method wherein the modeling error is embedded into the parameters of the model. The method is specifically described for coupled shear-flexural beam models here, but it can be applied to any parametric surrogate model. The major benefit the method offers is the ability to consider the modeling uncertainty in the forward prediction of any degree-of-freedom or composite response regardless of the data used in calibration. The method is extensively verified using two synthetic examples. In the first example, the beam model is calibrated to represent a similar beam model but with enforced modeling errors. In the second example, the beam model is used to represent the detailed finite element model of a 52-story building. Both examples show the capability of the proposed solution to provide realistic uncertainty estimation around the mean prediction.

show abstract

“…The California Strong Motion Instrumentation Program (CSMIP) of the California Geological Survey (CGS), established in 1972 after the devastating 1971 San Fernando earthquake, is an example of such a program and may be the largest of its kind globally (Huang and Shakal, 2011). It aims to provide critical earthquake data to the engineering and scientific communities through a statewide network of strong motion instruments, supporting numerous research studies (Çelebi et al, 2016a, 2016b, 2017; Ghahari et al, 2017). While post-earthquake damage assessment was one of its original objectives, SHM was in its infancy during CSMIP’s initiation.…”

Section: Introductionmentioning

confidence: 99%

A hybrid model-data method for seismic response reconstruction of instrumented buildings

Ghahari,

Swensen,

Haddadi

et al. 2024

Earthquake Spectra

Self Cite

View full text Add to dashboard Cite

This study presents a two-step hybrid (model-data fusion) method for reconstructing the seismic response of instrumented buildings at their non-instrumented floors. Over the past couple of decades, seismic data recorded within instrumented buildings have yielded invaluable insights into the behavior of civil structures, which were arguably impossible to obtain through numerical simulations, laboratory-scale experiments, or even in-situ testing. Recently, advances in sensing technology have opened new pathways for structural health monitoring (SHM) and rapid post-earthquake assessment. However, data-driven techniques tend to lack accuracy when structures have sparse instrumentation. In addition, creating detailed numerical models for the monitored structures is labor-intensive and time-consuming, often unsuitable for rapid post-event assessments. The common approach to address these challenges has been to use simple interpolation techniques over the sparse measurements. However, uncertainties associated with such estimates are usually overlooked, and these methods have certain physical limitations. In this study, we propose a two-step approach for reconstructing seismic responses. In the initial step, a coupled shear–flexural beam model is calibrated using data collected from instrumented floors. Next, the residual, representing the difference between measurements and the beam model’s predictions, is used to train a Gaussian process regression model. The combination of these two models provides both the mean and variance of the response at the non-instrumented floors. This new approach is verified by using simulated acceleration responses of a tall building. Validation is attained by using real seismic data recorded in two tall buildings and comparing the method’s predictions with actual measurements on floors not used for training. Finally, data recorded in a 52-story building during multiple earthquakes are used for demonstrating the practical application of the proposed approach in real-world scenarios.

show abstract

Probabilistic blind identification of site effects from ground surface signals

Cited by 9 publications

References 25 publications

Convolutional neural network for identifying effective seismic force at a DRM layer for rapid reconstruction of SH ground motions

Convolutional neural network for identifying effective seismic force at a DRM layer for rapid reconstruction of SH ground motions

Quantifying modeling uncertainty in simplified beam models for building response prediction

A hybrid model-data method for seismic response reconstruction of instrumented buildings

Contact Info

Product

Resources

About