Waveform-Based Probabilistic Seismic Hazard Analysis Using Ground-Motion Generative Models

TL;DR

This work develops waveform-based probabilistic seismic hazard analysis by modeling the full distribution of ground-motion waveforms with ground-motion generative models (GMGMs) and performing Monte Carlo sampling to represent hazard as an ensemble of waveforms $p(oldsymbol{g} vert oldsymbol{s})$. Three GMGMs (StyleGAN-based, conditional Wasserstein GAN, and conditional StyleGAN) are trained on a Japan-focused strong-motion dataset to capture waveform variability conditioned on magnitude, distance, and site.proxy variables, enabling direct computation of hazard curves from waveforms and subsequent nonlinear structural analyses. Hazard results from the waveform-based PSHA are shown to be consistent with conventional IM-based PSHA, while providing additional capabilities such as hazard disaggregation by source characteristics and direct assessment of engineering demand parameters (EDPs) through building response simulations. The framework highlights practical gains for PBEE and performance-based design, while acknowledging epistemic uncertainties stemming from model architectures and training data, and identifying future directions to improve robustness and efficiency with larger datasets and advanced sampling techniques.

Abstract

In probabilistic seismic hazard analysis (PSHA), the exceedance probability of a ground-motion intensity measure (IM) is typically evaluated. However, in recent years, dynamic response analyses using ground-motion time histories as input have been increasingly common in seismic design and risk assessment, and thus there is a growing demand for representing seismic hazard in terms of ground-motion waveforms. In this study, we propose a novel PSHA framework, referred to as waveform-based PSHA, that enables the direct evaluation of the probability distribution of ground-motion waveforms by introducing ground-motion models (GMMs) based on deep generative models (ground-motion generative models; GMGMs) into the PSHA framework. In waveform-based PSHA, seismic hazard is represented, in a Monte Carlo sense, as a set of ground-motion waveforms. We propose the formulation of such a PSHA framework as well as an algorithm for performing the required Monte Carlo simulations. Three different GMGMs based on generative adversarial networks (GANs) are constructed. After verifying the performance of each GMGM, hazard evaluations using the proposed method are conducted for two numerical examples: one assuming a hypothetical area source and the other assuming an actual site and source faults in Japan. We demonstrate that seismic hazard can be represented as a set of ground-motion waveforms, and that the IM-based hazard obtained from these waveforms is consistent with the results of conventional PSHA using GMMs. Finally, nonlinear dynamic response analyses of a building model are performed using the evaluated seismic hazard as input, and it is shown that exceedance probabilities of engineering demand parameters (EDPs) as well as hazard disaggregation with respect to EDPs can be carried out in a straightforward manner within the proposed framework.

Figures (51)

• Figure 1: Locations of the earthquake epicenters (circles) and stations (triangles).
• Figure 2: Magnitude-distance distribution of the training dataset.
• Figure 3: Diagrams of the DNN architectures of the GMGMs: (a) S-GMGM, (b) CS-GMGM, and (c) CW-GMGM. The discriminator of the CS-GMGM has the same architecture as that of the S-GMGM.
• Figure 4: Examples of ground-motion acceleration waveforms generated by the S-GMGM. The waveform in each column correspond to the value of $M_W$ shown at the top. Each panel shows the associated $R_{\mathrm{RUP}}$ and $V_{\mathrm{S}30}$ values.
• Figure 5: Comparison of the distributions of ground-motion characteristic indices in Table \ref{['tab01']} between the observed records and ground motions generated by the S-GMGM.