A Caltech Library Service

Data-driven Accelerogram Synthesis using Deep Generative Models

Florez, Manuel A. and Caporale, Michaelangelo and Buabthong, Pakpoom and Ross, Zachary E. and Asimaki, Domniki and Meier, Men-Andrin (2020) Data-driven Accelerogram Synthesis using Deep Generative Models. . (Unpublished)

PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Robust estimation of ground motions generated by scenario earthquakes is critical for many engineering applications. We leverage recent advances in Generative Adversarial Networks (GANs) to develop a new framework for synthesizing earthquake acceleration time histories. Our approach extends the Wasserstein GAN formulation to allow for the generation of ground-motions conditioned on a set of continuous physical variables. Our model is trained to approximate the intrinsic probability distribution of a massive set of strong-motion recordings from Japan. We show that the trained generator model can synthesize realistic 3-Component accelerograms conditioned on magnitude, distance, and V_(s30). Our model captures the expected statistical features of the acceleration spectra and waveform envelopes. The output seismograms display clear P and S-wave arrivals with the appropriate energy content and relative onset timing. The synthesized Peak Ground Acceleration (PGA) estimates are also consistent with observations. We develop a set of metrics that allow us to assess the training process's stability and tune model hyperparameters. We further show that the trained generator network can interpolate to conditions where no earthquake ground motion recordings exist. Our approach allows the on-demand synthesis of accelerograms for engineering purposes.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Buabthong, Pakpoom0000-0001-5538-138X
Ross, Zachary E.0000-0002-6343-8400
Asimaki, Domniki0000-0002-3008-8088
Meier, Men-Andrin0000-0002-2949-8602
Group:Seismological Laboratory
Record Number:CaltechAUTHORS:20210111-160825629
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:107401
Deposited By: George Porter
Deposited On:12 Jan 2021 16:30
Last Modified:12 Jan 2021 16:30

Repository Staff Only: item control page