Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition

Jaeheun Jung, Jaehyuk Lee, Chang-Hae Jung, Hanyoung Kim, Bosung Jung, Donghun Lee

Abstract: Shock waves caused by earthquakes can be devastating. Generating realistic earthquake-caused ground motion waveforms help reducing losses in lives and properties, yet generative models for the task tend to generate subpar waveforms. We present High-fidelity Earthquake Groundmotion Generation System (HEGGS) and demonstrate its superior performance using earthquakes from North American, East Asian, and European regions. HEGGS exploits the intrinsic characteristics of earthquake dataset and learns the waveforms using an end-to-end differentiable generator containing conditional latent diffusion model and hi-fidelity waveform construction model. We show the learning efficiency of HEGGS by training it on a single GPU machine and validate its performance using earthquake databases from North America, East Asia, and Europe, using diverse criteria from waveform generation tasks and seismology. Once trained, HEGGS can generate three dimensional E-N-Z seismic waveforms with accurate P/S phase arrivals, envelope correlation, signal-to-noise ratio, GMPE analysis, frequency content analysis, and section plot analysis.

Lay Summary:

Can a purely data-driven method (i.e. not knowing earth science) synthesize earthquake shockwaves with seismologically plausible properties? Off-the-shelf tools failed, so we created our own that works great on earthquake recordings from North America, Far East, and Europe.

We call it High-fidelity Earthquake Groundmotion Generation System (HEGGS). HEGGS exploits the fact that earthquake recordings are in fact a collection of earth-moving-sound caused by an earthquake, heard from many places. Notably, HEGGS does not require complicated earth-related measurements but only four minimal information -- earthquake location, depth, magnitude, and recording station location -- to create realistic earthquake shockwaves.

Earthquake shockwaves created by HEGGS look plausible both from time series analysis and seismological perspectives. This work may help not only earthquake researchers but also the general public as a primary tool to emulate the consequences of hypothetical earthquakes.

Application-Driven Machine Learning: This submission is on Application-Driven Machine Learning.

Primary Area: Applications->Chemistry, Physics, and Earth Sciences

Keywords: seismology, earthquake synthesis, diffusion model

Submission Number: 6515