Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jung, Jaeheun, Lee, Jaehyuk, Jung, Changhae, Kim, Hanyoung, Jung, Bosung, Lee, Donghun
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910973512646656
author Jung, Jaeheun
Lee, Jaehyuk
Jung, Changhae
Kim, Hanyoung
Jung, Bosung
Lee, Donghun
author_facet Jung, Jaeheun
Lee, Jaehyuk
Jung, Changhae
Kim, Hanyoung
Jung, Bosung
Lee, Donghun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17333
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
Jung, Jaeheun
Lee, Jaehyuk
Jung, Changhae
Kim, Hanyoung
Jung, Bosung
Lee, Donghun
Machine Learning
Artificial Intelligence
Geophysics
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.
title Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
topic Machine Learning
Artificial Intelligence
Geophysics
url https://arxiv.org/abs/2412.17333