Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition

Jaeheun Jung, Jaehyuk Lee, Chang-Hae Jung, Hanyoung Kim, Bosung Jung, Donghun Lee
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28503-28526, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-jung25b, title = {Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition}, author = {Jung, Jaeheun and Lee, Jaehyuk and Jung, Chang-Hae and Kim, Hanyoung and Jung, Bosung and Lee, Donghun}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {28503--28526}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/jung25b/jung25b.pdf}, url = {https://proceedings.mlr.press/v267/jung25b.html}, 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.} }
Endnote
%0 Conference Paper %T Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition %A Jaeheun Jung %A Jaehyuk Lee %A Chang-Hae Jung %A Hanyoung Kim %A Bosung Jung %A Donghun Lee %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-jung25b %I PMLR %P 28503--28526 %U https://proceedings.mlr.press/v267/jung25b.html %V 267 %X 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.
APA
Jung, J., Lee, J., Jung, C., Kim, H., Jung, B. & Lee, D.. (2025). Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:28503-28526 Available from https://proceedings.mlr.press/v267/jung25b.html.

Related Material