Scenario-conditioned flow matching for probabilistic generation of three-component ground-motion waveforms
Abstract
Performance-based seismic risk assessment requires three-component acceleration histories compatible with specified source, path, and site conditions. Conventional ground-motion prediction equations provide scalar intensity measures, while many generative waveform models learn amplitude and waveform shape within a single high-dimensional target. We present WaveFlowGMM, a two-stage probabilistic ground-motion model that uses peak ground acceleration (PGA) as an amplitude interface between scenario conditioning and waveform generation. The amplitude stage uses physics-informed symbolic learning to estimate component-wise PGA medians and a full cross-component covariance. The waveform stage uses few-step AlphaFlow in an invertible wavelet-packet coefficient space to generate normalised three-component histories that are rescaled by sampled PGA. Tests on an event-level NGA-West2 holdout set show that the generated motions recover the main magnitude, distance, and site scaling, keep peak and spectral residuals close to zero, preserve three-component amplitude dependence, and yield velocity and displacement histories without systematic drift after integration of the generated three-component acceleration histories. The framework provides an interpretable and computationally efficient candidate component for waveform-level seismic hazard and risk analysis.
Related
- Fault-conditioned Seismic Image Generation using Denoising Diffusion Probabilistic Modeling and Neural Style Transfer
- Multi-scenario probabilistic hazard assessment of flash flood disasters in Chengkou County based on a multi-state system model
- Preserving Probabilistic Meaning in Weather-to-Text Generation
- Broadband Ground-Motion Synthesis by Conditioning Denoising Diffusion Models on Low-Frequency Waveforms
- Automatic Extraction of a Generalized Physics‐Based Feature From Time‐Lapse Active Source Ultrasonic Waveforms for Prediction of Shear Stress in Laboratory Friction Experiments
BibTeX
@misc{ding2026scenarioconditioned,
title = {{Scenario-conditioned flow matching for probabilistic generation of three-component ground-motion waveforms}},
author = {Yi Ding and Jinjun Hu and Su Chen and Xianwei Liu and Zhongxiang Zhang and Zongchao Li and Xiaojun Li and Lili Xie},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.31340},
eprint = {2606.31340},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.31340},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Scenario-conditioned flow matching for probabilistic generation of three-component ground-motion waveforms
AU - Yi Ding
AU - Jinjun Hu
AU - Su Chen
AU - Xianwei Liu
AU - Zhongxiang Zhang
AU - Zongchao Li
AU - Xiaojun Li
AU - Lili Xie
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2606.31340
UR - https://arxiv.org/abs/2606.31340
AB - Performance-based seismic risk assessment requires three-component acceleration histories compatible with specified source, path, and site conditions. Conventional ground-motion prediction equations provide scalar intensity measures, while many generative waveform models learn amplitude and waveform shape within a single high-dimensional target. We present WaveFlowGMM, a two-stage probabilistic ground-motion model that uses peak ground acceleration (PGA) as an amplitude interface between scenario conditioning and waveform generation. The amplitude stage uses physics-informed symbolic learning to estimate component-wise PGA medians and a full cross-component covariance. The waveform stage uses few-step AlphaFlow in an invertible wavelet-packet coefficient space to generate normalised three-component histories that are rescaled by sampled PGA. Tests on an event-level NGA-West2 holdout set show that the generated motions recover the main magnitude, distance, and site scaling, keep peak and spectral residuals close to zero, preserve three-component amplitude dependence, and yield velocity and displacement histories without systematic drift after integration of the generated three-component acceleration histories. The framework provides an interpretable and computationally efficient candidate component for waveform-level seismic hazard and risk analysis.
ER -