Training a continuous conditional diffusion-based model to simulate horizontal strike-slip ground motions for scenario seismic events
- 1Department of Civil and Environmental Engineering, Western University
- 2School of Intelligent Civil and Ocean Engineering, Harbin Institute of Technology (Shenzhen)
Abstract
Parametric models of the time–frequency-dependent power spectral density (TFPSD) function of seismic ground motion records can be developed from historical records, though model selection involves some subjectivity. The TFPSD function varies complexly in time–frequency domain, with the duration and spectral content depending on the moment magnitude M, rupture distance R rup, and shear-wave velocity of the top 30 m of soil V S30 at the site. These conditional TFPSD images serve as training data for generative neural networks which then generate new TFPSD images conditioned on scenario parameters. A new model is trained using the continuous conditional diffusion model (CCDM), and a framework is proposed to simulate the horizontal components of strike-slip ground motions conditioned on (M, R rup, V S30). It integrates three parts: (1) variables predicting equations for defining the marginal probability distribution function (PDF), duration, and total energy; (2) the trained CCDM-based model; (3) an algorithm to simulate nonstationary non-Gaussian time histories matching the targets. The proposed framework is validated by comparing pseudospectral acceleration from established ground motion models, actual recorded ground motions, and simulated records, as well as by comparing the Arias intensity, significant durations, peak ground velocity, cumulative absolute velocity and ductility demand calculated using actual and simulated records. The simulated ground motions reproduce several important real seismic features: TFPSD, duration, and nonstationary non-Gaussian behaviour.
Related
- High-intensity interval training and moderate-intensity continuous training versus usual care in adults with familial hypercholesterolaemia: protocol for the UPPA-FH three-arm randomised trial
- Mitochondrial Biogenesis in Human Skeletal Muscle: High-Intensity Interval Training Versus Moderate-Intensity Continuous Training
- Resistance training enhances the post-exercise fat oxidation of Tabata-style exercise more than moderate-intensity continuous training in young males with obesity: an acute randomized crossover study
- What are the experiences, perceptions and training needs of inpatient general nursing staff on Continuous Glucose Monitoring?
- Investigating the potential association between the continuous-time random-walk MR diffusion model and lymph node metastasis and vascular invasion in patients with rectal cancer: A preliminary exploratory study
BibTeX
@article{jiang2026training,
title = {{Training a continuous conditional diffusion-based model to simulate horizontal strike-slip ground motions for scenario seismic events}},
author = {X. H. Jiang and X. Z. Cui and H. P. Hong},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-62119-9},
url = {https://doi.org/10.1038/s41598-026-62119-9},
note = {CC BY},
}
RIS
TY - JOUR
TI - Training a continuous conditional diffusion-based model to simulate horizontal strike-slip ground motions for scenario seismic events
AU - X. H. Jiang
AU - X. Z. Cui
AU - H. P. Hong
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-62119-9
UR - https://doi.org/10.1038/s41598-026-62119-9
AB - Parametric models of the time–frequency-dependent power spectral density (TFPSD) function of seismic ground motion records can be developed from historical records, though model selection involves some subjectivity. The TFPSD function varies complexly in time–frequency domain, with the duration and spectral content depending on the moment magnitude M, rupture distance R rup, and shear-wave velocity of the top 30 m of soil V S30 at the site. These conditional TFPSD images serve as training data for generative neural networks which then generate new TFPSD images conditioned on scenario parameters. A new model is trained using the continuous conditional diffusion model (CCDM), and a framework is proposed to simulate the horizontal components of strike-slip ground motions conditioned on (M, R rup, V S30). It integrates three parts: (1) variables predicting equations for defining the marginal probability distribution function (PDF), duration, and total energy; (2) the trained CCDM-based model; (3) an algorithm to simulate nonstationary non-Gaussian time histories matching the targets. The proposed framework is validated by comparing pseudospectral acceleration from established ground motion models, actual recorded ground motions, and simulated records, as well as by comparing the Arias intensity, significant durations, peak ground velocity, cumulative absolute velocity and ductility demand calculated using actual and simulated records. The simulated ground motions reproduce several important real seismic features: TFPSD, duration, and nonstationary non-Gaussian behaviour.
SN - 2045-2322
ER -