TimesNet-Gen: Deep Learning-based Site Specific Strong Motion Generation

Baris Yilmaz, Bevan Deniz Cilgin, Erdem Akagündüz, Salih Tileylioglu
12/4/2025
cs.LGcs.AI

Official code: brsylmz23/TimesNet-Gen (2 stars, MIT, last commit 2025-12-08).

Abstract

Effective earthquake risk reduction relies on accurate site-specific evaluations. This requires models that can represent the influence of local site conditions on ground motion characteristics. In this context, data driven approaches that learn site controlled signatures from recorded ground motions offer a promising direction. We address strong ground motion generation from time-domain accelerometer records and introduce the TimesNet-Gen, a time-domain conditional generator. The approach uses a station specific latent bottleneck. We evaluate generation by comparing HVSR curves and fundamental site-frequency $f_0$ distributions between real and generated records per station, and summarize station specificity with a score based on the $f_0$ distribution confusion matrices. TimesNet-Gen achieves strong station-wise alignment and compares favorably with a spectrogram-based conditional VAE baseline for site-specific strong motion synthesis. Our codes are available via https://github.com/brsylmz23/TimesNet-Gen.

View on arXivView PDF

Code Implementations(1)

brsylmz23/TimesNet-GenOfficial100%
MIT

Generative seismic waveform synthesis using TimesNet-Gen architecture

20PythonNov 30, 202510 months agoMIT

Similar Papers

Learning Physics for Unveiling Hidden Earthquake Ground Motions via Conditional Generative Modeling

83% match1 repo122024

Exploring Challenges in Deep Learning of Single-Station Ground Motion Records

83% match2024

Deep Learning-based Average Shear Wave Velocity Prediction using Accelerometer Records

82% match2024

Broadband Ground Motion Synthesis via Generative Adversarial Neural Operators: Development and Validation

82% match2023

SourceNet: Interpretable Sim-to-Real Inference on Variable-Geometry Sensor Arrays for Earthquake Source Inversion

81% match2026

Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition

80% match2024

Cite this paper

@article{yilmaz2025timesnetgen,
  title  = {TimesNet-Gen: Deep Learning-based Site Specific Strong Motion Generation},
  author = {Baris Yilmaz and Bevan Deniz Cilgin and Erdem Akagündüz and Salih Tileylioglu},
  year   = {2025},
  eprint = {2512.04694},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.04694v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.04694.svg)](https://codeofpaper.com/paper/2512.04694)

Discussion