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

arXiv: https://arxiv.org/abs/2512.04694 · HTML: https://mlsanity.com/paper/2512.04694/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 43 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024)
- [Bayesian-Deep-Learning Estimation of Earthquake Location from Single-Station Observations](https://mlsanity.com/paper/1912.01144/) (2019)
- [Broadband Ground Motion Synthesis via Generative Adversarial Neural Operators: Development and Validation](https://mlsanity.com/paper/2309.03447/) (2023)
- [Learning Physics for Unveiling Hidden Earthquake Ground Motions via Conditional Generative Modeling](https://mlsanity.com/paper/2407.15089/) (2024)
- [Deep Learning-based Epicenter Localization using Single-Station Strong Motion Records](https://mlsanity.com/paper/2405.18451/) (2024)
- [Exploring Challenges in Deep Learning of Single-Station Ground Motion Records](https://mlsanity.com/paper/2403.07569/) (2024)
- [Deep Learning-based Average Shear Wave Velocity Prediction using Accelerometer Records](https://mlsanity.com/paper/2408.14962/) (2024)
- [High Resolution Seismic Waveform Generation using Denoising Diffusion](https://mlsanity.com/paper/2410.19343/) (2024)
- [Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition](https://mlsanity.com/paper/2412.17333/) (2024)
- [Data-driven Accelerogram Synthesis using Deep Generative Models](https://mlsanity.com/paper/2011.09038/) (2020)

## Abstract (arXiv)

Effective earthquake risk reduction relies on accurate site-specific evaluations, which require models capable of representing the influence of local site conditions on ground motion characteristics. We address strong ground motion generation from time-domain accelerometer records and introduce the TimesNet-Gen, a deep generative framework. In this framework, site-specific generation is directly achieved through a station-restricted, Dirichlet-based latent space resampling strategy, without relying on explicit conditioning inputs or dimensionality reduction. Pre-trained on the AFAD dataset via self-supervised learning, the frozen model demonstrates robust cross-regional generalization by successfully generating station-specific NGA-West2 records without any fine-tuning. Model performance is evaluated by comparing the distributions of generated and real records in the log-HVSR space, alongside the joint analysis of peak ground acceleration and fundamental site frequency. As a baseline, we construct a spectrogram-based conditional variational autoencoder (CVAE) explicitly formulated for station-specific latent space modeling. The results show strong station-wise alignment, consistent cross-regional ground motion synthesis, and a favorable comparison with a spectrogram-based conditional variational autoencoder baseline, demonstrating that the model empirically maintains the essential physical coupling between frequency content and peak amplitude. Our codes are available via https://github.com/brsylmz23/TimesNet-Gen.