Seismic Wave Simulation

In seismology, generating synthetic seismic waveform has different applications such as in full-waveform inversion and earthquake simulation among many other application. Currently, discretizing and iteratively solving the wave equation using numerical methods like Finite Difference or Spectral Element is the most common approach for seismic wave simulation in seismology.

Used ML Approaches:

• Artificial Neural Networks

Used Neural Networks:

• FC

• CNN

• RNN

• ResNet

• GAN

• Autoencoder

• WaveNet

• LSTM

• PINN

• VGG

Used Learning Procedures:

• Supervised Learning

• Transfer Learning

• Unsupervised Learning

References:

1. Lee, S. C., & Han, S. W. (2002). Neural-network-based models for generating artificial earthquakes and response spectra. Computers & structures, 80(20-21), 1627-1638.

2. Paolucci, R., Gatti, F., Infantino, M., Smerzini, C., Güney Özcebe, A., & Stupazzini, M. (2018). Broadband ground motions from 3D physics‐based numerical simulations using artificial neural networks. Bulletin of the Seismological Society of America, 108(3A), 1272-1286.

3. Siahkoohi, A., Louboutin, M., & Herrmann, F. J. (2019). Neural network augmented wave-equation simulation. arXiv preprint arXiv:1910.00925.

4. Moseley, B., Nissen-Meyer, T., & Markham, A. (2020). Deep learning for fast simulation of seismic waves in complex media. Solid Earth, 11(4), 1527-1549.

5. Roncoroni, G., Fortini, C., Bortolussi, L., Bienati, N., & Pipan, M. (2021). Synthetic seismic data generation with deep learning. Journal of Applied Geophysics, 190, 104347.

6. Moseley, B., Markham, A., & Nissen-Meyer, T. (2020). Solving the wave equation with physics-informed deep learning. arXiv preprint arXiv:2006.11894.

7. Song, C., Alkhalifah, T., & Waheed, U. B. (2021). Solving the frequency-domain acoustic VTI wave equation using physics-informed neural networks. Geophysical Journal International, 225(2), 846-859.

8. Shiloh, L., Eyal, A., & Giryes, R. (2019). Efficient processing of distributed acoustic sensing data using a deep learning approach. Journal of Lightwave Technology, 37(18), 4755-4762.

9. Gatti, F., & Clouteau, D. (2020). Towards blending Physics-Based numerical simulations and seismic databases using Generative Adversarial Network. Computer Methods in Applied Mechanics and Engineering, 372, 113421.

10. Florez, M. A., Caporale, M., Buabthong, P., Ross, Z. E., Asimaki, D., & Meier, M. A. (2020). Data-driven Accelerogram Synthesis using Deep Generative Models. arXiv preprint arXiv:2011.09038.

11. Wang, T., Trugman, D., & Lin, Y. (2021). SeismoGen: Seismic Waveform Synthesis Using GAN With Application to Seismic Data Augmentation. Journal of Geophysical Research: Solid Earth, 126(4), e2020JB020077.

12. Spurio Mancini, A., Piras, D., Ferreira, A. M. G., Hobson, M. P., & Joachimi, B. (2021). Accelerating Bayesian microseismic event location with deep learning. Solid Earth Discussions, 1-36.