This Earthquake Doesn't Exist
Abstract
This study applies Conditional Generative Adversarial Networks (cGAN) to the field of seismology. With GAN, realistic seismic waveforms can be created for various applications, such as augmenting limited seismic data or modeling, or generating realistic noise. A potential and alarming application of GAN is to generate realistic seismic signals that can cause disturbances to the international treaty banning nuclear explosions (CTBT). Results show that the generated seismic waves are nearly indistinguishable from real ones.
Cite
Text
Novoselov et al. "This Earthquake Doesn't Exist." NeurIPS 2021 Workshops: AI4Science, 2021.Markdown
[Novoselov et al. "This Earthquake Doesn't Exist." NeurIPS 2021 Workshops: AI4Science, 2021.](https://mlanthology.org/neuripsw/2021/novoselov2021neuripsw-earthquake/)BibTeX
@inproceedings{novoselov2021neuripsw-earthquake,
title = {{This Earthquake Doesn't Exist}},
author = {Novoselov, Artemii and Sinkovics, Krisztina and Bokelmann, Goetz},
booktitle = {NeurIPS 2021 Workshops: AI4Science},
year = {2021},
url = {https://mlanthology.org/neuripsw/2021/novoselov2021neuripsw-earthquake/}
}