Skip to content

Unsupervised (Self-Supervised) Clustering of Seismic Signals Using Deep Convolutional Autoencoders

Notifications You must be signed in to change notification settings

smousavi05/Unsupervised_Deep_Learning

Repository files navigation

Demo codes (see the jupyter notebook) for:

GitHub last commit
GitHub stars GitHub followers GitHub forks GitHub watchers Twitter Follow

Unsupervised (Self-Supervised) Discrimination of Seismic Signals Using Deep Convolutional Autoencoders


You can get the paper from here:

Link 1:

https://ieeexplore.ieee.org/document/8704258

Link 2:

https://www.researchgate.net/publication/332814555_Unsupervised_Clustering_of_Seismic_Signals_Using_Deep_Convolutional_Autoencoders


You can get the training dataset from here:

https://drive.google.com/file/d/16itT_IZpM8w8KyFN8eL8iEfYX66Hk6Xb/view?usp=sharing


Reference:

Mousavi, S. M., W. Zhu, W. Ellsworth, G. Beroza (2019).                        
Unsupervised Clustering of Seismic Signals Using Deep Convolutional Autoencoders, 
IEEE Geoscience and Remote Sensing Letters, 1 - 5, doi:10.1109/LGRS.2019.2909218.                                                                                                       

BibTeX:

@article{mousavi2019unsupervised,
 title={Unsupervised Clustering of Seismic Signals Using Deep Convolutional Autoencoders},
 author={Mousavi, S Mostafa and Zhu, Weiqiang and Ellsworth, William and Beroza, Gregory},
 journal={IEEE Geoscience and Remote Sensing Letters},
 year={2019},
 publisher={IEEE}
}        

Abstract:

In this paper, we use deep neural networks for unsupervised clustering of seismic data.We perform the clustering in a feature space that is simultaneously optimized with the clustering assignment, resulting in learned feature representations that are effective for a specific clustering task. To demonstrate the application of this method in seismic signal processing, we design two different neural networks consisting primarily of full convolutional and pooling layers and apply them to: (1) discriminate waveforms recorded at different hypocentral distances and (2) discriminate waveforms with different first-motion polarities. Our method results in precisions that are comparable to those recently achieved by supervised methods, but without the need for labeled data, manual feature engineering, and large training sets. The applications we present here can be used in standard singlesite earthquake early warning systems to reduce the false alerts on an individual station level. However, the presented technique is general and suitable for a variety of applications including quality control of the labeling and classification results of other
supervised methods.


network architecture

Sampel data. a) and b) are two examples of the seismograms with different polarity of first motion. c) and d) are examples of local and teleseismic waveforms respectively while e) and f) are the associated Short-Time Fourier transforms.

network architecture

The architecture of fully convolutional autoencoder used in our study.

clustering results

Clustering results.

embeded features

Visualization of embeded features.

embeded features

embeded features

About

Unsupervised (Self-Supervised) Clustering of Seismic Signals Using Deep Convolutional Autoencoders

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published