Skip to content

Analysis of the waveforms of seismic data from the Stromboli volcano

Notifications You must be signed in to change notification settings

llayer/StromboliWF

Repository files navigation

StromboliWF

Unsupervised analysis of the time evolution of clusters of VLP signal waveforms (timeseries) from the Stromboli volcano.

Cutting of the signals

The selected signals stored in day files can be cutted with day_to_ascii.py.

Feature extraction

Filtering, decimating, LPC and amplitude parametrization of the created ascii files is done with the script ascii_to_param.py. A visualization for an exemplary signal can be found in parametrization.ipynb.

Autoencoders

The script autoencoder.ipynb implements autoencoders and can be run on Google Colab.

t-SNE and SOM optimization

The expensive t-SNE algorithm and the Bayesian optimization of the SOM can be run with tsne_somopt.ipynb and then saved for later usage.

Clustering with K-Means

An example to cluster the filtered signals can be found in cluster.ipynb. The SOM and clustering with K-Means on the weight vectors of the SOM is done in SOM.ipynb

Comparison of the time evolution

The time evolution of the clusters of the different methods can be found in ratio.ipynb

About

Analysis of the waveforms of seismic data from the Stromboli volcano

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published