Specufex/specufex

Probabilistic unsupervised feature extraction from seismic spectrograms for machine learning.

44
/ 100
Emerging

This tool helps seismologists and geophysicists analyze seismic waveform data, particularly from earthquakes. It takes raw seismic spectrograms (visual representations of sound frequencies over time) and extracts simplified "fingerprints" that capture important variations. These fingerprints make it easier to identify patterns in seismic activity for further machine learning analysis like clustering or classification.

Use this if you need to transform large collections of seismic spectrograms into concise, low-dimensional representations to uncover hidden patterns or prepare data for other machine learning tasks.

Not ideal if your data is not seismic spectrograms, or if you need a simpler, non-probabilistic method for feature extraction.

seismology geophysics earthquake-analysis spectral-analysis waveform-processing
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

18

Forks

6

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Specufex/specufex"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.