SeisBench is a toolbox for applying machine learning techniques to seismology. It provides a common interface for seismic datasets, pretrained models and data-generation pipelines, reducing the amount of custom code needed to train and evaluate models on different seismic datasets.

The software can be used for tasks such as seismic phase picking, earthquake detection, denoising, event catalogue construction and analysis of distributed acoustic sensing data. Researchers can load existing benchmark datasets and pretrained models, train models on their own data, or construct reproducible processing pipelines for comparative studies.

This is free and open source software.

• Access benchmark seismic datasets through a unified interface.
• Load and apply pretrained machine learning models.
• Train supported models on different seismic datasets.
• Build configurable data generation and augmentation pipelines.
• Perform seismic phase picking and earthquake detection.
• Build earthquake event catalogues.
• Support seismic denoising workflows.
• Work with distributed acoustic sensing data.

Website: github.com/seisbench/seisbench
Support:
Developer: SeisBench developers
License: GNU General Public License v3.0

SeisBench is written in Python. Learn Python with our recommended free books and free tutorials.

Explore our comprehensive directory of recommended free and open source software. Our carefully curated collection spans every major software category.

This directory is part of our ongoing series of informative articles for Linux enthusiasts. It features hundreds of detailed reviews, along with open source alternatives to proprietary solutions from major corporations such as Google, Microsoft, Apple, Adobe, IBM, Cisco, Oracle, and Autodesk.

You’ll also find interesting projects to try, hardware coverage, free programming books and tutorials, and much more.

Discovered a useful open source Linux program that we haven’t covered yet? Let us know by completing this form.