Earthquake catalog-based machine learning identification of laboratory fault states and the effects of magnitude of completeness

TL;DR

This study demonstrates that machine learning regression using earthquake event catalogs can effectively predict fault properties, with performance depending on the catalog's magnitude of completeness, highlighting the importance of catalog quality.

Contribution

It introduces a method for applying machine learning regression to earthquake catalogs of various scales and completeness levels to predict fault states.

Findings

Model performance improves with lower magnitude of completeness.

Performance saturates below a certain completeness threshold.

Applicable to catalogs of arbitrary scale and completeness.

Abstract

Machine learning regression can predict macroscopic fault properties such as shear stress, friction, and time to failure using continuous records of fault zone acoustic emissions. Here we show that a similar approach is successful using event catalogs derived from the continuous data. Our methods are applicable to catalogs of arbitrary scale and magnitude of completeness. We investigate how machine learning regression from an event catalog of laboratory earthquakes performs as a function of the catalog magnitude of completeness. We find that strong model performance requires a sufficiently low magnitude of completeness, and below this magnitude of completeness model performance saturates.