Explainable machine learning for labquake prediction using catalog-driven 
features

Karimpouli, Sadegh; Caus, Danu; Grover, Harsh; Martinez Garzon, P.; Bohnhoff, M.; Beroza, Gregory C.; Dresen, G.; Goebel, Thomas; Weigel, Tobias; Kwiatek, G.

doi:10.1016/j.epsl.2023.118383

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Journal Article

Explainable machine learning for labquake prediction using catalog-driven features

Authors

/persons/resource/sadeghkp

Karimpouli, Sadegh
4.2 Geomechanics and Scientific Drilling, 4.0 Geosystems, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

Caus, Danu
External Organizations;

Grover, Harsh
External Organizations;

/persons/resource/patricia

Martinez Garzon, P.
4.2 Geomechanics and Scientific Drilling, 4.0 Geosystems, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

/persons/resource/bohnhoff

Bohnhoff, M.
4.2 Geomechanics and Scientific Drilling, 4.0 Geosystems, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

Beroza, Gregory C.
External Organizations;

/persons/resource/dre

Dresen, G.
4.2 Geomechanics and Scientific Drilling, 4.0 Geosystems, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

Goebel, Thomas
External Organizations;

Weigel, Tobias
External Organizations;

/persons/resource/kwiatek

Kwiatek, G.
4.2 Geomechanics and Scientific Drilling, 4.0 Geosystems, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

External Ressource

No external resources are shared

Fulltext (public)

5022837.pdf
(Publisher version), 3MB

Supplementary Material (public)

There is no public supplementary material available

Citation

Karimpouli, S., Caus, D., Grover, H., Martinez Garzon, P., Bohnhoff, M., Beroza, G. C., Dresen, G., Goebel, T., Weigel, T., Kwiatek, G. (2023): Explainable machine learning for labquake prediction using catalog-driven features. - Earth and Planetary Science Letters, 622, 118383.
https://doi.org/10.1016/j.epsl.2023.118383

Cite as: https://gfzpublic.gfz-potsdam.de/pubman/item/item_5022837

Abstract

Recently, Machine learning (ML) has been widely utilized for laboratory earthquake (labquake) prediction using various types of data. This study pioneers in time to failure (TTF) prediction based on ML using acoustic emission (AE) records from three laboratory stick-slip experiments performed on Westerly granite samples with naturally fractured rough faults, more similar to the heterogeneous fault structures in the nature. 47 catalog-driven seismo-mechanical and statistical features are extracted introducing some new features based on focal mechanism. A regression voting ensemble of Long-Short Term Memory (LSTM) networks predicts TTF with a coefficient of determination () of 70% on the test dataset. Feature importance analysis revealed that AE rate, correlation integral, event proximity, and focal mechanism-based features are the most important features for TTF prediction. Results reveal that the network uses all information among the features for prediction, including general trends in high correlated features as well as fine details about local variations and fault evolution involved in low correlated features. Therefore, some highly correlated and physically meaningful features may be considered less important for TTF prediction due to their correlation with other important features. Our study provides a ground for applying catalog-driven to constrain TTF of complex heterogeneous rough faults, which is capable to be developed for real application.