Earthquake Catalog‐Based Machine Learning Identification of Laboratory Fault States and the Effects of Magnitude of Completeness

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.

[1]  Jeen‐Hwa Wang,et al.  Precursor times of abnormal b-values prior to mainshocks , 2016, Journal of Seismology.

[2]  Paul A. Johnson,et al.  Estimating Fault Friction From Seismic Signals in the Laboratory , 2017, 1710.04172.

[3]  Xinglin Lei,et al.  Laboratory acoustic emission study for earthquake generation process , 2014 .

[4]  Warwick D. Smith.  The b-value as an earthquake precursor , 1981, Nature.

[5]  C. Humphreys,et al.  Machine Learning Predicts Laboratory Earthquakes , 2017, Geophysical Research Letters.

[6]  Alan R. Nelson,et al.  Great earthquakes of variable magnitude at the Cascadia subduction zone , 2005, Quaternary Research.

[7]  Chris Marone,et al.  The effect of loading rate on static friction and the rate of fault healing during the earthquake cycle , 1998, Nature.

[8]  A. E. Hoerl,et al.  Ridge regression: biased estimation for nonorthogonal problems , 2000 .

[9]  C. Scholz.  On the stress dependence of the earthquake b value , 2015 .

[10]  T. Heaton,et al.  The hidden simplicity of subduction megathrust earthquakes , 2017, Science.

[11]  Danijel Schorlemmer,et al.  Acoustic emissions document stress changes over many seismic cycles in stick‐slip experiments , 2013 .

[12]  C. Scholz.  The frequency-magnitude relation of microfracturing in rock and its relation to earthquakes , 1968 .

[13]  Stefan Wiemer,et al.  Short‐term probabilistic earthquake risk assessment considering time‐dependent b values , 2016 .

[14]  J. Carmeliet,et al.  Microslips as precursors of large slip events in the stick‐slip dynamics of sheared granular layers: A discrete element model analysis , 2013 .

[15]  Amir Hossein Alavi,et al.  Machine learning in geosciences and remote sensing , 2016 .

[16]  Zhigang Peng,et al.  Foreshocks, b Value Map, and Aftershock Triggering for the 2011 Mw 5.7 Virginia Earthquake , 2018, Journal of Geophysical Research: Solid Earth.

[17]  J. Anthony,et al.  Influence of particle characteristics on granular friction , 2005 .

[18]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[19]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[20]  D. Marsan,et al.  The long precursory phase of most large interplate earthquakes , 2013 .

[21]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[22]  M. Bouchon,et al.  The Aftershock Signature of Supershear Earthquakes , 2008, Science.

[23]  Mei Li,et al.  Studies on earthquake precursors in China: A review for recent 50 years , 2017 .

[24]  D. Lockner,et al.  Physical modeling of the formation and evolution of seismically active fault zones , 1997 .

[25]  Arthur Paté,et al.  Machine learning reveals cyclic changes in seismic source spectra in Geysers geothermal field , 2018, Science Advances.

[26]  Francisco Martínez-Álvarez,et al.  Seismic indicators based earthquake predictor system using Genetic Programming and AdaBoost classification , 2018, Soil Dynamics and Earthquake Engineering.

[27]  Zefeng Li,et al.  Machine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning , 2018, Geophysical Research Letters.

[28]  Paul A. Johnson,et al.  Breaking Cascadia's Silence: Machine Learning Reveals the Constant Chatter of the Megathrust , 2018 .

[29]  Jacques Rivière,et al.  Evolution of b-value during the seismic cycle: Insights from laboratory experiments on simulated faults , 2018 .

[30]  Hideitsu Hino,et al.  Geochemical Discrimination and Characteristics of Magmatic Tectonic Settings: A Machine‐Learning‐Based Approach , 2017, 1712.09016.

[31]  Grzegorz Kwiatek,et al.  Seismic moment tensor and b value variations over successive seismic cycles in laboratory stick‐slip experiments , 2014 .

[32]  P. Johnson,et al.  Acoustic emission and microslip precursors to stick‐slip failure in sheared granular material , 2013 .

[33]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[34]  D. Marsan,et al.  Foreshock activity related to enhanced aftershock production , 2014 .

[35]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[36]  J. Weeks,et al.  Change in b-values during movement on cut surfaces in granite , 1978 .