Directivity Modes of Earthquake Populations with Unsupervised Learning. Issue 2 (15th February 2020)

• Record Type: Journal Article
• Authors: Ross, Zachary E.; Trugman, Daniel T.; Azizzadenesheli, Kamyar; Anandkumar, Anima
• Is Part Of: Journal of geophysical research. Volume 125:Issue 2(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-02-15
• Subjects: rupture directivity -- earthquake source properties -- machine learning -- unsupervised learning; Geomagnetism -- Periodicals; Geochemistry -- Periodicals; Geophysics -- Periodicals; Earth sciences -- Periodicals; 551.1
• DOI: 10.1029/2019JB018299
• Languages: English
• ISSNs: 2169-9313

Abstract

Abstract: We present a novel approach for resolving modes of rupture directivity in large populations of earthquakes. A seismic spectral decomposition technique is used to first produce relative measurements of radiated energy for earthquakes in a spatially compact cluster. The azimuthal distribution of energy for each earthquake is then assumed to result from one of several distinct modes of rupture propagation. Rather than fitting a kinematic rupture model to determine the most likely mode of rupture propagation, we instead treat the modes as latent variables and learn them with a Gaussian mixture model. The mixture model simultaneously determines the number of events that best identify with each mode. The technique is demonstrated on four datasets in California, each with compact clusters of several thousand earthquakes with comparable slip mechanisms. We show that the datasets naturally decompose into distinct rupture propagation modes that correspond to different rupture directions, and the fault plane is unambiguously identified for all cases. We find that these small earthquakes exhibit unilateral ruptures 63–73% of the time on average. The results provide important observational constraints on the physics of earthquakes and faults. Key Points: We develop an unsupervised machine learning approach to resolving directivity modes in earthquake populations The problem is formulated as recovering the latent modes of rupture propagation that exist in the data naturally Across four strike‐slip datasets in California with thousands of earthquakes, unilateral ruptures occur 63–73% of the time