Earthquake Phase Association using a Bayesian Gaussian Mixture Model

Abstract

Earthquake phase association algorithms aggregate picked seismic phases from a network of seismometers into individual earthquakes and play an important role in earthquake monitoring. Dense seismic networks and improved phase picking methods produce massive earthquake phase data sets, particularly for earthquake swarms and aftershocks occurring closely in time and space, making phase association a challenging problem. We present a new association method, the Gaussian M ixture M odel Association (GaMMA), that combines the Gaussian mixture model for phase measurements (both time and amplitude), with earthquake location, origin time, and magnitude estimation. We treat earthquake phase association as an unsupervised clustering problem in a probabilistic framework, where each earthquake corresponds to a cluster of P and S phases with hyperbolic moveout of arrival times and a decay of amplitude with distance. We use a multivariate Gaussian distribution to model the collection of phase picks for an event, the mean of which is given by the predicted arrival time and amplitude from the causative event. We carry out the pick assignment for each earthquake and determine earthquake parameters (i.e., earthquake location, origin time, and magnitude) under the maximum likelihood criterion using the Expectation-Maximization (EM) algorithm. The GaMMA method does not require the typical association steps of other algorithms, such as grid-search or supervised training. The results on both synthetic test and the 2019 Ridgecrest earthquake sequence show that GaMMA effectively associates phases from a temporally and spatially dense earthquake sequence while producing useful estimates of earthquake location and magnitude.

Machine learning event detection workflows in practice: A case study from the 2019 Durrës aftershock sequence

“…There are also a more prominent general suite of techniques being applied to tackle the scalability problem; ML-based methods, which can utilise the information contained within extensive datasets to perform inference. Newly proposed phase association methods utilise a variety of ML techniques, from graph-theory (McBrearty, Gomberg, Delorey & Johnson 2019), Bayesian Gaussian Mixture Models for unsupervised clustering (Zhu, McBrearty, Mousavi, Ellsworth & Beroza 2021), recurrent neural networks (Ross, Yue, Meier, Hauksson & Heaton 2019), and also RANdom SAmple Consensus (RANSAC; Fischler & Bolles, 1981), a data-driven ML technique to fit a parametric model to a data distribution (e.g. Woollam et al, 2020;Zhu, Chuang, McClellan, Liu & Peng, 2021).…”