Generalized Seismic Phase Detection with Deep Learning

By Zachary E. Ross, Men‐Andrin Meier, Egill Hauksson, Thomas H. Heaton. Bulletin of The Seismological Society of America (BSSA), 2018

478 citations recorded by the source corpus.

To optimally monitor earthquake‐generating processes, seismologists have sought to lower detection sensitivities ever since instrumental seismic networks were started about a century ago. Recently, it has become possible to search continuous waveform archives for replicas of previously recorded events (i.e., template matching), which has led to at least an order of magnitude increase in the number of detected earthquakes and greatly sharpened our view of geological structures. Earthquake catalogs produced in this fashion, however, are heavily biased in that they are completely blind to events for which no templates are available, such as in previously quiet regions or for very large‐magnitude events. Here, we show that with deep learning, we can overcome such biases without sacrificing detection sensitivity. We trained a convolutional neural network (ConvNet) on the vast hand‐labeled data archives of the Southern California Seismic Network to detect seismic body‐wave phases. We show that the ConvNet is extremely sensitive and robust in detecting phases even when masked by high background noise and when the ConvNet is applied to new data that are not represented in the training set (in particular, very large‐magnitude events). This generalized phase detection framework will significantly improve earthquake monitoring and catalogs, which form the underlying basis for a wide range of basic and applied seismological research.

Subfields: Artificial Intelligence, Geophysics

View Paper: https://www.semanticscholar.org/paper/e178d94a0601f0f395cf6d81b884a238331fa869

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Geophysics

Citations in the corpus

Physics‐Informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions (2021, background): “, 2019) to tackle problems such as earthquake detection, automatic phase picking (Mousavi et al., 2020; Ross et al., 2018; Yoon et al., 2015) and seismic signal denoising (Zhu et al.”
STanford EArthquake Dataset (STEAD): A Global Data Set of Seismic Signals for AI (2019, methodology): “Neural networks have been used for earthquake signal detection (e.g. [ 5], [6], [38]–[43]).”
Deep-learning seismology (2022, methodology): “The classification capability of DNNs makes them ideal for processing tasks such as event discrimination ( 6 – 8 ), event detection ( 9 , 10 ), phase picking ( 11 , 12 ), first-polarity determination ( 13 , 14 ), and phase association ( 15 , 16 ) that together form a seismicity monitoring workflow.”
Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking (2020, methodology): “Ross et al. 9 adopted a similar approach (3 convolutional and 2 fully connected layers) for picking P arrival times.”
Earthquake Phase Association Using a Bayesian Gaussian Mixture Model (2021, background): “The phase picking step has been significantly improved by deep-learning-based pickers that learn from manual picks labeled by analysts to detect millions of phase picks from raw seismic waveforms (Mousavi et al., 2020; Ross et al., 2018; W. Zhu & Beroza, 2018).”
Machine Learning in Seismology: Turning Data into Insights (2018, methodology): “Ross, Meier, and Hauksson (2018) trained a CNN to pick P - wave onset times, but instead used the network as a regressor to predict the time index of the phase onset.”
Seismic Signal Denoising and Decomposition Using Deep Neural Networks (2018, methodology): “Deep learning has been shown to be a powerful tool for learning the characteristics of seismic data [47, 48, 49, 50, 51, 52, 53, 54].”
Which Picker Fits My Data? A Quantitative Evaluation of Deep Learning Based Seismic Pickers (2021, background): “Generalized phase detection (GPD) (Ross et al., 2018) is a phase identification model with a short input window of only 4 s at 100 Hz sampling rate.”