P Wave Arrival Picking and First‐Motion Polarity Determination With Deep Learning

  title={P Wave Arrival Picking and First‐Motion Polarity Determination With Deep Learning},
  author={Zachary E. Ross and Men‐Andrin Meier and Egill Hauksson},
  journal={Journal of Geophysical Research: Solid Earth},
  pages={5120 - 5129}
Determining earthquake hypocenters and focal mechanisms requires precisely measured P wave arrival times and first‐motion polarities. Automated algorithms for estimating these quantities have been less accurate than estimates by human experts, which are problematic for processing large data volumes. Here we train convolutional neural networks to measure both quantities, which learn directly from seismograms without the need for feature extraction. The networks are trained on 18.2 million… 
P-wave first-motion polarity determination of waveform data in western Japan using deep learning
P-wave first-motion polarity is the most useful information in determining the focal mechanisms of earthquakes, particularly for smaller earthquakes. Algorithms have been developed to automatically
Automatic Identification of Mantle Seismic Phases Using a Convolutional Neural Network
Typical seismic waveform data sets comprise hundreds of thousands to millions of records. Compilation is performed by time‐consuming handpicking of phase arrival times, or signal processing
Generalized Seismic Phase Detection with Deep Learning
This work 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 and shows that the ConvNet is extremely sensitive and robust in detecting phases even when masked by high background noise and when the Conv net is applied to new data that are not represented in the training set.
Deep learning for P-wave arrival picking in earthquake early warning
Fast and accurate P-wave arrival picking significantly affects the performance of earthquake early warning (EEW) systems. Automated P-wave picking algorithms used in EEW have encountered problems of
Seismic Phase Picking Using Convolutional Networks
Cospy is described, an open-source convolutional phase picker that uses a two-stage analysis in which the first stage segments a rough area around the phase, and the second stage regresses the precise location.
Pairwise Association of Seismic Arrivals with Convolutional Neural Networks
This work applies convolutional neural networks (CNNs) to the problem of associations to read earthquake waveform arrival pairs between two stations and predict the binary classification of whether the two waveforms are from a common source or different sources.
Earthquake Detection and P-Wave Arrival Time Picking Using Capsule Neural Network
The CapsNet shows the highest picking accuracy and outperforms the benchmark methods and is tested using continuous seismic data associated with the 24-hours microearthquakes swarm that occurred in the Arkansas area.
P-Wave Identification with Deep Neural Network
The results show that for dataset of regional and distant earthquakes, recall ratio for p-wave is 90% on the average, and precision ratio is around 70%, indicating that DNN along with appropriate signal processing such as STFT perform well in P-wave identification.
Monitoring the 2020 Magna, Utah, Earthquake Sequence with Nodal Seismometers and Machine Learning
This work uses machine learning (ML) methods to create a new catalog of arrival time picks, earthquake locations, and P-wave polarities for 18 March 2020–30 April 2020, and integrates the geophone data with data from the permanent regional seismic network operated by the University of Utah Seismograph Stations.


Automatic picking of P and S phases using a neural tree
Comparison between neural network automatic onset picking and standard, manual methods, shows that the technique presented here is generally robust and that it is capable to correctly identify phase-types while providing estimates of their accuracies.
Automatic S-Wave Picker for Local Earthquake Tomography
High-resolution seismic tomography at local and regional scales requires large and consistent sets of arrival-time data. Algorithms combining accurate pick- ing with an automated quality
An Automatic Kurtosis‐Based P ‐ and S ‐Phase Picker Designed for Local Seismic Networks
An automatic P ‐ and S ‐wave onset‐picking algorithm, using kurtosis‐derived characteristic functions (CF) and eigenvalue decompositions on three‐component seismic data, which resulted in more locations than manual picking, picking as many P onsets and twice as many S onsets as with manual picking or the STA/LTA algorithm.
Seismic features and automatic discrimination of deep and shallow induced-microearthquakes using neural network and logistic regression
We develop an automated strategy for discriminating deep microseismic events from shallow ones on the basis of the waveforms recorded on a limited number of surface receivers. Machine-learning
Computing a Large Refined Catalog of Focal Mechanisms for Southern California (1981-2010): Temporal Stability of the Style of Faulting
Using the method developed by Hardebeck and Shearer (2002, 2003) termed the HASH method, we calculate focal mechanisms for earthquakes that occurred in the southern California region from 1981 to
Convolutional neural network for earthquake detection and location
This work leverages the recent advances in artificial intelligence and presents ConvNetQuake, a highly scalable convolutional neural network for earthquake detection and location from a single waveform, and applies it to study the induced seismicity in Oklahoma, USA.
Evidence for fluid‐triggered slip in the 2009 Mount Rainier, Washington earthquake swarm
A vigorous swarm of over 1000 small, shallow earthquakes occurred 20–22 September 2009 beneath Mount Rainier, Washington, including the largest number of events ever recorded in a single day at
Event Detection and Phase Picking Using a Time-Domain Estimate of Predominate Period Tpd
We present a new approach for event detection and accurate determination of the onset time of seismic phases. We use a simple time-domain function ( T pd ), which is readily and efficiently
PAI-S/K: A robust automatic seismic P phase arrival identification scheme
A new approach based on higher-order statistics (HOS) is introduced that overcomes the subjectivity of human intervention and eliminates the noise factor, making the proposed PAI-S/K scheme an attractive candidate for huge seismic data assessment in a real-time context.