Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Making Phase-Picking Neural Networks More Consistent and Interpretable

Journal Article · · The Seismic Record
DOI:https://doi.org/10.1785/0320230054· OSTI ID:2329261

Improving the interpretability of phase-picking neural networks remains an important task to facilitate their deployment to routine, real-time seismic monitoring. The popular phase-picking neural networks published in the literature lack interpretability because their output prediction scores do not necessarily correspond with the reliability of phase picks and can even be highly inconsistent depending on how we window the waveform data. Here, we show that systematically shifting the waveforms during training and using an antialiasing filter within the neural network architecture can substantially improve the consistency of the output prediction scores and can even make them scale with the signal-to-noise ratios of the waveforms. We demonstrate the improvements by applying these approaches to a commonly used phase-picking neural network architecture and using waveform data from the 2019 Ridgecrest earthquake sequence.

Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation
Grant/Contract Number:
89233218CNA000001
OSTI ID:
2329261
Report Number(s):
LA-UR--23-34160
Journal Information:
The Seismic Record, Journal Name: The Seismic Record Journal Issue: 1 Vol. 4; ISSN 2694-4006
Publisher:
Seismological Society of AmericaCopyright Statement
Country of Publication:
United States
Language:
English

References (21)

U-Net: Convolutional Networks for Biomedical Image Segmentation
  • Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas
  • Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III https://doi.org/10.1007/978-3-319-24574-4_28
book November 2015
Rapid Characterization of the July 2019 Ridgecrest, California, Earthquake Sequence From Raw Seismic Data Using Machine‐Learning Phase Picker journal February 2020
Machine‐Learning‐Based Analysis of the Guy‐Greenbrier, Arkansas Earthquakes: A Tale of Two Sequences journal March 2020
Raton Basin Induced Seismicity Is Hosted by Networks of Short Basement Faults and Mimics Tectonic Earthquake Statistics journal November 2021
EdgePhase: A Deep Learning Model for Multi‐Station Seismic Phase Picking journal October 2022
Phase Neural Operator for Multi‐Station Picking of Seismic Arrivals journal December 2023
Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking journal August 2020
DeepPhasePick: A method for detecting and picking seismic phases from local earthquakes based on highly optimized convolutional and recurrent deep neural networks journal July 2021
En echelonfaults reactivated by wastewater disposal near Musreau Lake, Alberta journal May 2023
PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method journal October 2018
The magmatic web beneath Hawai‘i journal February 2023
Generalized Seismic Phase Detection with Deep Learning journal August 2018
A Detailed View of the 2020–2023 Southwestern Puerto Rico Seismic Sequence with Deep Learning journal July 2023
Reactivation of Precambrian Faults by Deep Wastewater Injection in Midland Basin, Texas, and Performance Evaluation of Seismic Response Areas journal August 2023
Convolutional Neural Network for Seismic Phase Classification, Performance Demonstration over a Local Seismic Network journal January 2019
Hybrid Event Detection and Phase‐Picking Algorithm Using Convolutional and Recurrent Neural Networks journal April 2019
A High-Resolution Seismic Catalog for the Initial 2019 Ridgecrest Earthquake Sequence: Foreshocks, Aftershocks, and Faulting Complexity journal January 2020
A Mitigation Strategy for the Prediction Inconsistency of Neural Phase Pickers journal March 2023
Machine-Learning-Based High-Resolution Earthquake Catalog Reveals How Complex Fault Structures Were Activated during the 2016–2017 Central Italy Sequence journal April 2021
Basement Fault Activation before Larger Earthquakes in Oklahoma and Kansas journal July 2022
Parametric Testing of EQTransformer’s Performance against a High-Quality, Manually Picked Catalog for Reliable and Accurate Seismic Phase Picking journal October 2023

Similar Records

An End-To-End Earthquake Detection Method for Joint Phase Picking and Association Using Deep Learning
Journal Article · Tue Mar 15 00:00:00 EDT 2022 · Journal of Geophysical Research. Solid Earth · OSTI ID:1978540

Related Subjects