Real-Time Fault Tracking and Ground Motion Prediction for Large Earthquakes With HR-GNSS and Deep Learning

Lin, Jiun‐Ting; Melgar-Moctezuma, Diego; Sahakian, Valerie J.; Thomas, Amanda M.; Searcy, Jacob

doi:10.1029/2023jb027255

Real-Time Fault Tracking and Ground Motion Prediction for Large Earthquakes With HR-GNSS and Deep Learning

Journal Article · Thu Dec 07 23:00:00 EST 2023 · Journal of Geophysical Research. Solid Earth

DOI:https://doi.org/10.1029/2023jb027255· OSTI ID:2246707

^[1]; ^[2]; ^[2]; ^[2]; ^[2]

Univ. of Oregon, Eugene, OR (United States); Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Univ. of Oregon, Eugene, OR (United States)

Earthquake early warning (EEW) systems aim to forecast the shaking intensity rapidly after an earthquake occurs and send warnings to affected areas before the onset of strong shaking. The system relies on rapid and accurate estimation of earthquake source parameters. However, it is known that source estimation for large ruptures in real-time is challenging, and it often leads to magnitude underestimation. In a previous study, we showed that machine learning, HR-GNSS, and realistic rupture synthetics can be used to reliably predict earthquake magnitude. This model, called Machine-Learning Assessed Rapid Geodetic Earthquake model (M-LARGE), can rapidly forecast large earthquake magnitudes with an accuracy of 99%. Here, we expand M-LARGE to predict centroid location and fault size, enabling the construction of the fault rupture extent for forecasting shaking intensity using existing ground motion models. We test our model in the Chilean Subduction Zone with thousands of simulated and five real large earthquakes. The result achieves an average warning time of 40.5 s for shaking intensity MMI4+, surpassing the 34 s obtained by a similar GNSS EEW model. Our approach addresses a critical gap in existing EEW systems for large earthquakes by demonstrating real-time fault tracking feasibility without saturation issues. This capability leads to timely and accurate ground motion forecasts and can support other methods, enhancing the overall effectiveness of EEW systems. Additionally, the ability to predict source parameters for real Chilean earthquakes implies that synthetic data, governed by our understanding of earthquake scaling, is consistent with the actual rupture processes.

View Accepted Manuscript (DOE)

Research Organization:: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA); National Aeronautics and Space Administration (NASA); National Science Foundation (NSF); USGS

Grant/Contract Number:: AC52-07NA27344

OSTI ID:: 2246707

Report Number(s):: LLNL--JRNL-849971; 1075553

Journal Information:: Journal of Geophysical Research. Solid Earth, Journal Name: Journal of Geophysical Research. Solid Earth Journal Issue: 12 Vol. 128; ISSN 2169-9313

Publisher:: American Geophysical UnionCopyright Statement

Country of Publication:: United States

Language:: English

References (61)

jiunting/MLARGE: First release of MLARGE Lin, Jiun-Ting https://doi.org/10.5281/zenodo.4527253	software	February 2021
Chilean Subduction Zone rupture scenarios and waveform data Lin, Jiun-Ting; Melgar, Diego; Thomas, Amanda M. Zenodo https://doi.org/10.5281/zenodo.5015610	dataset	January 2020
Earthquake magnitude scaling using seismogeodetic data Crowell, Brendan W.; Melgar, Diego; Bock, Yehuda Geophysical Research Letters, Vol. 40, Issue 23 https://doi.org/10.1002/2013gl058391	journal	December 2013
Real‐time inversions for finite fault slip models and rupture geometry based on high‐rate GPS data Minson, S. E.; Murray, Jessica R.; Langbein, John O. Journal of Geophysical Research: Solid Earth, Vol. 119, Issue 4 https://doi.org/10.1002/2013jb010622	journal	April 2014
LITHO1.0: An updated crust and lithospheric model of the Earth: LITHO1.0 Pasyanos, Michael E.; Masters, T. Guy; Laske, Gabi Journal of Geophysical Research: Solid Earth, Vol. 119, Issue 3 https://doi.org/10.1002/2013jb010626	journal	March 2014
Operational real-time GPS-enhanced earthquake early warning Grapenthin, R.; Johanson, I. A.; Allen, R. M. Journal of Geophysical Research: Solid Earth, Vol. 119, Issue 10 https://doi.org/10.1002/2014jb011400	journal	October 2014
Kinematic rupture scenarios and synthetic displacement data: An example application to the Cascadia subduction zone Melgar, Diego; LeVeque, Randall J.; Dreger, Douglas S. Journal of Geophysical Research: Solid Earth, Vol. 121, Issue 9 https://doi.org/10.1002/2016jb013314	journal	September 2016
Fiber-Optic Network Observations of Earthquake Wavefields: FIBER-OPTIC EARTHQUAKE OBSERVATIONS Lindsey, Nathaniel J.; Martin, Eileen R.; Dreger, Douglas S. Geophysical Research Letters, Vol. 44, Issue 23 https://doi.org/10.1002/2017gl075722	journal	December 2017
How “good” are real-time ground motion predictions from Earthquake Early Warning systems?: Performance Metrics for Real-Time GMPs Meier, Men-Andrin Journal of Geophysical Research: Solid Earth, Vol. 122, Issue 7 https://doi.org/10.1002/2017jb014025	journal	July 2017
The ElarmS Earthquake Early Warning Methodology and Application across California Allen, Richard M. Earthquake Early Warning Systems https://doi.org/10.1007/978-3-540-72241-0_3	book	January 2007
Earthquake Early Warning and Tsunami Warning of the Japan Meteorological Agency, and Their Performance in the 2011 off the Pacific Coast of Tohoku Earthquake (M_w 9.0) Hoshiba, M.; Ozaki, T. Advanced Technologies in Earth Sciences https://doi.org/10.1007/978-3-642-12233-0_1	book	January 2014
EDIM: Earthquake Disaster Information System for the Marmara Region, Turkey Wenzel, F.; Erdik, M.; Köhler, N. Advanced Technologies in Earth Sciences https://doi.org/10.1007/978-3-642-12233-0_6	book	January 2014
GPS seismology Larson, Kristine M. Journal of Geodesy, Vol. 83, Issue 3-4 https://doi.org/10.1007/s00190-008-0233-x	journal	February 2009
The finite, kinematic rupture properties of great-sized earthquakes since 1990 Hayes, Gavin P. Earth and Planetary Science Letters, Vol. 468 https://doi.org/10.1016/j.epsl.2017.04.003	journal	June 2017
The global CMT project 2004–2010: Centroid-moment tensors for 13,017 earthquakes Ekström, G.; Nettles, M.; Dziewoński, A. M. Physics of the Earth and Planetary Interiors, Vol. 200-201 https://doi.org/10.1016/j.pepi.2012.04.002	journal	June 2012
Processing of strong-motion accelerograms: needs, options and consequences Boore, David M.; Bommer, Julian J. Soil Dynamics and Earthquake Engineering, Vol. 25, Issue 2 https://doi.org/10.1016/j.soildyn.2004.10.007	journal	February 2005
Earthquake source scaling and self-similarity estimation from stacking P and S spectra : SOURCE SCALING AND SELF-SIMILARITY Prieto, Germán A.; Shearer, Peter M.; Vernon, Frank L. Journal of Geophysical Research: Solid Earth, Vol. 109, Issue B8 https://doi.org/10.1029/2004jb003084	journal	August 2004
Earthquake early warning for Bucharest, Romania: Novel and revised scaling relations Böse, M.; Ionescu, C.; Wenzel, F. Geophysical Research Letters, Vol. 34, Issue 7 https://doi.org/10.1029/2007gl029396	journal	April 2007
Development of earthquake early warning system in Taiwan Hsiao, Nai‐Chi; Wu, Yih‐Min; Shin, Tzay‐Chyn Geophysical Research Letters, Vol. 36, Issue 5 https://doi.org/10.1029/2008gl036596	journal	January 2009
Earthquake early warning system in southern Italy: Methodologies and performance evaluation Zollo, A.; Iannaccone, G.; Lancieri, M. Geophysical Research Letters, Vol. 36, Issue 5 https://doi.org/10.1029/2008gl036689	journal	February 2009
Quantifying the Value of Real‐Time Geodetic Constraints for Earthquake Early Warning Using a Global Seismic and Geodetic Data Set Ruhl, C. J.; Melgar, D.; Chung, A. I. Journal of Geophysical Research: Solid Earth, Vol. 124, Issue 4 https://doi.org/10.1029/2018jb016935	journal	April 2019
A Machine‐Learning Approach for Earthquake Magnitude Estimation Mousavi, S. Mostafa; Beroza, Gregory C. Geophysical Research Letters, Vol. 47, Issue 1 https://doi.org/10.1029/2019gl085976	journal	January 2020
Noise Characteristics of Operational Real‐Time High‐Rate GNSS Positions in a Large Aperture Network Melgar, Diego; Crowell, Brendan W.; Melbourne, Timothy I. Journal of Geophysical Research: Solid Earth, Vol. 125, Issue 7 https://doi.org/10.1029/2019jb019197	journal	June 2020
Improving Early Estimates of Large Earthquake's Final Fault Lengths and Magnitudes Leveraging Source Fault Structural Maturity Information Hutchison, Allie A.; Böse, Maren; Manighetti, Isabelle Geophysical Research Letters, Vol. 47, Issue 14 https://doi.org/10.1029/2020gl087539	journal	July 2020
Toward Near‐Field Tsunami Forecasting Along the Cascadia Subduction Zone Using Rapid GNSS Source Models Williamson, Amy L.; Melgar, Diego; Crowell, Brendan W. Journal of Geophysical Research: Solid Earth, Vol. 125, Issue 8 https://doi.org/10.1029/2020jb019636	journal	August 2020
Early Warning for Great Earthquakes From Characterization of Crustal Deformation Patterns With Deep Learning Lin, J. ‐T.; Melgar, D.; Thomas, A. M. Journal of Geophysical Research: Solid Earth, Vol. 126, Issue 10 https://doi.org/10.1029/2021jb022703	journal	October 2021
Earthquake source scaling relationships from −1 to 5 M _L using seismograms recorded at 2.5-km depth Abercrombie, Rachel E. Journal of Geophysical Research: Solid Earth, Vol. 100, Issue B12 https://doi.org/10.1029/95jb02397	journal	December 1995
Scaling law of seismic spectrum Aki, Keiiti Journal of Geophysical Research, Vol. 72, Issue 4 https://doi.org/10.1029/jz072i004p01217	journal	February 1967
Real-time determination of earthquake focal mechanism via deep learning Kuang, Wenhuan; Yuan, Congcong; Zhang, Jie Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-21670-x	journal	March 2021
The Limits of Earthquake Early Warning Accuracy and Best Alerting Strategy Minson, Sarah E.; Baltay, Annemarie S.; Cochran, Elizabeth S. Scientific Reports, Vol. 9, Issue 1 https://doi.org/10.1038/s41598-019-39384-y	journal	February 2019
A note on the dynamic and static displacements from a point source in multilayered media: A note on the dynamic and static displacements from a point source Zhu, Lupei; Rivera, Luis A. Geophysical Journal International, Vol. 148, Issue 3 https://doi.org/10.1046/j.1365-246x.2002.01610.x	journal	March 2002
Physical applications of GPS geodesy: a review Bock, Yehuda; Melgar, Diego Reports on Progress in Physics, Vol. 79, Issue 10 https://doi.org/10.1088/0034-4885/79/10/106801	journal	August 2016
Rapid prediction of earthquake ground shaking intensity using raw waveform data and a convolutional neural network Jozinović, Dario; Lomax, Anthony; Štajduhar, Ivan Geophysical Journal International, Vol. 222, Issue 2 https://doi.org/10.1093/gji/ggaa233	journal	May 2020
The transformer earthquake alerting model: a new versatile approach to earthquake early warning Münchmeyer, Jannes; Bindi, Dino; Leser, Ulf Geophysical Journal International, Vol. 225, Issue 1 https://doi.org/10.1093/gji/ggaa609	journal	December 2020
Learning source, path and site effects: CNN-based on-site intensity prediction for earthquake early warning Zhang, Hongcai; Melgar, Diego; Sahakian, Valerie Geophysical Journal International, Vol. 231, Issue 3 https://doi.org/10.1093/gji/ggac325	journal	August 2022
FinDer v.2: Improved real-time ground-motion predictions for M2–M9 with seismic finite-source characterization Böse, M.; Smith, D. E.; Felizardo, C. Geophysical Journal International, Vol. 212, Issue 1 https://doi.org/10.1093/gji/ggx430	journal	October 2017
Real-time Finite Fault Rupture Detector (FinDer) for large earthquakes Böse, Maren; Heaton, Thomas H.; Hauksson, Egill Geophysical Journal International, Vol. 191, Issue 2 https://doi.org/10.1111/j.1365-246x.2012.05657.x	journal	September 2012
Earthquake Early Warning: Advances, Scientific Challenges, and Societal Needs Allen, Richard M.; Melgar, Diego Annual Review of Earth and Planetary Sciences, Vol. 47, Issue 1 https://doi.org/10.1146/annurev-earth-053018-060457	journal	May 2019
Experiment on an Onsite Early Warning Method for the Taiwan Early Warning System Wu, Y. -M.; Kanamori, H. Bulletin of the Seismological Society of America, Vol. 95, Issue 1 https://doi.org/10.1785/0120040097	journal	February 2005
On the Use of High-Resolution Topographic Data as a Proxy for Seismic Site Conditions (VS30) Allen, T. I.; Wald, D. J. Bulletin of the Seismological Society of America, Vol. 99, Issue 2A https://doi.org/10.1785/0120080255	journal	April 2009
Broadband Ground-Motion Simulation Using a Hybrid Approach Graves, R. W.; Pitarka, A. Bulletin of the Seismological Society of America, Vol. 100, Issue 5A https://doi.org/10.1785/0120100057	journal	September 2010
A Revised Ground-Motion and Intensity Interpolation Scheme for ShakeMap Worden, C. B.; Wald, D. J.; Allen, T. I. Bulletin of the Seismological Society of America, Vol. 100, Issue 6 https://doi.org/10.1785/0120100101	journal	December 2010
Scaling Relations of Earthquake Source Parameter Estimates with Special Focus on Subduction Environment Blaser, L.; Kruger, F.; Ohrnberger, M. Bulletin of the Seismological Society of America, Vol. 100, Issue 6 https://doi.org/10.1785/0120100111	journal	December 2010
Ground‐Motion Prediction Equation for the Chilean Subduction Zone Montalva, Gonzalo A.; Bastías, Nicolás; Rodriguez‐Marek, Adrian Bulletin of the Seismological Society of America, Vol. 107, Issue 2 https://doi.org/10.1785/0120160221	journal	February 2017
The Propagation of Local Undamped Motion (PLUM) Method: A Simple and Robust Seismic Wavefield Estimation Approach for Earthquake Early Warning Kodera, Yuki; Yamada, Yasuyuki; Hirano, Kazuyuki Bulletin of the Seismological Society of America, Vol. 108, Issue 2 https://doi.org/10.1785/0120170085	journal	January 2018
Event Detection Performance of the PLUM Earthquake Early Warning Algorithm in Southern California Cochran, Elizabeth S.; Bunn, Julian; Minson, Sarah E. Bulletin of the Seismological Society of America, Vol. 109, Issue 4 https://doi.org/10.1785/0120180326	journal	June 2019
ShakeAlert Earthquake Early Warning System Performance during the 2019 Ridgecrest Earthquake Sequence Chung, Angela I.; Meier, Men-Andrin; Andrews, Jennifer Bulletin of the Seismological Society of America, Vol. 110, Issue 4 https://doi.org/10.1785/0120200032	journal	July 2020
Generation and Validation of Broadband Synthetic P Waves in Semistochastic Models of Large Earthquakes Goldberg, Dara E.; Melgar, Diego Bulletin of the Seismological Society of America, Vol. 110, Issue 4 https://doi.org/10.1785/0120200049	journal	July 2020
Regional-Scale 3D Ground-Motion Simulations of Mw 7 Earthquakes on the Hayward Fault, Northern California Resolving Frequencies 0–10 Hz and Including Site-Response Corrections Rodgers, Arthur J.; Pitarka, Arben; Pankajakshan, Ramesh Bulletin of the Seismological Society of America, Vol. 110, Issue 6 https://doi.org/10.1785/0120200147	journal	August 2020
The Impact of 3D Finite-Fault Information on Ground-Motion Forecasting for Earthquake Early Warning Murray, Jessica R.; Thompson, Eric M.; Baltay, Annemarie S. Bulletin of the Seismological Society of America, Vol. 112, Issue 2 https://doi.org/10.1785/0120210162	journal	November 2021
Refinements to the Graves and Pitarka (2010) Broadband Ground-Motion Simulation Method Graves, R.; Pitarka, A. Seismological Research Letters, Vol. 86, Issue 1 https://doi.org/10.1785/0220140101	journal	December 2014
Demonstration of the Cascadia G‐FAST Geodetic Earthquake Early Warning System for the Nisqually, Washington, Earthquake Crowell, Brendan W.; Schmidt, David A.; Bodin, Paul Seismological Research Letters, Vol. 87, Issue 4 https://doi.org/10.1785/0220150255	journal	June 2016
The Chilean GNSS Network: Current Status and Progress toward Early Warning Applications Báez, J. C.; Leyton, F.; Troncoso, C. Seismological Research Letters, Vol. 89, Issue 4 https://doi.org/10.1785/0220180011	journal	April 2018
Development of a Geodetic Component for the U.S. West Coast Earthquake Early Warning System Murray, J. R.; Crowell, B. W.; Grapenthin, R. Seismological Research Letters, Vol. 89, Issue 6 https://doi.org/10.1785/0220180162	journal	October 2018
An Investigation of Rapid Earthquake Characterization Using Single‐Station Waveforms and a Convolutional Neural Network Lomax, Anthony; Michelini, Alberto; Jozinović, Dario Seismological Research Letters, Vol. 90, Issue 2A https://doi.org/10.1785/0220180311	journal	February 2019
New empirical relationships among magnitude, rupture length, rupture width, rupture area, and surface displacement Wells, Donald L.; Coppersmith, Kevin J. Bulletin of the Seismological Society of America, Vol. 84, Issue 4, p. 974-1002 https://doi.org/10.1785/bssa0840040974	journal	August 1994
Mexico City Seismic Alert System Aranda, J. M. E.; Jimenez, A.; Ibarrola, G. Seismological Research Letters, Vol. 66, Issue 6 https://doi.org/10.1785/gssrl.66.6.42	journal	November 1995
Evolution of the Mexican Seismic Alert System (SASMEX) Espinosa-Aranda, J. M.; Cuellar, A.; Garcia, A. Seismological Research Letters, Vol. 80, Issue 5 https://doi.org/10.1785/gssrl.80.5.694	journal	September 2009
Earthquake Early Warning in Japan: Warning the General Public and Future Prospects Kamigaichi, O.; Saito, M.; Doi, K. Seismological Research Letters, Vol. 80, Issue 5 https://doi.org/10.1785/gssrl.80.5.717	journal	September 2009
The Impact of the Three-Dimensional Structure of a Subduction Zone on Time-dependent Crustal Deformation Measured by HR-GNSS Fadugba, Oluwaseun Idowu; Sahakian, Valerie J.; Melgar, Diego https://doi.org/10.31223/X5PD5N	preprint	June 2023
Outline of the 2011 off the Pacific coast of Tohoku Earthquake (M w 9.0) —Earthquake Early Warning and observed seismic intensity— Hoshiba, Mitsuyuki; Iwakiri, Kazuhiro; Hayashimoto, Naoki Earth, Planets and Space, Vol. 63, Issue 7 https://doi.org/10.5047/eps.2011.05.031	journal	May 2011

Similar Records

Instantaneous tracking of earthquake growth with elastogravity signals

Journal Article · Wed May 11 00:00:00 EDT 2022 · Nature (London) · OSTI ID:2310321

Development of earthquake early warning system using real time signal of broadband seismogram

Journal Article · Wed Jun 20 00:00:00 EDT 2012 · AIP Conference Proceedings · OSTI ID:22068971

A machine learning estimator trained on synthetic data for real-time earthquake ground-shaking predictions in Southern California

Journal Article · Thu May 16 00:00:00 EDT 2024 · Communications Earth & Environment · OSTI ID:2581921

Related Subjects

58 GEOSCIENCES
GNSS
deep learning
earthquake early warning
fault tracking
ground motion prediction
rupture simulation

Real-Time Fault Tracking and Ground Motion Prediction for Large Earthquakes With HR-GNSS and Deep Learning

Citation Formats

References (61)

Similar Records

Related Subjects