Application of machine learning techniques to predict rupture propagation and arrest in 2-D dynamic earthquake simulations

SUMMARY Simulating dynamic earthquake rupture propagation is challenging due to uncertainties in the underlying physics of fault slip, stress conditions and the fault frictional properties. A trial and error approach is often used to determine the unknown parameters describing rupture, though runnin...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Geophysical journal international Ročník 224; číslo 3; s. 1918 - 1929
Hlavní autoři: Ahamed, Sabber, Daub, Eric G
Médium: Journal Article
Jazyk:angličtina
Vydáno: Oxford University Press 01.03.2021
Témata:
ISSN:0956-540X, 1365-246X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract SUMMARY Simulating dynamic earthquake rupture propagation is challenging due to uncertainties in the underlying physics of fault slip, stress conditions and the fault frictional properties. A trial and error approach is often used to determine the unknown parameters describing rupture, though running many simulations usually requires human review to determine how to adjust parameter values and is thus inefficient. We leverage machine learning approaches to reduce computational cost and improve the ability to determine reasonable stress and friction parameters. Two models have been developed using neural networks and the random forest to predict if a rupture can break 2-D geometrically complex fault. We train the models using a database of 1600 dynamic rupture simulations computed numerically. Fault geometry, stress conditions and friction parameters vary in each simulation. Both models distinguish the underlying complex data patterns that reflect the physics of the rupture. For example, our models identify in a quantitative fashion, how higher normal and shear stress components and low static and dynamic friction can be tied to the probability of rupture propagation. Both models are efficient in predicting rupture propagation such that 400 unseen examples are predicted in a fraction of a second, leading to potential applications of dynamic rupture that have previously not been possible due to the computational demands of physics-based rupture simulations.
AbstractList SUMMARY Simulating dynamic earthquake rupture propagation is challenging due to uncertainties in the underlying physics of fault slip, stress conditions and the fault frictional properties. A trial and error approach is often used to determine the unknown parameters describing rupture, though running many simulations usually requires human review to determine how to adjust parameter values and is thus inefficient. We leverage machine learning approaches to reduce computational cost and improve the ability to determine reasonable stress and friction parameters. Two models have been developed using neural networks and the random forest to predict if a rupture can break 2-D geometrically complex fault. We train the models using a database of 1600 dynamic rupture simulations computed numerically. Fault geometry, stress conditions and friction parameters vary in each simulation. Both models distinguish the underlying complex data patterns that reflect the physics of the rupture. For example, our models identify in a quantitative fashion, how higher normal and shear stress components and low static and dynamic friction can be tied to the probability of rupture propagation. Both models are efficient in predicting rupture propagation such that 400 unseen examples are predicted in a fraction of a second, leading to potential applications of dynamic rupture that have previously not been possible due to the computational demands of physics-based rupture simulations.
Simulating dynamic earthquake rupture propagation is challenging due to uncertainties in the underlying physics of fault slip, stress conditions and the fault frictional properties. A trial and error approach is often used to determine the unknown parameters describing rupture, though running many simulations usually requires human review to determine how to adjust parameter values and is thus inefficient. We leverage machine learning approaches to reduce computational cost and improve the ability to determine reasonable stress and friction parameters. Two models have been developed using neural networks and the random forest to predict if a rupture can break 2-D geometrically complex fault. We train the models using a database of 1600 dynamic rupture simulations computed numerically. Fault geometry, stress conditions and friction parameters vary in each simulation. Both models distinguish the underlying complex data patterns that reflect the physics of the rupture. For example, our models identify in a quantitative fashion, how higher normal and shear stress components and low static and dynamic friction can be tied to the probability of rupture propagation. Both models are efficient in predicting rupture propagation such that 400 unseen examples are predicted in a fraction of a second, leading to potential applications of dynamic rupture that have previously not been possible due to the computational demands of physics-based rupture simulations.
Author Ahamed, Sabber
Daub, Eric G
Author_xml – sequence: 1
  givenname: Sabber
  surname: Ahamed
  fullname: Ahamed, Sabber
  email: sabbers@gmail.com
– sequence: 2
  givenname: Eric G
  surname: Daub
  fullname: Daub, Eric G
BookMark eNp9kDtPwzAUhS1UJNrCxB_wxIICduI8PFblKVViAalbdOPYqUtip7YzlF9PaDshwXR1pHM-XX0zNDHWSISuKbmjhCf3zVbfNw1AyvIzNKVJlkYxy9YTNCU8zaKUkfUFmnm_JYQyyoop-lr0fasFBG0Ntgp3IDbaSNxKcEabBgcpNkbvBulxsLh3stYiYDf0YXByzLaH5rgGU2NwTvqAtcFx9IDrvYFOCzyywmY3wKfEXndDe-j7S3SuoPXy6nTn6OPp8X35Eq3enl-Xi1UEcZGHCCjlCed5XcQVSypWyCSDuI5FrUSuUlCiyhUhqsqByhSooEQUKlUxY5JzxZM5uj1yhbPeO6nK3ukO3L6kpPzRVo7aypO2sU1_tYUOh4eDA93-sbk5buzQ_wv_BnqvhcI
CitedBy_id crossref_primary_10_1029_2024JB030069
crossref_primary_10_1029_2024JB030278
crossref_primary_10_1016_j_engappai_2023_105856
Cites_doi 10.1029/2018JB016214
10.1029/2006JB004443
10.1007/s10462-009-9124-7
10.1111/j.1365-246X.2005.02769.x
10.1029/2001GL012869
10.1038/323533a0
10.1146/annurev.ea.06.050178.002201
10.1029/1999GL900377
10.1038/35016072
10.1016/S0012-821X(03)00424-2
10.1029/2008JB006174
10.1146/annurev.earth.26.1.643
10.1002/2017GL074677
10.1190/tle36030208.1
10.1016/j.tecto.2010.06.015
10.1002/2015GL063802
10.1002/2014JB011595
10.2307/2291432
10.1029/2008GL036832
10.1029/2000JB900241
10.1785/BSSA0870010061
10.1109/MCAS.2006.1688199
10.1029/98JB01576
10.1111/j.1365-246X.2005.02579.x
10.1023/A:1010933404324
10.1613/jair.614
10.1111/j.1365-246X.1977.tb01339.x
10.1785/0120070076
10.1371/journal.pone.0146101
10.1002/2015JB012512
10.1029/2002JB002189
10.1029/2007JB005027
10.1029/JB081i020p03575
10.1007/BF00058655
10.1126/sciadv.1700578
10.1023/A:1007607513941
10.1029/2001JB000205
10.1029/2008JB006271
10.1002/2016GL071700
10.1007/BF00116251
10.1037/h0042519
10.1029/95JB01460
10.1785/0120170293
10.1007/s00024-010-0161-6
ContentType Journal Article
Copyright The Author(s) 2020. Published by Oxford University Press on behalf of The Royal Astronomical Society. 2021
Copyright_xml – notice: The Author(s) 2020. Published by Oxford University Press on behalf of The Royal Astronomical Society. 2021
DBID AAYXX
CITATION
DOI 10.1093/gji/ggaa547
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Physics
EISSN 1365-246X
EndPage 1929
ExternalDocumentID 10_1093_gji_ggaa547
10.1093/gji/ggaa547
GroupedDBID -~X
.2P
.3N
.GA
.I3
.Y3
0R~
10A
1OC
1TH
29H
31~
4.4
48X
51W
51X
52M
52N
52O
52P
52S
52T
52W
52X
5GY
5HH
5LA
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8UM
AAHHS
AAIJN
AAJKP
AAJQQ
AAKDD
AAMVS
AAOGV
AAPQZ
AAPXW
AARHZ
AAUQX
AAVAP
ABAZT
ABCQN
ABEJV
ABEML
ABEUO
ABGNP
ABIXL
ABNGD
ABNKS
ABPTD
ABQLI
ABSMQ
ABTAH
ABXVV
ABZBJ
ACCFJ
ACFRR
ACGFS
ACSCC
ACUFI
ACUKT
ACUTJ
ACUXJ
ACXQS
ACYTK
ADEYI
ADGZP
ADHKW
ADHZD
ADOCK
ADQBN
ADRDM
ADRTK
ADVEK
ADYVW
ADZOD
ADZXQ
AECKG
AEEZP
AEGPL
AEJOX
AEKKA
AEKSI
AEMDU
AENEX
AENZO
AEPUE
AEQDE
AETBJ
AEWNT
AFBPY
AFEBI
AFFZL
AFIYH
AFOFC
AFZJQ
AGINJ
AGKRT
AGSYK
AHEFC
AHXPO
AI.
AIWBW
AJAOE
AJBDE
AJEEA
AJEUX
ALMA_UNASSIGNED_HOLDINGS
ALTZX
ALUQC
ALXQX
AMNDL
ANAKG
APIBT
APJGH
ASAOO
ATDFG
AXUDD
AZFZN
AZVOD
BAYMD
BEFXN
BEYMZ
BFFAM
BFHJK
BGNUA
BHONS
BKEBE
BPEOZ
BQUQU
BTQHN
BY8
CAG
CDBKE
COF
CS3
CXTWN
D-E
D-F
DAKXR
DC6
DCZOG
DFGAJ
DILTD
DR2
D~K
EBS
EE~
EJD
F00
F04
F9B
FA8
FEDTE
FLIZI
FLUFQ
FOEOM
FRJ
FZ0
GAUVT
GJXCC
GROUPED_DOAJ
H13
H5~
HAR
HF~
HOLLA
HVGLF
HW0
HZI
HZ~
IHE
IX1
J21
JAVBF
JXSIZ
K48
KBUDW
KOP
KQ8
KSI
KSN
LC2
LC3
LH4
LP6
LP7
LW6
M49
MBTAY
MK4
N9A
NGC
NMDNZ
NOMLY
O0~
O9-
OCL
ODMLO
OIG
OJQWA
O~Y
P2P
P2X
P4D
PAFKI
PB-
PEELM
Q1.
Q11
Q5Y
QB0
ROL
ROZ
RUSNO
RW1
RX1
RXO
TJP
TOX
UB1
VH1
VOH
W8V
W99
WQJ
WYUIH
XG1
YAYTL
YKOAZ
YXANX
ZCG
ZY4
ZZE
~02
AAYXX
ABVLG
AHGBF
CITATION
ROX
ID FETCH-LOGICAL-a287t-a1193997d82b43b48e36a2d2cdfc7f5afcb7f00fb7a1e5a1c10c8f5f244e99f93
IEDL.DBID TOX
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000606573600027&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0956-540X
IngestDate Sat Nov 29 05:20:48 EST 2025
Tue Nov 18 22:15:54 EST 2025
Wed Apr 02 07:04:34 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 3
Keywords Earthquake ground motions
Numerical modelling
Earthquake dynamics
Machine learning
Language English
License This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model)
https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a287t-a1193997d82b43b48e36a2d2cdfc7f5afcb7f00fb7a1e5a1c10c8f5f244e99f93
PageCount 12
ParticipantIDs crossref_primary_10_1093_gji_ggaa547
crossref_citationtrail_10_1093_gji_ggaa547
oup_primary_10_1093_gji_ggaa547
PublicationCentury 2000
PublicationDate 2021-03-01
PublicationDateYYYYMMDD 2021-03-01
PublicationDate_xml – month: 03
  year: 2021
  text: 2021-03-01
  day: 01
PublicationDecade 2020
PublicationTitle Geophysical journal international
PublicationYear 2021
Publisher Oxford University Press
Publisher_xml – name: Oxford University Press
References Kohlstedt (2021111807272471700_bib32) 1995; 100
Aslam (2021111807272471700_bib5) 2018; 123
Breiman (2021111807272471700_bib8) 1996; 24
Hahnloser (2021111807272471700_bib24) 2000; 405
Daub (2021111807272471700_bib16) 2017
Lawrence (2021111807272471700_bib35) 1997
Rouet-Leduc (2021111807272471700_bib53) 2017; 44
Das (2021111807272471700_bib15) 1977; 50
Chester (2021111807272471700_bib13) 2000; 105
Polikar (2021111807272471700_bib48) 2006; 6
Gal (2021111807272471700_bib22) 2016
Lawrence (2021111807272471700_bib34) 2000
Mullachery (2021111807272471700_bib40) 2018
Saffer (2021111807272471700_bib57) 2001; 28
Zielke (2021111807272471700_bib60) 2017; 44
Harris (2021111807272471700_bib26) 1999; 26
Douilly (2021111807272471700_bib19) 2015; 120
Rumelhart (2021111807272471700_bib54) 1986; 323
Bhat (2021111807272471700_bib6) 2007; 112
Last (2021111807272471700_bib33) 2016; 11
Rumelhart (2021111807272471700_bib55) 1988; 323
Warren (2021111807272471700_bib59) 2006; 164
Olsen (2021111807272471700_bib42) 2009; 36
Bruhat (2021111807272471700_bib10) 2016; 121
Perol (2021111807272471700_bib46) 2018; 4
Chen (2021111807272471700_bib12) 2004
Kame (2021111807272471700_bib28) 2003; 108
Templeton (2021111807272471700_bib58) 2009; 114
Bouchon (2021111807272471700_bib7) 1997; 87
Duan (2021111807272471700_bib20) 2006; 111
Hinton (2021111807272471700_bib27) 2012
Pedregosa (2021111807272471700_bib45) 2011; 12
Quinlan (2021111807272471700_bib49) 1986; 1
Harris (2021111807272471700_bib25) 1998; 103
Paolucci (2021111807272471700_bib44) 2018; 108
Saffer (2021111807272471700_bib56) 2003; 215
Ripperger (2021111807272471700_bib50) 2008; 98
Rosenblatt (2021111807272471700_bib52) 1958; 65
de la Puente (2021111807272471700_bib17) 2009; 114
Chollet (2021111807272471700_bib14) 2015
Ohnaka (2021111807272471700_bib41) 1986
Duan (2021111807272471700_bib21) 2007; 112
Dietterich (2021111807272471700_bib18) 2000; 40
Rokach (2021111807272471700_bib51) 2010; 33
Breiman (2021111807272471700_bib9) 2001; 45
Graves (2021111807272471700_bib23) 2011; 168
Zoback (2021111807272471700_bib61) 2010
Michie (2021111807272471700_bib39) 1996; 91
Andrews (2021111807272471700_bib3) 1976; 81
Kingma (2021111807272471700_bib31) 2014
Kaneko (2021111807272471700_bib30) 2010; 493
Marone (2021111807272471700_bib37) 1998; 26
Lozos (2021111807272471700_bib36) 2015; 42
Peyrat (2021111807272471700_bib47) 2001; 106
Araya-Polo (2021111807272471700_bib4) 2017
Abercrombie (2021111807272471700_bib1) 2005; 162
Opitz (2021111807272471700_bib43) 1999; 11
Carbonell (2021111807272471700_bib11) 1983
Kanamori (2021111807272471700_bib29) 1993; 83
McGarr (2021111807272471700_bib38) 1978; 6
References_xml – volume: 111
  issue: 5
  year: 2006
  ident: 2021111807272471700_bib20
  article-title: Heterogeneous fault stresses from previous earthquakes and the effect on dynamics of parallel strike-slip faults
  publication-title: J. geophys. Res.
– volume: 123
  start-page: 9689
  issue: 11
  year: 2018
  ident: 2021111807272471700_bib5
  article-title: Effect of fault roughness on aftershock distribution: elastic off-fault material properties
  publication-title: J. geophys. Res.
  doi: 10.1029/2018JB016214
– volume: 112
  issue: B5
  year: 2007
  ident: 2021111807272471700_bib21
  article-title: Nonuniform prestress from prior earthquakes and the effect on dynamics of branched fault systems
  publication-title: J. geophys. Res.
  doi: 10.1029/2006JB004443
– volume: 33
  start-page: 1
  issue: 1
  year: 2010
  ident: 2021111807272471700_bib51
  article-title: Ensemble-based classifiers
  publication-title: Artif. Intell. Rev.
  doi: 10.1007/s10462-009-9124-7
– volume: 164
  start-page: 46
  issue: 1
  year: 2006
  ident: 2021111807272471700_bib59
  article-title: Systematic determination of earthquake rupture directivity and fault planes from analysis of long-period P-wave spectra
  publication-title: Geophys. J. Int.
  doi: 10.1111/j.1365-246X.2005.02769.x
– volume: 28
  start-page: 2297
  issue: 15
  year: 2001
  ident: 2021111807272471700_bib57
  article-title: Laboratory results indicating complex and potentially unstable frictional behavior of smectite clay
  publication-title: Geophys. Res. Lett.
  doi: 10.1029/2001GL012869
– volume: 323
  start-page: 533
  issue: 6088
  year: 1986
  ident: 2021111807272471700_bib54
  article-title: Learning representations by back-propagating errors
  publication-title: Nature
  doi: 10.1038/323533a0
– volume: 6
  start-page: 405
  issue: 1
  year: 1978
  ident: 2021111807272471700_bib38
  article-title: State of stress in the Earth’s crust
  publication-title: Annu. Rev. Earth Planet. Sci.
  doi: 10.1146/annurev.ea.06.050178.002201
– volume: 26
  start-page: 2089
  issue: 14
  year: 1999
  ident: 2021111807272471700_bib26
  article-title: Dynamic 3D simulations of earthquakes on en echelon faults
  publication-title: Geophys. Res. Lett.
  doi: 10.1029/1999GL900377
– volume: 405
  start-page: 947
  issue: 6789
  year: 2000
  ident: 2021111807272471700_bib24
  article-title: Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit
  publication-title: Nature
  doi: 10.1038/35016072
– year: 2016
  ident: 2021111807272471700_bib22
  publication-title: Uncertainty in Deep Learning
– start-page: 3
  volume-title: Machine Learning
  year: 1983
  ident: 2021111807272471700_bib11
  article-title: An overview of machine learning
– volume: 12
  start-page: 2825
  year: 2011
  ident: 2021111807272471700_bib45
  article-title: Scikit-learn: machine learning in Python
  publication-title: J. Mach. Learn. Res.
– volume: 215
  start-page: 219
  issue: 1
  year: 2003
  ident: 2021111807272471700_bib56
  article-title: Comparison of smectite-and illite-rich gouge frictional properties: application to the updip limit of the seismogenic zone along subduction megathrusts
  publication-title: Earth planet. Sci. Lett.
  doi: 10.1016/S0012-821X(03)00424-2
– start-page: 540
  year: 1997
  ident: 2021111807272471700_bib35
  article-title: Lessons in neural network training: overfitting may be harder than expected
– volume: 83
  start-page: 330
  issue: 2
  year: 1993
  ident: 2021111807272471700_bib29
  article-title: Determination of earthquake energy release and ML using TERRAscope
  publication-title: Bull. seism. Soc. Am.
– volume: 114
  issue: B8
  year: 2009
  ident: 2021111807272471700_bib58
  article-title: Finite element simulations of dynamic shear rupture experiments and dynamic path selection along kinked and branched faults
  publication-title: J. geophys. Res.
  doi: 10.1029/2008JB006174
– volume: 26
  start-page: 643
  issue: 1
  year: 1998
  ident: 2021111807272471700_bib37
  article-title: Laboratory-derived friction laws and their application to seismic faulting
  publication-title: Annu. Rev. Earth Planet. Sci.
  doi: 10.1146/annurev.earth.26.1.643
– start-page: 13
  volume-title: Earthquake Source Mechanics
  year: 1986
  ident: 2021111807272471700_bib41
  article-title: Dynamic breakdown processes and the generating mechanism for high-frequency elastic radiation during stick-slip instabilities
– volume: 44
  start-page: 9276
  year: 2017
  ident: 2021111807272471700_bib53
  article-title: Machine learning predicts laboratory earthquakes
  publication-title: Geophys. Res. Lett.
  doi: 10.1002/2017GL074677
– year: 2012
  ident: 2021111807272471700_bib27
  article-title: Improving neural networks by preventing co-adaptation of feature detectors
– year: 2017
  ident: 2021111807272471700_bib4
  article-title: Automated fault detection without seismic processing
  publication-title: Leading Edge
  doi: 10.1190/tle36030208.1
– volume: 493
  start-page: 272
  issue: 3–4
  year: 2010
  ident: 2021111807272471700_bib30
  article-title: Supershear transition due to a free surface in 3D simulations of spontaneous dynamic rupture on vertical strike-slip faults
  publication-title: Tectonophysics
  doi: 10.1016/j.tecto.2010.06.015
– volume: 42
  start-page: 4343
  issue: 11
  year: 2015
  ident: 2021111807272471700_bib36
  article-title: Dynamic rupture models of earthquakes on the Bartlett Springs Fault, Northern California
  publication-title: Geophys. Res. Lett.
  doi: 10.1002/2015GL063802
– volume: 120
  start-page: 1108
  year: 2015
  ident: 2021111807272471700_bib19
  article-title: 3D dynamic rupture simulations across interacting faults: the Mw 7.0, 2010, Haiti earthquake
  publication-title: J. geophys. Res.
  doi: 10.1002/2014JB011595
– start-page: 114
  volume-title: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000
  year: 2000
  ident: 2021111807272471700_bib34
  article-title: Overfitting and neural networks: conjugate gradient and backpropagation
– volume: 91
  start-page: 436
  issue: 433
  year: 1996
  ident: 2021111807272471700_bib39
  article-title: Machine learning, neural and statistical classification
  publication-title: J. Am. Stat. Assoc.
  doi: 10.2307/2291432
– volume: 36
  issue: 4
  year: 2009
  ident: 2021111807272471700_bib42
  article-title: Shakeout: ground motion estimates using an ensemble of large earthquakes on the southern San Andreas fault with spontaneous rupture propagation
  publication-title: Geophys. Res. Lett.
  doi: 10.1029/2008GL036832
– volume: 105
  start-page: 23 421
  issue: B10
  year: 2000
  ident: 2021111807272471700_bib13
  article-title: Stress and deformation along wavy frictional faults
  publication-title: J. geophys. Res.
  doi: 10.1029/2000JB900241
– volume: 87
  start-page: 61
  issue: 1
  year: 1997
  ident: 2021111807272471700_bib7
  article-title: Propagation of a shear crack on a nonplanar fault: a method of calculation
  publication-title: Bull. seism. Soc. Am.
  doi: 10.1785/BSSA0870010061
– volume: 6
  start-page: 21
  issue: 3
  year: 2006
  ident: 2021111807272471700_bib48
  article-title: Ensemble based systems in decision making
  publication-title: IEEE Circuits Syst. Mag.
  doi: 10.1109/MCAS.2006.1688199
– volume: 103
  start-page: 24 347
  issue: B10
  year: 1998
  ident: 2021111807272471700_bib25
  article-title: Introduction to special section: stress triggers, stress shadows, and implications for seismic hazard
  publication-title: J. geophys. Res.
  doi: 10.1029/98JB01576
– volume: 162
  start-page: 406
  issue: 2
  year: 2005
  ident: 2021111807272471700_bib1
  article-title: Can observations of earthquake scaling constrain slip weakening?
  publication-title: Geophys. J. Int.
  doi: 10.1111/j.1365-246X.2005.02579.x
– volume: 45
  start-page: 5
  issue: 1
  year: 2001
  ident: 2021111807272471700_bib9
  article-title: Random forests
  publication-title: Mach. Learn.
  doi: 10.1023/A:1010933404324
– volume-title: Reservoir Geomechanics
  year: 2010
  ident: 2021111807272471700_bib61
– volume: 11
  start-page: 169
  year: 1999
  ident: 2021111807272471700_bib43
  article-title: Popular ensemble methods: An empirical study
  publication-title: J. Artif. Intell. Res.(JAIR)
  doi: 10.1613/jair.614
– volume: 50
  start-page: 643
  issue: 3
  year: 1977
  ident: 2021111807272471700_bib15
  article-title: A numerical study of two-dimensional spontaneous rupture propagation
  publication-title: Geophys. J. Int.
  doi: 10.1111/j.1365-246X.1977.tb01339.x
– volume: 98
  start-page: 1207
  issue: 3
  year: 2008
  ident: 2021111807272471700_bib50
  article-title: Variability of near-field ground motion from dynamic earthquake rupture simulations
  publication-title: Bull. seism. Soc. Am.
  doi: 10.1785/0120070076
– volume: 11
  start-page: e0146101
  issue: 1
  year: 2016
  ident: 2021111807272471700_bib33
  article-title: Predicting the maximum earthquake magnitude from seismic data in Israel and its neighboring countries
  publication-title: PloS One
  doi: 10.1371/journal.pone.0146101
– volume: 121
  start-page: 210
  issue: 1
  year: 2016
  ident: 2021111807272471700_bib10
  article-title: Rupture complexity and the supershear transition on rough faults
  publication-title: J. geophys. Res.
  doi: 10.1002/2015JB012512
– volume: 108
  issue: B5
  year: 2003
  ident: 2021111807272471700_bib28
  article-title: Effects of prestress state and rupture velocity on dynamic fault branching
  publication-title: J. geophys. Res.
  doi: 10.1029/2002JB002189
– volume: 112
  issue: B11
  year: 2007
  ident: 2021111807272471700_bib6
  article-title: Role of fault branches in earthquake rupture dynamics
  publication-title: J. geophys. Res.
  doi: 10.1029/2007JB005027
– year: 2014
  ident: 2021111807272471700_bib31
  article-title: Adam: a method for stochastic optimization
– volume: 81
  start-page: 3575
  issue: 20
  year: 1976
  ident: 2021111807272471700_bib3
  article-title: Rupture propagation with finite stress in antiplane strain
  publication-title: J. geophys. Res.
  doi: 10.1029/JB081i020p03575
– volume: 24
  start-page: 123
  issue: 2
  year: 1996
  ident: 2021111807272471700_bib8
  article-title: Bagging predictors
  publication-title: Machi. Learn.
  doi: 10.1007/BF00058655
– volume: 4
  start-page: e1700578
  issue: 2
  year: 2018
  ident: 2021111807272471700_bib46
  article-title: Convolutional neural network for earthquake detection and location
  publication-title: Sci. Adv.
  doi: 10.1126/sciadv.1700578
– volume: 40
  start-page: 139
  issue: 2
  year: 2000
  ident: 2021111807272471700_bib18
  article-title: An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization
  publication-title: Mach. Learn.
  doi: 10.1023/A:1007607513941
– volume: 106
  start-page: 26467
  issue: B11
  year: 2001
  ident: 2021111807272471700_bib47
  article-title: Dynamic modeling of the 1992 Landers earthquake
  publication-title: J. geophys. Res.
  doi: 10.1029/2001JB000205
– volume: 114
  issue: B10
  year: 2009
  ident: 2021111807272471700_bib17
  article-title: Dynamic rupture modeling on unstructured meshes using a discontinuous Galerkin method
  publication-title: J. geophys. Res.
  doi: 10.1029/2008JB006271
– volume: 44
  start-page: 777
  issue: 2
  year: 2017
  ident: 2021111807272471700_bib60
  article-title: Fault roughness and strength heterogeneity control earthquake size and stress drop
  publication-title: Geophys. Res. Lett.
  doi: 10.1002/2016GL071700
– volume: 1
  start-page: 81
  issue: 1
  year: 1986
  ident: 2021111807272471700_bib49
  article-title: Induction of decision trees
  publication-title: Mach. Learn.
  doi: 10.1007/BF00116251
– volume: 323
  start-page: 533
  issue: 6088
  year: 1988
  ident: 2021111807272471700_bib55
  article-title: Learning representations by back-propagating errors
  publication-title: Nature
  doi: 10.1038/323533a0
– year: 2017
  ident: 2021111807272471700_bib16
  article-title: ‘Finite difference code for earthquake faulting’
– year: 2015
  ident: 2021111807272471700_bib14
  article-title: Keras: Deep learning library for theano and tensorflow
– volume: 65
  start-page: 386
  issue: 6
  year: 1958
  ident: 2021111807272471700_bib52
  article-title: The perceptron: a probabilistic model for information storage and organization in the brain
  publication-title: Psychol. Rev.
  doi: 10.1037/h0042519
– year: 2018
  ident: 2021111807272471700_bib40
  article-title: Bayesian Neural Networks
– volume: 100
  start-page: 17 587
  issue: B9
  year: 1995
  ident: 2021111807272471700_bib32
  article-title: Strength of the lithosphere: constraints imposed by laboratory experiments
  publication-title: J. geophys. Res.
  doi: 10.1029/95JB01460
– volume: 108
  start-page: 1272
  issue: 3A
  year: 2018
  ident: 2021111807272471700_bib44
  article-title: Broadband ground motions from 3D physics-based numerical simulations using artificial neural networks
  publication-title: Bull. seism. Soc. Am.
  doi: 10.1785/0120170293
– volume: 168
  start-page: 367
  issue: 3–4
  year: 2011
  ident: 2021111807272471700_bib23
  article-title: Cybershake: a physics-based seismic hazard model for southern California
  publication-title: Pure appl. Geophys.
  doi: 10.1007/s00024-010-0161-6
– year: 2004
  ident: 2021111807272471700_bib12
  article-title: Using Random Forest to Learn Imbalanced Data
SSID ssj0014148
Score 2.363124
Snippet SUMMARY Simulating dynamic earthquake rupture propagation is challenging due to uncertainties in the underlying physics of fault slip, stress conditions and...
Simulating dynamic earthquake rupture propagation is challenging due to uncertainties in the underlying physics of fault slip, stress conditions and the fault...
SourceID crossref
oup
SourceType Enrichment Source
Index Database
Publisher
StartPage 1918
Title Application of machine learning techniques to predict rupture propagation and arrest in 2-D dynamic earthquake simulations
Volume 224
WOSCitedRecordID wos000606573600027&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVASL
  databaseName: Oxford Journals Open Access Collection
  customDbUrl:
  eissn: 1365-246X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014148
  issn: 0956-540X
  databaseCode: TOX
  dateStart: 19880101
  isFulltext: true
  titleUrlDefault: https://academic.oup.com/journals/
  providerName: Oxford University Press
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3LSsQwFA0iCm58i-Mzi1kJZZqmaZrloA4uZHQxSnclzaNWnc7Ydlz49SZtHR8M6rJwE8pN4N5wzj0HgK4mpgnnlDtUBcTxVRA4PKHS8RgRCKOEonqQ9v6aDodhFLHbliBbLoDwGe6lj1kvTTknvh0aRyS013l0E83BAh_VJlm1pJ5pQKJ2DO_H2m-Fxw6zfakjg43__sEmWG87RdhvjnYLLKl8G6zWjE1R7oC3_if0DCcajmtWpIKtDUQK5-qsJawmcFpYRKaCxWxqMQPzbV7LabOa5xLy2qQDZjn0nAsoG596aPaqHl5m_EnBMhu3Tl_lLrgbXI7Or5zWSMHh5kFUORyZNo0xKkMv8XHihwoH3JOekFpQTbgWCdWuqxPKkSIcCeSKUBNtSr9iTDO8B5bzSa72AQyxZNzFBDNf-NIqBUnXNxu4CQsZkl4HnH1kORatyrg1u3iOG7QbxyaZcZvMDujOg6eNuMbisFNzXL9FHPwZcQjWPMtGqdljR2C5KmbqGKyI1yori5P6Pr0DpTrLVg
linkProvider Oxford University Press
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Application+of+machine+learning+techniques+to+predict+rupture+propagation+and+arrest+in+2-D+dynamic+earthquake+simulations&rft.jtitle=Geophysical+journal+international&rft.au=Ahamed%2C+Sabber&rft.au=Daub%2C+Eric+G&rft.date=2021-03-01&rft.pub=Oxford+University+Press&rft.issn=0956-540X&rft.eissn=1365-246X&rft.volume=224&rft.issue=3&rft.spage=1918&rft.epage=1929&rft_id=info:doi/10.1093%2Fgji%2Fggaa547&rft.externalDocID=10.1093%2Fgji%2Fggaa547
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0956-540X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0956-540X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0956-540X&client=summon