Physics-informed neural networks for heterogeneous poroelastic media

This study presents a novel physics-informed neural network (PINN) framework for modeling poroelasticity in heterogeneous media with material interfaces. The approach introduces a composite neural network (CoNN) where separate neural networks predict displacement and pressure variables for each mate...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computational methods in engineering science and mechanics Vol. 26; no. 2; pp. 187 - 207
Main Authors: Roy, Sumanta, Annavarapu, Chandrasekhar, Roy, Pratanu, Valiveti, Dakshina M.
Format: Journal Article
Language:English
Published: United States Taylor & Francis 04.03.2025
Subjects:
ISSN:1550-2287, 1550-2295
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract This study presents a novel physics-informed neural network (PINN) framework for modeling poroelasticity in heterogeneous media with material interfaces. The approach introduces a composite neural network (CoNN) where separate neural networks predict displacement and pressure variables for each material. While sharing identical activation functions, these networks are independently trained for all other parameters. To address challenges posed by heterogeneous material interfaces, the CoNN is integrated with the Interface-PINNs (I-PINNs) framework (Sarma et al., Comput. Methods Appl. Mech. Eng. 429: 117135, 2024), allowing different activation functions across material interfaces. This ensures accurate approximation of discontinuous solution fields and gradients. Performance and accuracy of this combined architecture were evaluated against the conventional PINNs approach, a single neural network (SNN) architecture, and the eXtended PINNs (XPINNs) framework through two one-dimensional benchmark examples with discontinuous material properties. The results show that the proposed CoNN with I-PINNs architecture achieves an RMSE that is two orders of magnitude better than the conventional PINNs approach and is at least 40 times faster than the SNN framework. Compared to XPINNs, the proposed method achieves an RMSE at least one order of magnitude better and is 40% faster.
AbstractList This study presents a novel physics-informed neural network (PINN) framework for modeling poroelasticity in heterogeneous media with material interfaces. The approach introduces a composite neural network (CoNN) where separate neural networks predict displacement and pressure variables for each material. While sharing identical activation functions, these networks are independently trained for all other parameters. To address challenges posed by heterogeneous material interfaces, the CoNN is integrated with the Interface-PINNs (I-PINNs) framework (Sarma et al., Comput. Methods Appl. Mech. Eng. 429: 117135, 2024), allowing different activation functions across material interfaces. This ensures accurate approximation of discontinuous solution fields and gradients. Performance and accuracy of this combined architecture were evaluated against the conventional PINNs approach, a single neural network (SNN) architecture, and the eXtended PINNs (XPINNs) framework through two one-dimensional benchmark examples with discontinuous material properties. The results show that the proposed CoNN with I-PINNs architecture achieves an RMSE that is two orders of magnitude better than the conventional PINNs approach and is at least 40 times faster than the SNN framework. Compared to XPINNs, the proposed method achieves an RMSE at least one order of magnitude better and is 40% faster.
This study presents a novel physics-informed neural network (PINN) framework for modeling poroelasticity in heterogeneous media with material interfaces. The approach introduces a composite neural network (CoNN) where separate neural networks predict displacement and pressure variables for each material. While sharing identical activation functions, these networks are independently trained for all other parameters. To address challenges posed by heterogeneous material interfaces, the CoNN is integrated with the Interface-PINNs (I-PINNs) framework (Sarma et al., Comput. Methods Appl. Mech. Eng. 429: 117135, 2024), allowing different activation functions across material interfaces. Further, this ensures accurate approximation of discontinuous solution fields and gradients. Performance and accuracy of this combined architecture were evaluated against the conventional PINNs approach, a single neural network (SNN) architecture, and the eXtended PINNs (XPINNs) framework through two one-dimensional benchmark examples with discontinuous material properties. The results show that the proposed CoNN with I-PINNs architecture achieves an RMSE that is two orders of magnitude better than the conventional PINNs approach and is at least 40 times faster than the SNN framework. Compared to XPINNs, the proposed method achieves an RMSE at least one order of magnitude better and is 40% faster.
Author Annavarapu, Chandrasekhar
Roy, Pratanu
Roy, Sumanta
Valiveti, Dakshina M.
Author_xml – sequence: 1
  givenname: Sumanta
  surname: Roy
  fullname: Roy, Sumanta
  organization: Department of Civil Engineering, Indian Institute of Technology Madras
– sequence: 2
  givenname: Chandrasekhar
  surname: Annavarapu
  fullname: Annavarapu, Chandrasekhar
  organization: Department of Civil Engineering, Indian Institute of Technology Madras
– sequence: 3
  givenname: Pratanu
  surname: Roy
  fullname: Roy, Pratanu
  organization: Atmospheric, Earth and Energy Division, Lawrence Livermore National Laboratory
– sequence: 4
  givenname: Dakshina M.
  surname: Valiveti
  fullname: Valiveti, Dakshina M.
  organization: Engineering & Computational Physics, Energy Sciences & Research, ExxonMobil Technology and Engineering
BackLink https://www.osti.gov/servlets/purl/2556941$$D View this record in Osti.gov
BookMark eNqFkE1LAzEQhoMo2FZ_grB43zqb3Wy2eFHqJxT0oOeQzU5sdJuUJEX6703Z6sGDnmYY3ucdeMbk0DqLhJwVMC2ggYuCMaC04VMKtJrSqoKKwgEZ7e45pTN2-LM3_JiMQ3gHKGtaw4jcPC-3waiQG6udX2GXWdx42acRP53_CFk6Z0uM6N0bWnSbkK2dd9jLEI3KEmHkCTnSsg94up8T8np3-zJ_yBdP94_z60WuKpjFXMuacd1gW-oZkyWyppOKdryEline0rYrWqhlpaoOkYNuU16XnGuldKcBywk5H3pd-i2CMhHVUjlrUUVBGatnVZFCbAgp70LwqMXam5X0W1GA2PkS377EzpfY-0rc5S8u9ctonI1emv5f-mqgB48yues7EeW2d157aZUJovy74gsafYfS
CitedBy_id crossref_primary_10_1016_j_finel_2025_104373
Cites_doi 10.1016/j.cam.2021.113995
10.1016/j.cma.2021.113741
10.48550/arXiv.2210.14795
10.1016/j.aej.2021.08.064
10.1002/nag.2154
10.1016/j.ijheatmasstransfer.2023.125089
10.1016/j.enpol.2013.11.034
10.56952/ARMA-2023-0760
10.1080/15502280802225234
10.1016/j.cma.2024.116813
10.1007/s10409-021-01148-1
10.1016/j.jcp.2018.11.039
10.1016/j.jngse.2017.10.012
10.1016/j.cma.2022.114909
10.48550/arXiv.1412.6980
10.1115/1.4050542
10.2172/964517
10.2118/50939-PA
10.1007/s10483-006-1001-z
10.1364/OE.384875
10.1007/978-1-4842-4470-8_7
10.48550/arXiv.2306.12749
10.4208/cicp.OA-2020-0164
10.1126/sciadv.abk0644
10.48550/arXiv.2308.08468
10.1080/15502287.2011.636789
10.1016/j.jcp.2018.10.045
10.1007/3-540-10861-0
10.1016/j.jcp.2021.110334
10.48550/arXiv.2210.12914
10.1016/j.jcp.2024.113299
10.1063/5.0116038
10.1080/15502280590923612
10.1080/15502280701252495
10.1016/j.cma.2022.115141
10.1016/j.cma.2020.113127
10.1016/j.cma.2024.117197
10.1016/j.cma.2024.117135
10.1109/TNN.2002.1000141
10.1007/BF02818935
10.48550/arXiv.2404.13909
10.1016/j.cam.2014.05.009
10.2110/pec.87.39.0321
10.1080/15502287.2023.2186974
10.48550/arXiv.2406.04626
10.1016/j.compfluid.2022.105583
10.48550/arXiv.2010.15426
ContentType Journal Article
Copyright 2024 Taylor & Francis Group, LLC 2024
Copyright_xml – notice: 2024 Taylor & Francis Group, LLC 2024
CorporateAuthor Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
CorporateAuthor_xml – name: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
DBID AAYXX
CITATION
OIOZB
OTOTI
DOI 10.1080/15502287.2024.2440420
DatabaseName CrossRef
OSTI.GOV - Hybrid
OSTI.GOV
DatabaseTitle CrossRef
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
EISSN 1550-2295
EndPage 207
ExternalDocumentID 2556941
10_1080_15502287_2024_2440420
2440420
Genre Research Article
GrantInformation_xml – fundername: ExxonMobil Corporation to the Subsurface Mechanics and Geo-Energy Laboratory
  grantid: SP22230020CEEXXU008957
– fundername: Ministry of Education, Government of India and IIT Madras
  grantid: SB20210856CEMHRD008957
– fundername: U.S. Department of Energy by Lawrence Livermore National Laboratory
  grantid: DE-AC52-07NA27344
GroupedDBID .7F
.DC
.QJ
0BK
0R~
29J
30N
4.4
5GY
5VS
AAENE
AAGDL
AAHIA
AAJMT
AALDU
AAMIU
AAPUL
AAQRR
ABCCY
ABFIM
ABHAV
ABJNI
ABLIJ
ABPAQ
ABPEM
ABTAI
ABXUL
ABXYU
ACGEJ
ACGFS
ACTIO
ADCVX
ADGTB
ADXPE
AEISY
AEOZL
AEPSL
AEYOC
AFKVX
AFRVT
AGDLA
AGMYJ
AHDZW
AIJEM
AIYEW
AJWEG
AKBVH
AKOOK
ALMA_UNASSIGNED_HOLDINGS
ALQZU
AQRUH
AQTUD
AVBZW
AWYRJ
BLEHA
CCCUG
CE4
CS3
DGEBU
DKSSO
EBS
E~A
E~B
FPAXQ
GEVLZ
GTTXZ
H13
HF~
H~P
J.P
KYCEM
LJTGL
M4Z
NA5
RIG
RNANH
ROSJB
RTWRZ
S-T
SNACF
TASJS
TBQAZ
TDBHL
TEN
TFL
TFT
TFW
TNC
TTHFI
TUROJ
TWF
UT5
UU3
ZGOLN
~S~
AAYXX
CITATION
OIOZB
OTOTI
ID FETCH-LOGICAL-c409t-fa657f8eb3f95a3e58dac2d730b5c7b2bd1b06a4c4dee70fba65f377fccfdf0e3
IEDL.DBID TFW
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001383659200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1550-2287
IngestDate Mon Nov 03 02:25:53 EST 2025
Sat Nov 29 08:06:02 EST 2025
Tue Nov 18 21:38:08 EST 2025
Mon Oct 20 23:45:19 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c409t-fa657f8eb3f95a3e58dac2d730b5c7b2bd1b06a4c4dee70fba65f377fccfdf0e3
Notes AC52-07NA27344
USDOE National Nuclear Security Administration (NNSA)
LLNL--JRNL-860569
OpenAccessLink https://www.osti.gov/servlets/purl/2556941
PageCount 21
ParticipantIDs crossref_primary_10_1080_15502287_2024_2440420
crossref_citationtrail_10_1080_15502287_2024_2440420
informaworld_taylorfrancis_310_1080_15502287_2024_2440420
osti_scitechconnect_2556941
PublicationCentury 2000
PublicationDate 2025-03-04
PublicationDateYYYYMMDD 2025-03-04
PublicationDate_xml – month: 03
  year: 2025
  text: 2025-03-04
  day: 04
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle International journal of computational methods in engineering science and mechanics
PublicationYear 2025
Publisher Taylor & Francis
Publisher_xml – name: Taylor & Francis
References e_1_3_2_20_1
e_1_3_2_41_1
Liu S. (e_1_3_2_52_1) 2022; 35
e_1_3_2_22_1
e_1_3_2_43_1
e_1_3_2_24_1
e_1_3_2_45_1
e_1_3_2_26_1
e_1_3_2_47_1
e_1_3_2_16_1
e_1_3_2_39_1
e_1_3_2_9_1
e_1_3_2_18_1
e_1_3_2_7_1
e_1_3_2_31_1
e_1_3_2_54_1
e_1_3_2_10_1
Valiveti D. M. (e_1_3_2_12_1) 2023; 608
e_1_3_2_33_1
e_1_3_2_35_1
e_1_3_2_5_1
e_1_3_2_14_1
e_1_3_2_37_1
e_1_3_2_3_1
e_1_3_2_50_1
Williams C. K. (e_1_3_2_32_1) 2006
e_1_3_2_27_1
e_1_3_2_29_1
e_1_3_2_42_1
Glorot X. (e_1_3_2_49_1) 2010
e_1_3_2_21_1
e_1_3_2_44_1
e_1_3_2_23_1
e_1_3_2_46_1
e_1_3_2_25_1
e_1_3_2_48_1
Coussy O. (e_1_3_2_28_1) 2004
e_1_3_2_40_1
e_1_3_2_17_1
e_1_3_2_38_1
e_1_3_2_8_1
e_1_3_2_19_1
e_1_3_2_2_1
e_1_3_2_30_1
e_1_3_2_55_1
e_1_3_2_11_1
e_1_3_2_53_1
e_1_3_2_6_1
e_1_3_2_13_1
e_1_3_2_34_1
e_1_3_2_4_1
e_1_3_2_15_1
e_1_3_2_36_1
e_1_3_2_51_1
References_xml – volume-title: Poromechanics
  year: 2004
  ident: e_1_3_2_28_1
– ident: e_1_3_2_8_1
  doi: 10.1016/j.cam.2021.113995
– volume: 608
  start-page: 730
  issue: 11
  year: 2023
  ident: e_1_3_2_12_1
  article-title: Grid modification during simulated fracture propagation
  publication-title: US Patent
– ident: e_1_3_2_14_1
  doi: 10.1016/j.cma.2021.113741
– ident: e_1_3_2_51_1
  doi: 10.48550/arXiv.2210.14795
– ident: e_1_3_2_11_1
  doi: 10.1016/j.aej.2021.08.064
– ident: e_1_3_2_30_1
  doi: 10.1002/nag.2154
– volume-title: Gaussian Processes for Machine Learning
  year: 2006
  ident: e_1_3_2_32_1
– ident: e_1_3_2_19_1
  doi: 10.1016/j.ijheatmasstransfer.2023.125089
– ident: e_1_3_2_44_1
– ident: e_1_3_2_4_1
  doi: 10.1016/j.enpol.2013.11.034
– ident: e_1_3_2_39_1
  doi: 10.56952/ARMA-2023-0760
– ident: e_1_3_2_6_1
  doi: 10.1080/15502280802225234
– ident: e_1_3_2_54_1
  doi: 10.1016/j.cma.2024.116813
– ident: e_1_3_2_16_1
  doi: 10.1007/s10409-021-01148-1
– ident: e_1_3_2_10_1
  doi: 10.1016/j.jcp.2018.11.039
– ident: e_1_3_2_7_1
  doi: 10.1016/j.jngse.2017.10.012
– ident: e_1_3_2_46_1
  doi: 10.1016/j.cma.2022.114909
– ident: e_1_3_2_43_1
  doi: 10.48550/arXiv.1412.6980
– ident: e_1_3_2_18_1
  doi: 10.1115/1.4050542
– ident: e_1_3_2_3_1
  doi: 10.2172/964517
– ident: e_1_3_2_5_1
  doi: 10.2118/50939-PA
– volume: 35
  start-page: 20
  year: 2022
  ident: e_1_3_2_52_1
  article-title: A unified hard-constraint framework for solving geometrically complex PDES
  publication-title: Advances Neural Inform. Processing Syst.
– ident: e_1_3_2_29_1
  doi: 10.1007/s10483-006-1001-z
– ident: e_1_3_2_21_1
  doi: 10.1364/OE.384875
– ident: e_1_3_2_45_1
  doi: 10.1007/978-1-4842-4470-8_7
– ident: e_1_3_2_20_1
– start-page: 249
  volume-title: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings
  year: 2010
  ident: e_1_3_2_49_1
– ident: e_1_3_2_50_1
  doi: 10.48550/arXiv.2306.12749
– ident: e_1_3_2_27_1
  doi: 10.4208/cicp.OA-2020-0164
– ident: e_1_3_2_15_1
  doi: 10.1126/sciadv.abk0644
– ident: e_1_3_2_48_1
  doi: 10.48550/arXiv.2308.08468
– ident: e_1_3_2_35_1
  doi: 10.1080/15502287.2011.636789
– ident: e_1_3_2_13_1
  doi: 10.1016/j.jcp.2018.10.045
– ident: e_1_3_2_37_1
  doi: 10.1007/3-540-10861-0
– ident: e_1_3_2_9_1
  doi: 10.1016/j.jcp.2021.110334
– ident: e_1_3_2_42_1
  doi: 10.48550/arXiv.2210.12914
– ident: e_1_3_2_25_1
  doi: 10.1016/j.jcp.2024.113299
– ident: e_1_3_2_40_1
  doi: 10.1063/5.0116038
– ident: e_1_3_2_34_1
  doi: 10.1080/15502280590923612
– ident: e_1_3_2_33_1
  doi: 10.1080/15502280701252495
– ident: e_1_3_2_22_1
  doi: 10.1016/j.cma.2022.115141
– ident: e_1_3_2_17_1
  doi: 10.1016/j.cma.2020.113127
– ident: e_1_3_2_55_1
  doi: 10.1016/j.cma.2024.117197
– ident: e_1_3_2_26_1
  doi: 10.1016/j.cma.2024.117135
– ident: e_1_3_2_38_1
  doi: 10.1109/TNN.2002.1000141
– ident: e_1_3_2_36_1
  doi: 10.1007/BF02818935
– ident: e_1_3_2_24_1
  doi: 10.48550/arXiv.2404.13909
– ident: e_1_3_2_53_1
  doi: 10.1016/j.cam.2014.05.009
– ident: e_1_3_2_2_1
  doi: 10.2110/pec.87.39.0321
– ident: e_1_3_2_31_1
  doi: 10.1080/15502287.2023.2186974
– ident: e_1_3_2_41_1
  doi: 10.48550/arXiv.2406.04626
– ident: e_1_3_2_47_1
  doi: 10.1016/j.compfluid.2022.105583
– ident: e_1_3_2_23_1
  doi: 10.48550/arXiv.2010.15426
SSID ssj0036260
Score 2.3451724
Snippet This study presents a novel physics-informed neural network (PINN) framework for modeling poroelasticity in heterogeneous media with material interfaces. The...
SourceID osti
crossref
informaworld
SourceType Open Access Repository
Enrichment Source
Index Database
Publisher
StartPage 187
SubjectTerms coupled problems
deep neural network
ENGINEERING
physics-constrained machine learning
Physics-informed neural networks
poromechanics
scientific machine learning
Title Physics-informed neural networks for heterogeneous poroelastic media
URI https://www.tandfonline.com/doi/abs/10.1080/15502287.2024.2440420
https://www.osti.gov/servlets/purl/2556941
Volume 26
WOSCitedRecordID wos001383659200001&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: PRVAWR
  databaseName: Taylor & Francis Online Journals
  customDbUrl:
  eissn: 1550-2295
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0036260
  issn: 1550-2287
  databaseCode: TFW
  dateStart: 20050101
  isFulltext: true
  titleUrlDefault: https://www.tandfonline.com
  providerName: Taylor & Francis
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQxcBCeYpSQB5YXRLHeY0IqJgqhiK6WfFLIKEENWl_P3eJg9oBdYA1yZ2ss8_-Lvr8HSG3sYtsIETOXJJzJpIiZ1A2K8ad4qEKVWR512winc2yxSJ_8WzC2tMqsYZ2nVBEu1djcheq7hlxd4iqOSB9qO64mHBUuONYtcPRj6k5n771ezFqrbRXIsGCoUl_h-c3L1un05Z2KWzZFSTdxuEzHf7DsI_IoUee9L5bKsdkz5YnZOhRKPU5Xp-Sx5YUqmvWjQveoeYlWJYdY7ym8Ji-I42mgtVnq1VNAcRXFnA4uKbtXZQz8jp9mj88M99rgWmo8BrmiiROXQaltcvjIrJxZgrNDeS_inWquDKhCpJCaGGsTQOn4HsXpanT2hkX2OicDMqqtBeEAuDIjMEOwCIVVuks0-BWcUBKhUrCZEREH2OpvRA59sP4lKHXK-0jJTFS0kdqRCY_Zl-dEscug3xzAmXT_gJxXb8SGe2wHeNsS4AhqKWrkXSkG4l6bbkIL__geUwOOLYQRhqbuCKDZrmy12Rfr5uPennTrt5v98rqbw
linkProvider Taylor & Francis
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT8MwDLYQIMGF8RRjPHrgmrGm6euIgGmIsdMQu0VNmggk1KK14_dj94G2A9oBrk1tRU7ifI7szwDXvvXMQIiY2SDmTARJzDBsVoxbxV3lKs_wutlEOJlEs1m8XAtDaZUUQ9uaKKLy1XS46TG6TYm7IVjNEepjeMdFnxPFHcewfcvHu5b486fD19YbE9tKVRSJIoxk2iqe39Ss3E8r7KXotHM8dkvXz7DzHxPfh70GfDq39W45gA2THUKnAaJOc8yLI7iv8kJ1weqJ4RjRXqJkVieNFw5-dt4okybHDWjyReEgjs8NQnFU7VTlKMfwMnyY3o1Y026BaQzySmaTwA9thNG1jf3EM36UJpqn6AKUr0PFVeqqQZAILVJjwoFV-L_1wtBqbVM7MN4JbGZ5Zk7BQcwRpSk1ARahMEpHkUa1iiNYSlTgBl0QrZGlbrjIqSXGh3QbytLWUpIsJRtLdaH_I_ZZk3GsE4iXV1CW1SuIrVuWSG-NbI-WWyISITpdTXlHupRE2RYL9-wPmq9gZzR9Hsvx4-SpB7ucOgpTVps4h81yvjAXsK2_yvdifllt5W_ecO6Z
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQQYiF8hSlPDKwujSO8xoRJQKBqg5FdLNixxZIKKmalN_PXeKgdkAdYE1yJ8s-n7-LPn9HyI1vPD3kPKYmiBnlQRpTKJslZUYyV7rS06xpNhGOx9FsFk8sm7C0tEqsoU0jFFHnatzc88y0jLhbRNUMkD5Ud4wPGCrcMajatwE6Bxjk0-StTcYotlLfiQQTijbtJZ7f3KwdT2vipZCzC9h1K6dP0v2HcR-QfQs9nbsmVg7Jls6PSNfCUMdu8vKYjGpWqCppMy54h6KXYJk3lPHSgcfOO_JoCgg_XSxLB1B8oQGIg2unvoxyQl6Th-n9I7XNFqiCEq-iJg380ERQW5vYTz3tR1mqWAYJQPoqlExmrhwGKVc80zocGgnfGy8MjVImM0PtnZJOXuT6jDiAOKIswxbAPORaqihS4FYygEqpDNygR3g7x0JZJXJsiPEpXCtY2s6UwJkSdqZ6ZPBjNm-kODYZxKsLKKr6H4hpGpYIb4NtH1dbAA5BMV2FrCNVCRRsi7l7_gfP12R3MkrEy9P4uU_2GLYTRkobvyCdarHUl2RHfVUf5eKqDuRvFjrtSw
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=Physics-informed+neural+networks+for+heterogeneous+poroelastic+media&rft.jtitle=International+journal+of+computational+methods+in+engineering+science+and+mechanics&rft.au=Roy%2C+Sumanta&rft.au=Annavarapu%2C+Chandrasekhar&rft.au=Roy%2C+Pratanu&rft.au=Valiveti%2C+Dakshina+M.&rft.date=2025-03-04&rft.issn=1550-2287&rft.eissn=1550-2295&rft.volume=26&rft.issue=2&rft.spage=187&rft.epage=207&rft_id=info:doi/10.1080%2F15502287.2024.2440420&rft.externalDBID=n%2Fa&rft.externalDocID=10_1080_15502287_2024_2440420
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1550-2287&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1550-2287&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1550-2287&client=summon