Deep Learning for Simultaneous Inference of Hydraulic and Transport Properties

Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this invers...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Water resources research Ročník 58; číslo 10
Hlavní autoři:	Zhou, Zitong, Zabaras, Nicholas, Tartakovsky, Daniel M.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Washington John Wiley & Sons, Inc 01.10.2022 American Geophysical Union (AGU)
Témata:	adversarial Algorithms Bayesian analysis Bayesian theory Coders Computational efficiency Computer applications Computing costs Conductivity Contaminants Data assimilation Data collection Deep learning History Hydraulics Identification inverse problem Inverse problems Machine learning Mathematical models neural network Parameters Piezometric head Probability theory Reconstruction Remediation Simulators Simultaneous discrimination learning source indentification subsurface Transport Transport properties water
ISSN:	0043-1397, 1944-7973
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We use a convolutional adversarial autoencoder (CAAE) to parameterize a heterogeneous non‐Gaussian conductivity field via a low‐dimensional latent representation. A three‐dimensional dense convolutional encoder‐decoder (DenseED) network serves as a forward surrogate of the flow and transport model. The CAAE‐DenseED surrogate is fed into the ensemble smoother with multiple data assimilation (ESMDA) algorithm to sample from the Bayesian posterior distribution of the unknown parameters, forming a CAAE‐DenseED‐ESMDA inversion framework. The resulting CAAE‐DenseED‐ESMDA inversion strategy is used to identify a three‐dimensional contaminant source and conductivity field. A comparison of the inversion results from CAAE‐ESMDA with physical flow and transport simulator and from CAAE‐DenseED‐ESMDA shows that the latter yields accurate reconstruction results at the fraction of the computational cost of the former. Plain Language Summary Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We develop a deep‐learning strategy to identify a three‐dimensional contaminant source and conductivity field from sparse observations. Key Points Our deep‐learning strategy reconstructs three‐dimensional conductivity field and contaminant release history Conductivity parameterization with convolutional adversarial autoencoder reduces the inverse problem's dimensionality Convolutional encoder‐decoder acts as a surrogate of forward models; ensemble smoother approximates parameters' posterior distribution
AbstractList	Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We use a convolutional adversarial autoencoder (CAAE) to parameterize a heterogeneous non‐Gaussian conductivity field via a low‐dimensional latent representation. A three‐dimensional dense convolutional encoder‐decoder (DenseED) network serves as a forward surrogate of the flow and transport model. The CAAE‐DenseED surrogate is fed into the ensemble smoother with multiple data assimilation (ESMDA) algorithm to sample from the Bayesian posterior distribution of the unknown parameters, forming a CAAE‐DenseED‐ESMDA inversion framework. The resulting CAAE‐DenseED‐ESMDA inversion strategy is used to identify a three‐dimensional contaminant source and conductivity field. A comparison of the inversion results from CAAE‐ESMDA with physical flow and transport simulator and from CAAE‐DenseED‐ESMDA shows that the latter yields accurate reconstruction results at the fraction of the computational cost of the former. Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We use a convolutional adversarial autoencoder (CAAE) to parameterize a heterogeneous non‐Gaussian conductivity field via a low‐dimensional latent representation. A three‐dimensional dense convolutional encoder‐decoder (DenseED) network serves as a forward surrogate of the flow and transport model. The CAAE‐DenseED surrogate is fed into the ensemble smoother with multiple data assimilation (ESMDA) algorithm to sample from the Bayesian posterior distribution of the unknown parameters, forming a CAAE‐DenseED‐ESMDA inversion framework. The resulting CAAE‐DenseED‐ESMDA inversion strategy is used to identify a three‐dimensional contaminant source and conductivity field. A comparison of the inversion results from CAAE‐ESMDA with physical flow and transport simulator and from CAAE‐DenseED‐ESMDA shows that the latter yields accurate reconstruction results at the fraction of the computational cost of the former. Plain Language Summary Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We develop a deep‐learning strategy to identify a three‐dimensional contaminant source and conductivity field from sparse observations. Key Points Our deep‐learning strategy reconstructs three‐dimensional conductivity field and contaminant release history Conductivity parameterization with convolutional adversarial autoencoder reduces the inverse problem's dimensionality Convolutional encoder‐decoder acts as a surrogate of forward models; ensemble smoother approximates parameters' posterior distribution Abstract Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We use a convolutional adversarial autoencoder (CAAE) to parameterize a heterogeneous non‐Gaussian conductivity field via a low‐dimensional latent representation. A three‐dimensional dense convolutional encoder‐decoder (DenseED) network serves as a forward surrogate of the flow and transport model. The CAAE‐DenseED surrogate is fed into the ensemble smoother with multiple data assimilation (ESMDA) algorithm to sample from the Bayesian posterior distribution of the unknown parameters, forming a CAAE‐DenseED‐ESMDA inversion framework. The resulting CAAE‐DenseED‐ESMDA inversion strategy is used to identify a three‐dimensional contaminant source and conductivity field. A comparison of the inversion results from CAAE‐ESMDA with physical flow and transport simulator and from CAAE‐DenseED‐ESMDA shows that the latter yields accurate reconstruction results at the fraction of the computational cost of the former. Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We use a convolutional adversarial autoencoder (CAAE) to parameterize a heterogeneous non‐Gaussian conductivity field via a low‐dimensional latent representation. A three‐dimensional dense convolutional encoder‐decoder (DenseED) network serves as a forward surrogate of the flow and transport model. The CAAE‐DenseED surrogate is fed into the ensemble smoother with multiple data assimilation (ESMDA) algorithm to sample from the Bayesian posterior distribution of the unknown parameters, forming a CAAE‐DenseED‐ESMDA inversion framework. The resulting CAAE‐DenseED‐ESMDA inversion strategy is used to identify a three‐dimensional contaminant source and conductivity field. A comparison of the inversion results from CAAE‐ESMDA with physical flow and transport simulator and from CAAE‐DenseED‐ESMDA shows that the latter yields accurate reconstruction results at the fraction of the computational cost of the former. Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We develop a deep‐learning strategy to identify a three‐dimensional contaminant source and conductivity field from sparse observations. Our deep‐learning strategy reconstructs three‐dimensional conductivity field and contaminant release history Conductivity parameterization with convolutional adversarial autoencoder reduces the inverse problem's dimensionality Convolutional encoder‐decoder acts as a surrogate of forward models; ensemble smoother approximates parameters' posterior distribution
Author	Tartakovsky, Daniel M. Zhou, Zitong Zabaras, Nicholas
Author_xml	– sequence: 1 givenname: Zitong surname: Zhou fullname: Zhou, Zitong organization: Stanford University – sequence: 2 givenname: Nicholas orcidid: 0000-0003-3144-8388 surname: Zabaras fullname: Zabaras, Nicholas organization: University of Notre Dame – sequence: 3 givenname: Daniel M. orcidid: 0000-0001-9019-8935 surname: Tartakovsky fullname: Tartakovsky, Daniel M. email: tartakovsky@stanford.edu organization: Stanford University
BackLink	https://www.osti.gov/biblio/1894737$$D View this record in Osti.gov
BookMark	eNp90U1v1DAQBmALFYlt4cYPsODCgYDHdmL7iJaPVloBWop6tLzOGFxl7WAnQvvvSRUOVSU4zeWZj1dzTs5STkjIc2BvgHHzljMON3smQAr9iGzASNkoo8QZ2TAmRQPCqCfkvNZbxkC2ndqQz-8RR7pDV1JMP2jIhX6Lx3mYXMI8V3qVAhZMHmkO9PLUFzcP0VOXenpdXKpjLhP9WvKIZYpYn5LHwQ0Vn_2tF-T7xw_X28tm9-XT1fbdrnHCMGg06IPSkitnehB9q0J3ACfa0HuvsAsC1KFrtWamdY457aFzB-U0OOQBOIoL8mKdm-sUbfVxQv_T55TQTxa0kUqoBb1a0VjyrxnrZI-xehyGNZvlGsAoAKYX-vIBvc1zSUsEyxXXUknD5aJer8qXXGvBYMcSj66cLDB79wF7_wML5w_4cqebYk5TcXH4V5NYm37HAU__XWBv9ts977gA8Qf0iJfv
CitedBy_id	crossref_primary_10_1016_j_jenvman_2025_124708 crossref_primary_10_1016_j_jhydrol_2024_130727 crossref_primary_10_1016_j_ecolind_2025_113839 crossref_primary_10_1016_j_wroa_2025_100367 crossref_primary_10_1029_2023WR034939 crossref_primary_10_1016_j_jcp_2024_113052 crossref_primary_10_3390_w17020255 crossref_primary_10_1016_j_energy_2024_131713 crossref_primary_10_1029_2023WR035408 crossref_primary_10_1016_j_jhydrol_2025_133654 crossref_primary_10_1016_j_jhydrol_2025_133797 crossref_primary_10_1029_2022WR033644 crossref_primary_10_1029_2024WR038468 crossref_primary_10_1007_s00477_024_02800_5 crossref_primary_10_1016_j_scitotenv_2023_161734 crossref_primary_10_3390_pr13061834 crossref_primary_10_1016_j_enggeo_2025_107998 crossref_primary_10_1016_j_jhydrol_2025_133202 crossref_primary_10_1029_2023WR036893 crossref_primary_10_1016_j_jhydrol_2024_131540 crossref_primary_10_1016_j_jconhyd_2024_104394 crossref_primary_10_1016_j_camwa_2025_07_022
Cites_doi	10.1002/2017wr020906 10.1016/j.cma.2020.113636 10.1002/2017wr022135 10.1029/2020wr027627 10.3389/fams.2019.00047 10.1029/94jc00572 10.1029/96wr03753 10.1615/JMachLearnModelComput.2021038925 10.1016/j.jhydrol.2016.04.008 10.1016/j.advwatres.2017.12.011 10.1007/s10596-020-10014-1 10.1016/j.cageo.2019.104333 10.1061/(asce)1084-0699(2001)6:3(225) 10.1016/j.cageo.2020.104456 10.1016/j.advwatres.2015.09.019 10.1016/j.advwatres.2013.10.014 10.1016/j.advwatres.2018.03.010 10.1016/j.jcp.2006.01.047 10.1175/1520-0493(1996)124<2898:daaimi>2.0.co;2 10.1016/j.petrol.2019.02.037 10.1061/(asce)1084-0699(2008)13:1(37) 10.1002/2014wr015740 10.1023/a:1022277418570 10.1029/2018wr024638 10.1080/23311835.2015.1118219 10.3389/fenvs.2019.00149 10.1098/rspa.2020.0213 10.1016/j.jcp.2022.111438 10.1007/s11004-014-9541-2 10.1201/9781482296426 10.1016/j.cageo.2021.104762 10.1016/j.cageo.2012.03.011 10.1016/j.cageo.2020.104567 10.1155/2019/3280961 10.1007/978-3-7908-2604-3_16 10.1016/j.advwatres.2018.10.023 10.1007/s11004-019-09794-9 10.1016/j.ijggc.2020.103223 10.1029/2020wr028538 10.1029/2019WR026082 10.1007/s11004-007-9131-7 10.1016/j.jcp.2022.111008 10.1002/2016wr019111 10.2118/56855-pa 10.1029/2020WR027643 10.2118/90058-MS 10.1002/2017wr022148 10.1007/s10236-003-0036-9 10.1007/s00477-020-01888-9 10.2307/3318737 10.1111/gwat.12413 10.1007/s11222-006-9438-0 10.1029/2005wr004731 10.1109/ICCV.2015.123 10.1007/s10040-019-01962-9 10.1016/j.jhydrol.2020.125266 10.1061/(ASCE)HZ.2153-5515.0000431 10.1029/2011wr010412 10.1016/j.jhydrol.2015.09.006 10.1137/19m1260773 10.1016/j.advwatres.2017.09.029 10.1016/j.jhydrol.2021.126903
ContentType	Journal Article
Copyright	2022. American Geophysical Union. All Rights Reserved.
Copyright_xml	– notice: 2022. American Geophysical Union. All Rights Reserved.
DBID	AAYXX CITATION 7QH 7QL 7T7 7TG 7U9 7UA 8FD C1K F1W FR3 H94 H96 KL. KR7 L.G M7N P64 7S9 L.6 OTOTI
DOI	10.1029/2021WR031438
DatabaseName	CrossRef Aqualine Bacteriology Abstracts (Microbiology B) Industrial and Applied Microbiology Abstracts (Microbiology A) Meteorological & Geoastrophysical Abstracts Virology and AIDS Abstracts Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database AIDS and Cancer Research Abstracts Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Meteorological & Geoastrophysical Abstracts - Academic Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Algology Mycology and Protozoology Abstracts (Microbiology C) Biotechnology and BioEngineering Abstracts AGRICOLA AGRICOLA - Academic OSTI.GOV
DatabaseTitle	CrossRef Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Virology and AIDS Abstracts Technology Research Database Aqualine Water Resources Abstracts Biotechnology and BioEngineering Abstracts Environmental Sciences and Pollution Management Meteorological & Geoastrophysical Abstracts Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Bacteriology Abstracts (Microbiology B) Algology Mycology and Protozoology Abstracts (Microbiology C) ASFA: Aquatic Sciences and Fisheries Abstracts AIDS and Cancer Research Abstracts Engineering Research Database Industrial and Applied Microbiology Abstracts (Microbiology A) Meteorological & Geoastrophysical Abstracts - Academic AGRICOLA AGRICOLA - Academic
DatabaseTitleList	AGRICOLA Civil Engineering Abstracts CrossRef
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography Economics
EISSN	1944-7973
EndPage	n/a
ExternalDocumentID	1894737 10_1029_2021WR031438 WRCR26231
Genre	article
GrantInformation_xml	– fundername: TotalEnergies – fundername: DOE Advanced Research Projects Agency ‐ Energy funderid: DE‐AR0001204 – fundername: National Science Foundation funderid: EAR‐2100927
GroupedDBID	-~X ..I .DC 05W 0R~ 123 1OB 1OC 24P 31~ 33P 3V. 50Y 5VS 6TJ 7WY 7XC 8-1 8CJ 8FE 8FG 8FH 8FL 8G5 8R4 8R5 8WZ A00 A6W AAESR AAHBH AAHHS AAIHA AAIKC AAMNW AANHP AANLZ AASGY AAXRX AAYCA AAYJJ AAYOK AAZKR ABCUV ABJCF ABJNI ABPPZ ABTAH ABUWG ACAHQ ACBWZ ACCFJ ACCMX ACCZN ACGFO ACGFS ACIWK ACKIV ACNCT ACPOU ACPRK ACRPL ACXBN ACXQS ACYXJ ADBBV ADEOM ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN AEEZP AEIGN AENEX AEQDE AEUYN AEUYR AFBPY AFGKR AFKRA AFPWT AFRAH AFWVQ AFZJQ AIDBO AIURR AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN ALXUD AMYDB ASPBG ATCPS AVWKF AZFZN AZQEC AZVAB BDRZF BENPR BEZIV BFHJK BGLVJ BHPHI BKSAR BMXJE BPHCQ BRXPI CCPQU CS3 D0L D1J DCZOG DDYGU DPXWK DRFUL DRSTM DU5 DWQXO EBS EJD F5P FEDTE FRNLG G-S GNUQQ GODZA GROUPED_ABI_INFORM_COMPLETE GUQSH HCIFZ HVGLF HZ~ K60 K6~ L6V LATKE LEEKS LITHE LK5 LOXES LUTES LYRES M0C M2O M7R M7S MEWTI MSFUL MSSTM MVM MW2 MXFUL MXSTM MY~ O9- OHT OK1 P-X P2P P2W PALCI PATMY PCBAR PQBIZ PQBZA PQQKQ PROAC PTHSS PYCSY Q2X R.K RIWAO RJQFR ROL SAMSI SUPJJ TAE TN5 TWZ UQL VJK VOH WBKPD WXSBR WYJ XOL XSW YHZ YV5 ZCG ZY4 ZZTAW ~02 ~KM ~OA ~~A AAMMB AAYXX ADXHL AEFGJ AETEA AFFHD AGQPQ AGXDD AIDQK AIDYY AIQQE CITATION GROUPED_DOAJ PHGZM PHGZT PQGLB WIN 7QH 7QL 7T7 7TG 7U9 7UA 8FD C1K F1W FR3 H94 H96 KL. KR7 L.G M7N P64 7S9 L.6 AAPBV ABHUG ADAWD ADDAD AEUQT AFVGU AGJLS OTOTI
ID	FETCH-LOGICAL-a3901-818b78427a9d13d57f6b1a35fdcc7e6f317b6588095aa0a8c16ab7a81ae2f12e3
IEDL.DBID	WIN
ISICitedReferencesCount	30
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000863034200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0043-1397
IngestDate	Mon Sep 25 05:37:39 EDT 2023 Fri Sep 05 17:31:43 EDT 2025 Wed Aug 13 03:48:52 EDT 2025 Tue Nov 18 22:20:11 EST 2025 Sat Nov 29 01:36:50 EST 2025 Wed Jan 22 16:22:04 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	10
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-a3901-818b78427a9d13d57f6b1a35fdcc7e6f317b6588095aa0a8c16ab7a81ae2f12e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 USDOE
ORCID	0000-0001-9019-8935 0000-0003-3144-8388 0000000190198935 0000000331448388
PQID	2728474924
PQPubID	105507
PageCount	20
ParticipantIDs	osti_scitechconnect_1894737 proquest_miscellaneous_2811971108 proquest_journals_2728474924 crossref_primary_10_1029_2021WR031438 crossref_citationtrail_10_1029_2021WR031438 wiley_primary_10_1029_2021WR031438_WRCR26231
PublicationCentury	2000
PublicationDate	October 2022
PublicationDateYYYYMMDD	2022-10-01
PublicationDate_xml	– month: 10 year: 2022 text: October 2022
PublicationDecade	2020
PublicationPlace	Washington
PublicationPlace_xml	– name: Washington – name: United States
PublicationTitle	Water resources research
PublicationYear	2022
Publisher	John Wiley & Sons, Inc American Geophysical Union (AGU)
Publisher_xml	– name: John Wiley & Sons, Inc – name: American Geophysical Union (AGU)
References	e_1_2_9_2_4_1 e_1_2_9_1_15_1 e_1_2_9_1_36_1 e_1_2_9_1_13_1 e_1_2_9_1_34_1 e_1_2_9_1_11_1 e_1_2_9_1_32_1 e_1_2_9_1_30_1 e_1_2_9_1_2_1 e_1_2_9_1_4_1 Bedekar V. (e_1_2_9_1_6_1) 2016 e_1_2_9_1_60_1 e_1_2_9_1_62_1 e_1_2_9_1_64_1 e_1_2_9_1_66_1 e_1_2_9_1_29_1 e_1_2_9_1_27_1 e_1_2_9_1_25_1 e_1_2_9_1_48_1 e_1_2_9_1_46_1 e_1_2_9_1_21_1 e_1_2_9_1_44_1 e_1_2_9_1_42_1 e_1_2_9_1_40_1 e_1_2_9_1_8_1 e_1_2_9_1_50_1 e_1_2_9_1_52_1 e_1_2_9_1_54_1 e_1_2_9_1_18_1 e_1_2_9_1_56_1 e_1_2_9_1_16_1 e_1_2_9_1_39_1 e_1_2_9_1_58_1 e_1_2_9_1_14_1 e_1_2_9_1_37_1 e_1_2_9_1_12_1 e_1_2_9_1_35_1 e_1_2_9_2_3_1 e_1_2_9_1_10_1 e_1_2_9_1_33_1 e_1_2_9_1_31_1 e_1_2_9_1_3_1 e_1_2_9_1_5_1 e_1_2_9_1_61_1 Goodfellow I. (e_1_2_9_2_2_1) 2016 e_1_2_9_1_63_1 e_1_2_9_1_65_1 e_1_2_9_1_67_1 e_1_2_9_1_28_1 e_1_2_9_1_49_1 e_1_2_9_1_26_1 e_1_2_9_1_47_1 e_1_2_9_1_24_1 e_1_2_9_1_45_1 e_1_2_9_1_22_1 e_1_2_9_1_43_1 e_1_2_9_1_20_1 e_1_2_9_1_41_1 e_1_2_9_1_7_1 e_1_2_9_1_9_1 e_1_2_9_1_51_1 e_1_2_9_1_53_1 e_1_2_9_1_55_1 e_1_2_9_1_19_1 e_1_2_9_1_57_1 Harbaugh A. W. (e_1_2_9_1_23_1) 2005 e_1_2_9_1_17_1 e_1_2_9_1_38_1 e_1_2_9_1_59_1
References_xml	– ident: e_1_2_9_1_64_1 doi: 10.1002/2017wr020906 – ident: e_1_2_9_1_49_1 doi: 10.1016/j.cma.2020.113636 – ident: e_1_2_9_1_25_1 doi: 10.1002/2017wr022135 – ident: e_1_2_9_1_29_1 doi: 10.1029/2020wr027627 – ident: e_1_2_9_1_16_1 doi: 10.3389/fams.2019.00047 – ident: e_1_2_9_1_14_1 doi: 10.1029/94jc00572 – ident: e_1_2_9_1_47_1 doi: 10.1029/96wr03753 – ident: e_1_2_9_1_48_1 doi: 10.1615/JMachLearnModelComput.2021038925 – volume-title: Deep Learning year: 2016 ident: e_1_2_9_2_2_1 – ident: e_1_2_9_1_40_1 – ident: e_1_2_9_1_3_1 doi: 10.1016/j.jhydrol.2016.04.008 – ident: e_1_2_9_1_61_1 doi: 10.1016/j.advwatres.2017.12.011 – ident: e_1_2_9_1_26_1 doi: 10.1007/s10596-020-10014-1 – ident: e_1_2_9_1_34_1 doi: 10.1016/j.cageo.2019.104333 – ident: e_1_2_9_1_2_1 doi: 10.1061/(asce)1084-0699(2001)6:3(225) – ident: e_1_2_9_1_42_1 doi: 10.1016/j.cageo.2020.104456 – ident: e_1_2_9_1_37_1 doi: 10.1016/j.advwatres.2015.09.019 – ident: e_1_2_9_1_66_1 doi: 10.1016/j.advwatres.2013.10.014 – volume-title: MT3D‐USGS version 1: A US Geological Survey release of MT3DMS updated with new and expanded transport capabilities for use with MODFLOW (Tech. Rep.) year: 2016 ident: e_1_2_9_1_6_1 – ident: e_1_2_9_1_27_1 doi: 10.1016/j.advwatres.2018.03.010 – ident: e_1_2_9_1_56_1 doi: 10.1016/j.jcp.2006.01.047 – ident: e_1_2_9_1_52_1 doi: 10.1175/1520-0493(1996)124<2898:daaimi>2.0.co;2 – ident: e_1_2_9_1_11_1 doi: 10.1016/j.petrol.2019.02.037 – ident: e_1_2_9_1_50_1 doi: 10.1061/(asce)1084-0699(2008)13:1(37) – ident: e_1_2_9_1_65_1 doi: 10.1002/2014wr015740 – ident: e_1_2_9_2_4_1 – ident: e_1_2_9_1_57_1 doi: 10.1023/a:1022277418570 – ident: e_1_2_9_1_43_1 doi: 10.1029/2018wr024638 – ident: e_1_2_9_1_55_1 doi: 10.1080/23311835.2015.1118219 – ident: e_1_2_9_1_5_1 doi: 10.3389/fenvs.2019.00149 – ident: e_1_2_9_1_8_1 doi: 10.1098/rspa.2020.0213 – volume-title: MODFLOW‐2005, the US Geological Survey modular ground‐water model: The ground‐water flow process year: 2005 ident: e_1_2_9_1_23_1 – ident: e_1_2_9_1_9_1 doi: 10.1016/j.jcp.2022.111438 – ident: e_1_2_9_1_53_1 doi: 10.1007/s11004-014-9541-2 – ident: e_1_2_9_1_17_1 doi: 10.1201/9781482296426 – ident: e_1_2_9_1_39_1 doi: 10.1016/j.cageo.2021.104762 – ident: e_1_2_9_1_13_1 doi: 10.1016/j.cageo.2012.03.011 – ident: e_1_2_9_1_45_1 doi: 10.1016/j.cageo.2020.104567 – ident: e_1_2_9_1_30_1 doi: 10.1155/2019/3280961 – ident: e_1_2_9_1_10_1 doi: 10.1007/978-3-7908-2604-3_16 – ident: e_1_2_9_1_12_1 doi: 10.1016/j.advwatres.2018.10.023 – ident: e_1_2_9_1_38_1 doi: 10.1007/s11004-019-09794-9 – ident: e_1_2_9_1_54_1 doi: 10.1016/j.ijggc.2020.103223 – ident: e_1_2_9_1_28_1 doi: 10.1029/2020wr028538 – ident: e_1_2_9_1_44_1 doi: 10.1029/2019WR026082 – ident: e_1_2_9_1_46_1 doi: 10.1007/s11004-007-9131-7 – ident: e_1_2_9_1_59_1 doi: 10.1016/j.jcp.2022.111008 – ident: e_1_2_9_1_60_1 doi: 10.1002/2016wr019111 – ident: e_1_2_9_1_58_1 doi: 10.2118/56855-pa – ident: e_1_2_9_1_62_1 doi: 10.1029/2020WR027643 – ident: e_1_2_9_1_18_1 doi: 10.2118/90058-MS – ident: e_1_2_9_1_32_1 doi: 10.1002/2017wr022148 – ident: e_1_2_9_1_15_1 doi: 10.1007/s10236-003-0036-9 – ident: e_1_2_9_1_67_1 doi: 10.1007/s00477-020-01888-9 – ident: e_1_2_9_1_22_1 doi: 10.2307/3318737 – ident: e_1_2_9_1_4_1 doi: 10.1111/gwat.12413 – ident: e_1_2_9_1_21_1 doi: 10.1007/s11222-006-9438-0 – ident: e_1_2_9_1_63_1 doi: 10.1029/2005wr004731 – ident: e_1_2_9_2_3_1 doi: 10.1109/ICCV.2015.123 – ident: e_1_2_9_1_20_1 – ident: e_1_2_9_1_24_1 doi: 10.1007/s10040-019-01962-9 – ident: e_1_2_9_1_19_1 doi: 10.1016/j.jhydrol.2020.125266 – ident: e_1_2_9_1_31_1 – ident: e_1_2_9_1_35_1 doi: 10.1061/(ASCE)HZ.2153-5515.0000431 – ident: e_1_2_9_1_41_1 doi: 10.1029/2011wr010412 – ident: e_1_2_9_1_36_1 doi: 10.1016/j.jhydrol.2015.09.006 – ident: e_1_2_9_1_7_1 doi: 10.1137/19m1260773 – ident: e_1_2_9_1_33_1 doi: 10.1016/j.advwatres.2017.09.029 – ident: e_1_2_9_1_51_1 doi: 10.1016/j.jhydrol.2021.126903
SSID	ssj0014567
Score	2.524289
Snippet	Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two... Abstract Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation....
SourceID	osti proquest crossref wiley
SourceType	Open Access Repository Aggregation Database Enrichment Source Index Database Publisher
SubjectTerms	adversarial Algorithms Bayesian analysis Bayesian theory Coders Computational efficiency Computer applications Computing costs Conductivity Contaminants Data assimilation Data collection Deep learning History Hydraulics Identification inverse problem Inverse problems Machine learning Mathematical models neural network Parameters Piezometric head Probability theory Reconstruction Remediation Simulators Simultaneous discrimination learning source indentification subsurface Transport Transport properties water
Title	Deep Learning for Simultaneous Inference of Hydraulic and Transport Properties
URI	https://onlinelibrary.wiley.com/doi/abs/10.1029%2F2021WR031438 https://www.proquest.com/docview/2728474924 https://www.proquest.com/docview/2811971108 https://www.osti.gov/biblio/1894737
Volume	58
WOSCitedRecordID	wos000863034200001&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: PRVWIB databaseName: Wiley Online Library customDbUrl: eissn: 1944-7973 dateEnd: 20231213 omitProxy: false ssIdentifier: ssj0014567 issn: 0043-1397 databaseCode: WIN dateStart: 19970101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell – providerCode: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1944-7973 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014567 issn: 0043-1397 databaseCode: DRFUL dateStart: 19970101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3da9swED9GNthetu6Lev1Ag_VpM4tkO5IfS9vQQgkl_UjfxEmW20BxSpwU-t9X58gmfdig9M3gEwjpTvfTffwE8CtFlVqHeVz2FfoLSmJiZVUeZyXmgmNhsKFrujqVo5G6vs7PQsCNemFW_BBdwI0sozmvycDR1IFsgDgy_a2dT8bEvp5Qry9PG7ucnIy6JILHBrJNMBPQCXXvfvjf9cHPPFJv5i3rGdpcx6yN0xl-eu10N-BjgJtsf6Ufn-GNq77A-7Ybufbf4RX028evMDp07p4FxtUb5uEsO59SxSFWbras2UnbHMhmJTt-LOa4vJtahlXBOo50dkbR_TnRtH6Dy-HRxcFxHN5biJEiH7H33UaqVEjMC54UmSwHhmOSlYW10g1KDzWMByzKozLEPirLB2gkKo5OlFy45Dv0qlnlNoFlXqjkA2m45akkXq2inyTGZF4H-lLmEfxu11zbQEZOb2Lc6SYpLnK9vl4R7HXS9ysSjn_IbdH2aQ8eiAHXUqmQXWiu8lQmMoLtdld1MNRaC0n-OfW30Ah-dr-9iVHeZLW6WijKtVK_RAR_mj3-7yz0ZHwwFh5W8h8vE9-CD4KaK5pSwW3oLeZLtwPv7MNiWs934e3heHh5utvo-BNlpPb_
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3da9RAEB_0KrQvfotpq66gTxp6m4_bzaO0Hlc8j3K2tm_L7GajByVX7kPof-9MbhOuDwriWyCTEHZnMr-dj98AvMtQZ85jEVd9jXRASW2snS7ivMIikVhabOiavo_VZKKvroqzMOeUe2E2_BBdwI0to_lfs4FzQDqwDTBJJh3b5eWU6ddTfR92MtKkvAc7J9PhxbhLJBA-UG2SmcFOqH2nNxxtP3_HK_XmZF13EOc2bm0cz_DRf3_yY3gYMKf4tFGSJ3DP109ht21JXtJ1GIX-8_YZTE68vxGBdvWHIEwrvs247BBrP18vxWnbISjmlRjdlgtcX8-cwLoUHVG6OOMQ_4K5Wp_DxfDz-fEoDkMXYuTwR0wO3CqdJQqLUqZlrqqBlZjmVemc8oOK8IYl1KIJmiH2UTs5QKtQS_RJJROfvoBePa_9SxA5CVVyoKx0MlNMrlX209TanBShr1QRwYd20Y0LjOQ8GOPaNJnxpDDb6xXB-076ZsPE8Qe5A94_QwiCaXAd1wu5lZG6yFSqIjhst9UEa12aRLGTzugoGsHb7jbZGSdPNqtrEs0JV26aiOBjs8l__QpzOT2eJoQt5f6_ib-B3dH517EZn06-HMBewt0WTe3gIfRWi7V_BQ_cr9VsuXgdVP03KLX6qw
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3daxQxEB_0KupL_ca1VSPoky69ZD-SPJaeR4vHcZzW9i0k2UQPyt5xH0L_ezN72eX6YEH6trCTJWQyO79kZn4D8DHXIrdOy9T3hQ4HlMykwgqZFl5LRnVldEPX9HPEx2NxeSknsc8p1sJs-SG6Cze0jOZ_jQbuFpWPbANIkhmO7fRiivTrmbgPe3khy2CZe4Pp8HzUBRICPuBtkBnBTsx9D1842h1_wyv15sG6biDOXdzaOJ7hkztP-SnsR8xJjreb5Bncc_VzeNSWJK_Cc2yF_vv6BYwHzi1IpF39RQKmJd9nmHaoazffrMhZWyFI5p6cXldLvbmaWaLrinRE6WSCV_xL5Gp9CefDrz9OTtPYdCHVeP2RBgduuMgZ17KiWVVwXxqqs8JX1nJX-oA3TEAtIkAzrftaWFpqw7Wg2jFPmcteQa-e1-41kCIIeVpyQy3NOZJrVf0sM6YIG6HPuUzgc7voykZGcmyMcaWayDiTane9EvjUSS-2TBz_kDtA_amAIJAG12K-kF0rKmTOM57AYatWFa11pRhHJ52Ho2gCH7rXwc4weLJdXcUEBlyxaCKBL42Sb52FupieTFnAlvTN_4m_h4eTwVCNzsbfDuAxw2KLJnXwEHrr5ca9hQf2z3q2Wr6LO_0vuKn6Jg
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=Deep+Learning+for+Simultaneous+Inference+of+Hydraulic+and+Transport+Properties&rft.jtitle=Water+resources+research&rft.au=Zhou%2C+Zitong&rft.au=Zabaras%2C+Nicholas&rft.au=Tartakovsky%2C+Daniel+M.&rft.date=2022-10-01&rft.issn=0043-1397&rft.volume=58&rft.issue=10+p.e2021WR031438-&rft_id=info:doi/10.1029%2F2021WR031438&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0043-1397&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0043-1397&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0043-1397&client=summon