Integration of Deep Learning‐Based Inversion and Upscaled Mass‐Transfer Model for DNAPL Mass‐Discharge Estimation and Uncertainty Assessment

The challenges posed by high‐resolution characterization of dense nonaqueous phase liquid (DNAPL) source zone architecture (SZA) have motivated the development of simpler upscaled models that rely on domain‐averaged metrics to capture the average mass discharge downstream of source zones (SZ). Howev...

Full description

Saved in:

Bibliographic Details
Published in:	Water resources research Vol. 58; no. 10
Main Authors:	Kang, Xueyuan, Kokkinaki, Amalia, Shi, Xiaoqing, Yoon, Hongkyu, Lee, Jonghyun, Kitanidis, Peter K., Wu, Jichun
Format:	Journal Article
Language:	English
Published:	Washington John Wiley & Sons, Inc 01.10.2022
Subjects:	3D DNAPL characterization Bayesian analysis Bayesian theory Boreholes convolutional variational autoencoder Data assimilation Data collection Decision making Deep learning Discharge DNAPL mass discharge Domains Effluents Estimates Frameworks kriging Mass mass transfer Mathematical models Modelling multistage dissolution Nonaqueous phase liquids Probability theory remediation Statistical methods Temporal variations Uncertainty upscaled modeling water
ISSN:	0043-1397, 1944-7973
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	The challenges posed by high‐resolution characterization of dense nonaqueous phase liquid (DNAPL) source zone architecture (SZA) have motivated the development of simpler upscaled models that rely on domain‐averaged metrics to capture the average mass discharge downstream of source zones (SZ). However, SZA is highly irregular, making estimation of these domain‐averaged metrics from sparse borehole data extremely difficult. Poor estimation of SZ metrics means that upscaled models cannot reproduce the multistage effluent concentrations. Bayesian inversion methods can be used to obtain accurate estimates of SZ metrics and their uncertainties from sparse data, and from there, upscaled models can better reproduce multistage effluent concentrations. This work presents a framework for integrating a deep‐learning‐based 3D SZA inversion method named Convolutional Variational AutoEncoder—Ensemble Smoother with Multiple Data Assimilation (CVAE‐ESMDA) with a process‐based (PB) upscaled mass‐transfer model. This framework can utilize sparse SZ data to estimate directly mass discharge without multiphase modeling. First, CVAE‐ESMDA estimates the SZA by conditioning on sparse data, which is then used as input in the upscaled model for mass‐discharge estimation. We evaluated our framework on two real and 30 synthetic bench‐scale experiments, with significantly different SZAs and multistage effluent concentrations. The results demonstrate that the CVAE‐based inversion method captures the temporal variations in SZ metrics better than standard ordinary kriging. With the improved SZ metrics, the PB model more accurately reproduces the salient patterns of the multistage mass‐discharge profiles and associated uncertainty. This approach can be used to provide valuable input for risk‐based decision making in remediation applications. Key Points We propose a framework to estimate mass discharge from complex dense nonaqueous phase liquid (DNAPL) source zones (SZ) using sparse monitoring data The proposed framework outperforms standard kriging method in characterizing the SZ metrics controlling mass‐transfer kinetics Combining the improved SZ metrics with an upscaled model allows better reproduction of multistage DNAPL mass discharge
AbstractList	The challenges posed by high‐resolution characterization of dense nonaqueous phase liquid (DNAPL) source zone architecture (SZA) have motivated the development of simpler upscaled models that rely on domain‐averaged metrics to capture the average mass discharge downstream of source zones (SZ). However, SZA is highly irregular, making estimation of these domain‐averaged metrics from sparse borehole data extremely difficult. Poor estimation of SZ metrics means that upscaled models cannot reproduce the multistage effluent concentrations. Bayesian inversion methods can be used to obtain accurate estimates of SZ metrics and their uncertainties from sparse data, and from there, upscaled models can better reproduce multistage effluent concentrations. This work presents a framework for integrating a deep‐learning‐based 3D SZA inversion method named Convolutional Variational AutoEncoder—Ensemble Smoother with Multiple Data Assimilation (CVAE‐ESMDA) with a process‐based (PB) upscaled mass‐transfer model. This framework can utilize sparse SZ data to estimate directly mass discharge without multiphase modeling. First, CVAE‐ESMDA estimates the SZA by conditioning on sparse data, which is then used as input in the upscaled model for mass‐discharge estimation. We evaluated our framework on two real and 30 synthetic bench‐scale experiments, with significantly different SZAs and multistage effluent concentrations. The results demonstrate that the CVAE‐based inversion method captures the temporal variations in SZ metrics better than standard ordinary kriging. With the improved SZ metrics, the PB model more accurately reproduces the salient patterns of the multistage mass‐discharge profiles and associated uncertainty. This approach can be used to provide valuable input for risk‐based decision making in remediation applications. The challenges posed by high‐resolution characterization of dense nonaqueous phase liquid (DNAPL) source zone architecture (SZA) have motivated the development of simpler upscaled models that rely on domain‐averaged metrics to capture the average mass discharge downstream of source zones (SZ). However, SZA is highly irregular, making estimation of these domain‐averaged metrics from sparse borehole data extremely difficult. Poor estimation of SZ metrics means that upscaled models cannot reproduce the multistage effluent concentrations. Bayesian inversion methods can be used to obtain accurate estimates of SZ metrics and their uncertainties from sparse data, and from there, upscaled models can better reproduce multistage effluent concentrations. This work presents a framework for integrating a deep‐learning‐based 3D SZA inversion method named Convolutional Variational AutoEncoder—Ensemble Smoother with Multiple Data Assimilation (CVAE‐ESMDA) with a process‐based (PB) upscaled mass‐transfer model. This framework can utilize sparse SZ data to estimate directly mass discharge without multiphase modeling. First, CVAE‐ESMDA estimates the SZA by conditioning on sparse data, which is then used as input in the upscaled model for mass‐discharge estimation. We evaluated our framework on two real and 30 synthetic bench‐scale experiments, with significantly different SZAs and multistage effluent concentrations. The results demonstrate that the CVAE‐based inversion method captures the temporal variations in SZ metrics better than standard ordinary kriging. With the improved SZ metrics, the PB model more accurately reproduces the salient patterns of the multistage mass‐discharge profiles and associated uncertainty. This approach can be used to provide valuable input for risk‐based decision making in remediation applications. We propose a framework to estimate mass discharge from complex dense nonaqueous phase liquid (DNAPL) source zones (SZ) using sparse monitoring data The proposed framework outperforms standard kriging method in characterizing the SZ metrics controlling mass‐transfer kinetics Combining the improved SZ metrics with an upscaled model allows better reproduction of multistage DNAPL mass discharge The challenges posed by high‐resolution characterization of dense nonaqueous phase liquid (DNAPL) source zone architecture (SZA) have motivated the development of simpler upscaled models that rely on domain‐averaged metrics to capture the average mass discharge downstream of source zones (SZ). However, SZA is highly irregular, making estimation of these domain‐averaged metrics from sparse borehole data extremely difficult. Poor estimation of SZ metrics means that upscaled models cannot reproduce the multistage effluent concentrations. Bayesian inversion methods can be used to obtain accurate estimates of SZ metrics and their uncertainties from sparse data, and from there, upscaled models can better reproduce multistage effluent concentrations. This work presents a framework for integrating a deep‐learning‐based 3D SZA inversion method named Convolutional Variational AutoEncoder—Ensemble Smoother with Multiple Data Assimilation (CVAE‐ESMDA) with a process‐based (PB) upscaled mass‐transfer model. This framework can utilize sparse SZ data to estimate directly mass discharge without multiphase modeling. First, CVAE‐ESMDA estimates the SZA by conditioning on sparse data, which is then used as input in the upscaled model for mass‐discharge estimation. We evaluated our framework on two real and 30 synthetic bench‐scale experiments, with significantly different SZAs and multistage effluent concentrations. The results demonstrate that the CVAE‐based inversion method captures the temporal variations in SZ metrics better than standard ordinary kriging. With the improved SZ metrics, the PB model more accurately reproduces the salient patterns of the multistage mass‐discharge profiles and associated uncertainty. This approach can be used to provide valuable input for risk‐based decision making in remediation applications. Key Points We propose a framework to estimate mass discharge from complex dense nonaqueous phase liquid (DNAPL) source zones (SZ) using sparse monitoring data The proposed framework outperforms standard kriging method in characterizing the SZ metrics controlling mass‐transfer kinetics Combining the improved SZ metrics with an upscaled model allows better reproduction of multistage DNAPL mass discharge
Author	Kang, Xueyuan Yoon, Hongkyu Shi, Xiaoqing Kokkinaki, Amalia Lee, Jonghyun Kitanidis, Peter K. Wu, Jichun
Author_xml	– sequence: 1 givenname: Xueyuan orcidid: 0000-0002-8359-8479 surname: Kang fullname: Kang, Xueyuan organization: Nanjing University – sequence: 2 givenname: Amalia orcidid: 0000-0002-8166-0371 surname: Kokkinaki fullname: Kokkinaki, Amalia organization: University of San Francisco – sequence: 3 givenname: Xiaoqing orcidid: 0000-0002-5074-8856 surname: Shi fullname: Shi, Xiaoqing email: shixq@nju.edu.cn organization: Nanjing University – sequence: 4 givenname: Hongkyu orcidid: 0000-0001-6719-280X surname: Yoon fullname: Yoon, Hongkyu organization: Sandia National Laboratories – sequence: 5 givenname: Jonghyun orcidid: 0000-0002-3646-2915 surname: Lee fullname: Lee, Jonghyun organization: University of Hawaii at Manoa – sequence: 6 givenname: Peter K. surname: Kitanidis fullname: Kitanidis, Peter K. organization: Stanford University – sequence: 7 givenname: Jichun orcidid: 0000-0001-9799-6745 surname: Wu fullname: Wu, Jichun email: jcwu@nju.edu.cn organization: Nanjing University
BookMark	eNp9kc9uEzEQxi1UpKaFGw9giQsHFvwv6_UxTQpESimKWvW48u6Ow1YbO3icVrnxCIhH5ElwGyqhSu1ppG9-M_PNzBE58MEDIW84-8CZMB8FE-JqyaQUWr8gI26UKrTR8oCMGFOy4NLoQ3KEeM0YV-NSj8jvuU-wijb1wdPg6AxgQxdgo-_96s_PXycWoaNzfwMR7xDrO3q5wdYOWT6ziJm5iNajg0jPQgcDdSHS2dfJt8VDftZj-93GFdBTTP16P-u-kW8hJtv7tKMTREBcg0-vyEtnB4TX_-Ixufx0ejH9UizOP8-nk0VhZSl5oVVlK8FKzjRTRmvXGKcYgHGic23Hx1lmjZM5KVzVjBkH3VSi7ca6acuuk8fk3b7vJoYfW8BUr7NRGAbrIWyxFhXnRnNmTEbfPkKvwzb67K4WWlRKK1OJTL3fU20MiBFcvYl53birOavvHlT__6CMi0d426f746Ro--GpIrkvuu0H2D07oL5aTpeiFJrLv2q_p1Y
CitedBy_id	crossref_primary_10_1016_j_enggeo_2025_107998 crossref_primary_10_1016_j_jhazmat_2025_139321 crossref_primary_10_1016_j_jconhyd_2024_104452 crossref_primary_10_1007_s11356_024_33405_8 crossref_primary_10_1016_j_advwatres_2024_104677 crossref_primary_10_1016_j_jenvman_2023_118817 crossref_primary_10_1016_j_watres_2023_120649
Cites_doi	10.1016/j.jconhyd.2020.103716 10.1029/2019WR026082 10.1029/2004WR003239 10.1029/2021wr029754 10.1029/2006WR004877 10.1007/978-1-4614-2239-6_10 10.1016/j.advwatres.2017.09.029 10.1016/j.jhydrol.2020.125443 10.1017/CBO9780511626166 10.1021/es032488k 10.1021/es061675q 10.1016/j.jconhyd.2017.01.002 10.1016/j.jconhyd.2010.02.005 10.1029/2019WR026481 10.1002/wrcr.20503 10.1002/2013WR013796 10.1029/2003WR002807 10.1016/j.jconhyd.2021.103920 10.1016/j.jappgeo.2014.10.022 10.1111/j.1745-6584.2004.tb02667.x 10.1016/S0169-7722(03)00142-6 10.1016/j.jconhyd.2003.11.002 10.1029/2020WR028538 10.1029/2004WR003214 10.1021/es101654j 10.1029/2007WR006213 10.1029/2020WR027627 10.1029/2006WR005427 10.1016/j.cageo.2019.04.006 10.1016/j.jconhyd.2006.09.004 10.1029/wr025i007p01727 10.1190/geo2019-0019.1 10.1016/j.jconhyd.2008.05.007 10.1002/2015WR018483 10.1016/s0169-7722(01)00177-2 10.1016/j.jhydrol.2021.126655 10.1029/2012WR012149 10.1029/2020WR027399 10.1016/j.jhydrol.2018.10.019 10.1002/2015WR017894 10.1016/j.cageo.2012.03.011 10.1111/j.1745-6584.2005.tb02287.x 10.1029/97WR03754 10.1029/2002wr001570 10.1016/j.jconhyd.2018.02.003 10.1029/2003wr001980 10.1002/2014WR015478 10.1002/2013WR014663 10.1029/2006WR004886 10.1016/s0169-7722(99)00092-3 10.1029/2008WR007009 10.1016/j.jhydrol.2016.11.036
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
DOI	10.1029/2022WR033277
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
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	Civil Engineering Abstracts CrossRef AGRICOLA
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography Economics
EISSN	1944-7973
EndPage	n/a
ExternalDocumentID	10_1029_2022WR033277 WRCR26271
Genre	article
GrantInformation_xml	– fundername: Jiangsu Funding Program for Excellent Postdoctoral Talent funderid: 20220ZB15 – fundername: National Science Foundation's Research Infrastructure Improvement funderid: OIA‐1557349 – fundername: Laboratory Directed Research and Development program at Sandia National Laboratories – fundername: China Postdoctoral Science Foundation funderid: 2022M711565 – fundername: National Natural Science Foundation of China funderid: 41730856; 41977157; 42202267
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
ID	FETCH-LOGICAL-a3631-748a820610704977fb9f40ee9f2dfcd157040bf30492f8b501e7b82cd57bc6dd3
IEDL.DBID	DRFUL
ISICitedReferencesCount	9
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000871486400001&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	Fri Sep 05 17:25:21 EDT 2025 Wed Aug 13 09:03:31 EDT 2025 Sat Nov 29 01:36:50 EST 2025 Tue Nov 18 19:41:24 EST 2025 Wed Jan 22 16:22:04 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	10
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-a3631-748a820610704977fb9f40ee9f2dfcd157040bf30492f8b501e7b82cd57bc6dd3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-3646-2915 0000-0001-6719-280X 0000-0002-5074-8856 0000-0002-8166-0371 0000-0002-8359-8479 0000-0001-9799-6745
PQID	2728474982
PQPubID	105507
PageCount	21
ParticipantIDs	proquest_miscellaneous_2811971099 proquest_journals_2728474982 crossref_primary_10_1029_2022WR033277 crossref_citationtrail_10_1029_2022WR033277 wiley_primary_10_1029_2022WR033277_WRCR26271
PublicationCentury	2000
PublicationDate	October 2022 2022-10-00 20221001
PublicationDateYYYYMMDD	2022-10-01
PublicationDate_xml	– month: 10 year: 2022 text: October 2022
PublicationDecade	2020
PublicationPlace	Washington
PublicationPlace_xml	– name: Washington
PublicationTitle	Water resources research
PublicationYear	2022
Publisher	John Wiley & Sons, Inc
Publisher_xml	– name: John Wiley & Sons, Inc
References	2009; 45 2018; 567 2004; 68 2000; 42 2020; 56 2019; 128 2017; 110 2017; 198 2008; 102 2022; 244 2004; 72 2013; 55 2010; 114 2018; 211 2021b; 601 2021a; 57 2014; 50 2001; 53 2004; 42 2004; 40 2013; 49 2012 2011 2020; 85 2015; 51 1998 2007; 90 2005; 41 1997 2016; 52 1996 2003; 37 2005; 43 2003; 39 2003 1989; 25 2010; 44 2021; 57 2006; 42 2015; 112 2020; 590 2016 2008; 44 2020; 235 2014 2013 2012; 48 2007; 41 2007; 43 2017; 544 1998; 34 e_1_2_8_28_1 e_1_2_8_24_1 e_1_2_8_26_1 e_1_2_8_49_1 Deutsch C. V. (e_1_2_8_15_1) 1998 e_1_2_8_3_1 e_1_2_8_5_1 Pankow J. F. (e_1_2_8_47_1) 1996 e_1_2_8_7_1 e_1_2_8_9_1 e_1_2_8_20_1 e_1_2_8_43_1 e_1_2_8_45_1 e_1_2_8_41_1 e_1_2_8_60_1 e_1_2_8_17_1 e_1_2_8_13_1 Kavanaugh M. C. (e_1_2_8_29_1) 2003 e_1_2_8_36_1 e_1_2_8_59_1 e_1_2_8_38_1 e_1_2_8_57_1 e_1_2_8_32_1 e_1_2_8_55_1 e_1_2_8_11_1 e_1_2_8_34_1 e_1_2_8_53_1 e_1_2_8_51_1 e_1_2_8_30_1 e_1_2_8_25_1 e_1_2_8_46_1 e_1_2_8_27_1 e_1_2_8_48_1 e_1_2_8_2_1 e_1_2_8_4_1 e_1_2_8_6_1 e_1_2_8_8_1 Illman W. (e_1_2_8_22_1) 2011 e_1_2_8_21_1 e_1_2_8_42_1 e_1_2_8_23_1 e_1_2_8_44_1 e_1_2_8_40_1 e_1_2_8_61_1 e_1_2_8_18_1 e_1_2_8_39_1 e_1_2_8_14_1 e_1_2_8_35_1 e_1_2_8_16_1 e_1_2_8_37_1 e_1_2_8_58_1 e_1_2_8_10_1 Goodfellow I. (e_1_2_8_19_1) 2016 e_1_2_8_31_1 e_1_2_8_56_1 e_1_2_8_12_1 e_1_2_8_33_1 e_1_2_8_54_1 e_1_2_8_52_1 e_1_2_8_50_1
References_xml	– start-page: 450 year: 2011 – start-page: 239 year: 2012 end-page: 276 – volume: 114 start-page: 18 issue: 1–4 year: 2010 end-page: 34 article-title: Predicting DNAPL mass discharge from pool‐dominated source zones publication-title: Journal of Contaminant Hydrology – volume: 48 issue: 10 year: 2012 article-title: Highly parameterized inverse estimation of hydraulic conductivity and porosity in a three‐dimensional, heterogeneous transport experiment publication-title: Water Resources Research – volume: 56 issue: 8 year: 2020 article-title: Improved characterization of DNAPL source zones via sequential hydrogeophysical inversion of hydraulic‐head, self‐potential and partitioning‐tracer data publication-title: Water Resources Research – volume: 42 start-page: 187 issue: 2 year: 2000 end-page: 218 article-title: The influence of field‐scale heterogeneity on the infiltration and entrapment of dense nonaqueous phase liquids in saturated formations publication-title: Journal of Contaminant Hydrology – volume: 112 start-page: 1 year: 2015 end-page: 13 article-title: Improved time‐lapse electrical resistivity tomography monitoring of dense nonaqueous phase liquids with surface‐to‐horizontal borehole arrays publication-title: Journal of Applied Geophysics – volume: 57 issue: 11 year: 2021 article-title: Deep convolutional autoencoders for robust flow model calibration under uncertainty in geologic continuity publication-title: Water Resources Research – volume: 42 start-page: 190 issue: 2 year: 2004 end-page: 202 article-title: Spatial interpolation methods for nonstationary plume data publication-title: Ground Water – volume: 44 start-page: 8609 issue: 22 year: 2010 end-page: 8614 article-title: Hydraulic/partitioning tracer tomography for DNAPL source zone characterization: Small‐scale sandbox experiments publication-title: Environmental Science & Technology – volume: 211 start-page: 1 year: 2018 end-page: 14 article-title: Modeling the influence of coupled mass transfer processes on mass flux downgradient of heterogeneous DNAPL source zones publication-title: Journal of Contaminant Hydrology – volume: 198 start-page: 37 year: 2017 end-page: 47 article-title: Field data and numerical simulation of btex concentration trends under water table fluctuations: Example of a jet fuel‐contaminated site in Brazil publication-title: Journal of Contaminant Hydrology – volume: 68 start-page: 1 issue: 1 year: 2004 end-page: 22 article-title: Noninvasive monitoring of DNAPL migration through a saturated porous medium using electrical impedance tomography publication-title: Journal of Contaminant Hydrology – volume: 56 issue: 12 year: 2020 article-title: Using deep learning to improve ensemble smoother: Applications to subsurface characterization publication-title: Water Resources Research – year: 2014 – volume: 37 start-page: 224A issue: 11 year: 2003 end-page: 230A article-title: Remediating chlorinated solvent source zones publication-title: Environmental Science & Technology – year: 1998 – volume: 57 issue: 2 year: 2021a article-title: Hydrogeophysical characterization of nonstationary DNAPL source zones by integrating a convolutional variational autoencoder and ensemble smoother publication-title: Water Resources Research – volume: 41 start-page: 3672 issue: 10 year: 2007 end-page: 3678 article-title: Characterization of NAPL source zone architecture and dissolution kinetics in heterogeneous porous media using magnetic resonance imaging publication-title: Environmental Science & Technology – volume: 40 issue: 5 year: 2004 article-title: Modeling field‐scale dense nonaqueous phase liquid dissolution kinetics in heterogeneous aquifers publication-title: Water Resources Research – volume: 49 start-page: 7023 issue: 10 year: 2013 end-page: 7036 article-title: Coupled simulation of DNAPL infiltration and dissolution in three‐dimensional heterogeneous domains: Process model validation publication-title: Water Resources Research – volume: 590 year: 2020 article-title: Coupling ensemble smoother and deep learning with generative adversarial networks to deal with non‐Gaussianity in flow and transport data assimilation publication-title: Journal of Hydrology – volume: 55 start-page: 3 issue: 3 year: 2013 end-page: 15 article-title: Ensemble smoother with multiple data assimilation publication-title: Computers & Geosciences – year: 1997 – volume: 85 start-page: M15 issue: 1 year: 2020 end-page: M31 article-title: Time‐lapse seismic history matching with an iterative ensemble smoother and deep convolutional autoencoder publication-title: Geophysics – volume: 56 issue: 3 year: 2020 article-title: Subsurface source zone characterization and uncertainty quantification using discriminative random fields publication-title: Water Resources Research – volume: 128 start-page: 87 year: 2019 end-page: 102 article-title: Towards a robust parameterization for conditioning facies models using deep variational autoencoders and ensemble smoother publication-title: Computers & Geosciences – volume: 56 issue: 2 year: 2020 article-title: Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non‐Gaussian hydraulic conductivities publication-title: Water Resources Research – volume: 42 issue: 11 year: 2006 article-title: Estimating mass discharge from dense nonaqueous phase liquid source zones using upscaled mass transfer coefficients: An evaluation using multiphase numerical simulations publication-title: Water Resources Research – volume: 25 start-page: 1727 issue: 7 year: 1989 end-page: 1736 article-title: A model for hysteretic constitutive relations governing multiphase flow: 3. Refinements and numerical simulations publication-title: Water Resources Research – volume: 102 start-page: 49 issue: 1–2 year: 2008 end-page: 60 article-title: Evaluation of simplified mass transfer models to simulate the impacts of source zone architecture on nonaqueous phase liquid dissolution in heterogeneous porous media publication-title: Journal of Contaminant Hydrology – volume: 53 start-page: 429 issue: 3–4 year: 2001 end-page: 453 article-title: An analytical quantification of mass fluxes and natural attenuation rate constants at a former gasworks site publication-title: Journal of Contaminant Hydrology – volume: 34 start-page: 611 issue: 4 year: 1998 end-page: 622 article-title: A generalized growth model for simulating initial migration of dense nonaqueous phase liquids publication-title: Water Resources Research – volume: 544 start-page: 254 year: 2017 end-page: 266 article-title: Quantitative assessment of electrical resistivity tomography for monitoring DNAPLs migration—Comparison with high‐resolution light transmission visualization in laboratory sandbox publication-title: Journal of Hydrology – volume: 39 issue: 10 year: 2003 article-title: Influence of constitutive model parameters on the predicted migration of DNAPL in heterogeneous porous media publication-title: Water Resources Research – volume: 244 year: 2022 article-title: Upscaled modeling of complex DNAPL dissolution publication-title: Journal of Contaminant Hydrology – volume: 52 start-page: 1009 issue: 2 year: 2016 end-page: 1025 article-title: Identification of contaminant source architectures‐A statistical inversion that emulates multiphase physics in a computationally practicable manner publication-title: Water Resources Research – year: 2003 – volume: 72 start-page: 245 issue: 1–4 year: 2004 end-page: 258 article-title: Simple screening models of NAPL dissolution in the subsurface publication-title: Journal of Contaminant Hydrology – year: 1996 – volume: 50 start-page: 1374 issue: 2 year: 2014 end-page: 1395 article-title: A method for implementing Dirichlet and third‐type boundary conditions in PTRW simulations publication-title: Water Resources Research – volume: 52 start-page: 5213 issue: 7 year: 2016 end-page: 5231 article-title: Scalable subsurface inverse modeling of huge data sets with an application to tracer concentration breakthrough data from magnetic resonance imaging publication-title: Water Resources Research – year: 2016 – volume: 45 issue: 8 year: 2009 article-title: Interphase mass transfer in variable aperture fractures: Controlling parameters and proposed constitutive relationships publication-title: Water Resources Research – volume: 43 issue: 6 year: 2007 article-title: Hydraulic/partitioning tracer tomography for characterization of dense nonaqueous phase liquid source zones publication-title: Water Resources Research – volume: 43 issue: 6 year: 2007 article-title: A geostatistical approach for quantification of contaminant mass discharge uncertainty using multilevel sampler measurements publication-title: Water Resources Research – volume: 40 issue: 1 year: 2004 article-title: DNAPL source zone characterization: Influence of hydraulic property correlation on predictions of DNAPL infiltration and entrapment publication-title: Water Resources Research – volume: 44 issue: 6 year: 2008 article-title: Numerical simulation of water flow in three dimensional heterogeneous porous media observed in a magnetic resonance imaging experiment publication-title: Water Resources Research – volume: 601 year: 2021b article-title: Integrating deep learning‐based data assimilation and hydrogeophysical data for improved monitoring of DNAPL source zones during remediation publication-title: Journal of Hydrology – volume: 43 start-page: 70 issue: 1 year: 2005 end-page: 86 article-title: Mass and flux distributions from DNAPL zones in sandy aquifers publication-title: Ground Water – volume: 51 start-page: 806 issue: 2 year: 2015 end-page: 831 article-title: Predicting DNAPL mass discharge and contaminated site longevity probabilities: Conceptual model and high‐resolution stochastic simulation publication-title: Water Resources Research – volume: 40 issue: 8 year: 2004 article-title: Estimation of historical groundwater contaminant distribution using the adjoint state method applied to geostatistical inverse modeling publication-title: Water Resources Research – volume: 235 year: 2020 article-title: Mathematical modeling of organic liquid dissolution in heterogeneous source zones publication-title: Journal of Contaminant Hydrology – volume: 567 start-page: 149 year: 2018 end-page: 164 article-title: Coupled hydrogeophysical inversion of DNAPL source zone architecture and permeability field in a 3D heterogeneous sandbox by assimilation time‐lapse cross‐borehole electrical resistivity data via ensemble Kalman filtering publication-title: Journal of Hydrology – volume: 50 start-page: 3187 issue: 4 year: 2014 end-page: 3205 article-title: Comparison of upscaled models for multistage mass discharge from DNAPL source zones publication-title: Water Resources Research – volume: 110 start-page: 387 year: 2017 end-page: 405 article-title: Inversion using a new low‐dimensional representation of complex binary geological media based on a deep neural network publication-title: Advances in Water Resources – volume: 90 start-page: 21 issue: 1 year: 2007 end-page: 40 article-title: Source‐zone characterization of a chlorinated‐solvent contaminated superfund site in Tucson, AZ publication-title: Journal of Contaminant Hydrology – volume: 41 issue: 1 year: 2005 article-title: Comparison of two‐dimensional and three‐dimensional simulations of dense nonaqueous phase liquids (DNAPLs): Migration and entrapment in a nonuniform permeability field publication-title: Water Resources Research – year: 2013 – ident: e_1_2_8_21_1 doi: 10.1016/j.jconhyd.2020.103716 – ident: e_1_2_8_45_1 doi: 10.1029/2019WR026082 – ident: e_1_2_8_9_1 doi: 10.1029/2004WR003239 – volume-title: Deep learning year: 2016 ident: e_1_2_8_19_1 – ident: e_1_2_8_24_1 doi: 10.1029/2021wr029754 – ident: e_1_2_8_31_1 – ident: e_1_2_8_55_1 doi: 10.1029/2006WR004877 – ident: e_1_2_8_2_1 doi: 10.1007/978-1-4614-2239-6_10 – ident: e_1_2_8_38_1 doi: 10.1016/j.advwatres.2017.09.029 – ident: e_1_2_8_4_1 doi: 10.1016/j.jhydrol.2020.125443 – ident: e_1_2_8_32_1 doi: 10.1017/CBO9780511626166 – ident: e_1_2_8_52_1 doi: 10.1021/es032488k – ident: e_1_2_8_58_1 doi: 10.1021/es061675q – ident: e_1_2_8_53_1 doi: 10.1016/j.jconhyd.2017.01.002 – ident: e_1_2_8_11_1 doi: 10.1016/j.jconhyd.2010.02.005 – ident: e_1_2_8_3_1 doi: 10.1029/2019WR026481 – ident: e_1_2_8_36_1 doi: 10.1002/wrcr.20503 – ident: e_1_2_8_33_1 doi: 10.1002/2013WR013796 – ident: e_1_2_8_48_1 doi: 10.1029/2003WR002807 – ident: e_1_2_8_51_1 doi: 10.1016/j.jconhyd.2021.103920 – ident: e_1_2_8_49_1 doi: 10.1016/j.jappgeo.2014.10.022 – ident: e_1_2_8_50_1 doi: 10.1111/j.1745-6584.2004.tb02667.x – ident: e_1_2_8_8_1 doi: 10.1016/S0169-7722(03)00142-6 – ident: e_1_2_8_61_1 doi: 10.1016/j.jconhyd.2003.11.002 – ident: e_1_2_8_25_1 doi: 10.1029/2020WR028538 – ident: e_1_2_8_44_1 doi: 10.1029/2004WR003214 – ident: e_1_2_8_23_1 doi: 10.1021/es101654j – ident: e_1_2_8_57_1 doi: 10.1029/2007WR006213 – ident: e_1_2_8_26_1 doi: 10.1029/2020WR027627 – ident: e_1_2_8_42_1 doi: 10.1029/2006WR005427 – ident: e_1_2_8_7_1 doi: 10.1016/j.cageo.2019.04.006 – ident: e_1_2_8_6_1 doi: 10.1016/j.jconhyd.2006.09.004 – start-page: 450 volume-title: Fusion of tomography tests for DNAPL source zone characterization: Technology development and validation (Final Report No. Project ER‐1365) year: 2011 ident: e_1_2_8_22_1 – ident: e_1_2_8_41_1 doi: 10.1029/wr025i007p01727 – ident: e_1_2_8_43_1 doi: 10.1190/geo2019-0019.1 – volume-title: Geostatistical software library and user's guide year: 1998 ident: e_1_2_8_15_1 – ident: e_1_2_8_59_1 doi: 10.1016/j.jconhyd.2008.05.007 – ident: e_1_2_8_39_1 doi: 10.1002/2015WR018483 – ident: e_1_2_8_5_1 doi: 10.1016/s0169-7722(01)00177-2 – ident: e_1_2_8_27_1 doi: 10.1016/j.jhydrol.2021.126655 – ident: e_1_2_8_56_1 doi: 10.1029/2012WR012149 – volume-title: Dense chlorinated solvents and other DNAPLs in groundwater: History, behavior, and remediation year: 1996 ident: e_1_2_8_47_1 – ident: e_1_2_8_60_1 doi: 10.1029/2020WR027399 – ident: e_1_2_8_28_1 doi: 10.1016/j.jhydrol.2018.10.019 – ident: e_1_2_8_35_1 doi: 10.1002/2015WR017894 – ident: e_1_2_8_16_1 doi: 10.1016/j.cageo.2012.03.011 – volume-title: The DNAPL remediation challenge: Is there a case for source depletion? year: 2003 ident: e_1_2_8_29_1 – ident: e_1_2_8_20_1 doi: 10.1111/j.1745-6584.2005.tb02287.x – ident: e_1_2_8_17_1 doi: 10.1029/97WR03754 – ident: e_1_2_8_18_1 doi: 10.1029/2002wr001570 – ident: e_1_2_8_54_1 doi: 10.1016/j.jconhyd.2018.02.003 – ident: e_1_2_8_40_1 doi: 10.1029/2003wr001980 – ident: e_1_2_8_46_1 – ident: e_1_2_8_30_1 – ident: e_1_2_8_34_1 doi: 10.1002/2014WR015478 – ident: e_1_2_8_37_1 doi: 10.1002/2013WR014663 – ident: e_1_2_8_10_1 doi: 10.1029/2006WR004886 – ident: e_1_2_8_12_1 doi: 10.1016/s0169-7722(99)00092-3 – ident: e_1_2_8_14_1 doi: 10.1029/2008WR007009 – ident: e_1_2_8_13_1 doi: 10.1016/j.jhydrol.2016.11.036
SSID	ssj0014567
Score	2.4428172
Snippet	The challenges posed by high‐resolution characterization of dense nonaqueous phase liquid (DNAPL) source zone architecture (SZA) have motivated the development...
SourceID	proquest crossref wiley
SourceType	Aggregation Database Enrichment Source Index Database Publisher
SubjectTerms	3D DNAPL characterization Bayesian analysis Bayesian theory Boreholes convolutional variational autoencoder Data assimilation Data collection Decision making Deep learning Discharge DNAPL mass discharge Domains Effluents Estimates Frameworks kriging Mass mass transfer Mathematical models Modelling multistage dissolution Nonaqueous phase liquids Probability theory remediation Statistical methods Temporal variations Uncertainty upscaled modeling water
Title	Integration of Deep Learning‐Based Inversion and Upscaled Mass‐Transfer Model for DNAPL Mass‐Discharge Estimation and Uncertainty Assessment
URI	https://onlinelibrary.wiley.com/doi/abs/10.1029%2F2022WR033277 https://www.proquest.com/docview/2728474982 https://www.proquest.com/docview/2811971099
Volume	58
WOSCitedRecordID	wos000871486400001&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 - Journals 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 – providerCode: PRVWIB databaseName: Wiley Online Library Free Content customDbUrl: eissn: 1944-7973 dateEnd: 20231214 omitProxy: false ssIdentifier: ssj0014567 issn: 0043-1397 databaseCode: WIN dateStart: 19970101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fT9swELcGTBovwP4gCgx50va0VUscN3YeC6UaEqtQtaq8RfG_DQmlVVOQeOMjoH3EfRLuHCfrHoY07S2yL3YUn32_89m_I-R9z1hVRDruWqZ4l-MxV6nBWeFpJIvIWKsj45NNiNFIXl5mF2HDDe_C1PwQ7YYbzgy_XuMEL1QVyAaQIxO8djYdR0nChFgjG3ivCpyvjcF4ODlv4wgAD0QTY0asE46-QwufV9__0yj9RpqreNUbnOH2_37qDtkKUJP2a914SZ7Z8hV50dxEruA5ZED_cfea_DwLvBEwTnTm6MDaOQ3kq99_3T8cg7UzFFk5_P4aLUpDJ_MKRhiKvwICBxlv95xdUEywdk0BDtPBqH9x3tQPripPzGTpKSws9Z3JuiHQPH8yYXlH-y1V6BsyGZ5-O_nSDfkaukWSJjHSkhZIBw8eJfgdQjiVOR5ZmzlmnDZxD4oj5TCwx5xUvSi2QkmmTU8onRqT7JL1clbaPUJ5wh2sPHHKlOJapgpwH6hPUgB6k4azDvnYDFiuA5k55tS4zn1QnWX56j_vkA-t9Lwm8fiL3GEz9nmYylXOBFpwnkno9F1bDZMQIytFaWc3ICMxGotBxg755DXhyX7y6fhkzFIm4v1_Ez8gm1hRHyY8JOvLxY19S57r2-VVtTgKyn9E1qZno0daYgb7
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fb9MwED9BhzRe-I8oDDASPEFF4rix81jWVZvoqqlatb1F8Z_ApCmtmg5pb3wExEfkk3DnOKE8gIR4i-yLHcU-3-989u8AXg-t00Vk4oHjWgwEHXNVBp0VkUaqiKxzJrI-2YSczdT5eXYS8pzSXZiGH6LbcCPN8Os1KThtSAe2ASLJRLedn82jJOFS3oQdkSZS9WBnPJ8spl0gAfGBbIPMBHbC2Xds4f32-79bpV9Qcxuweoszufvf33oP7gSwyUbN7LgPN1z1AHbbu8g1Pocc6J-vH8L3o8AcgSPFliUbO7digX7104-v3z6gvbOMeDn8DhsrKssWqxrHGIuPEYOjjLd8pVszSrF2yRAQs_FsdDJt68cXtadmcuwAl5bm1mTTEM49fzZhc81GHVnoI1hMDk73DwchY8OgSNIkJmLSggjh0adEz0PKUmeliJzLSm5LY-MhFke6pNAeL5UeRrGTWnFjh1Kb1NrkMfSqZeWeABOJKHHtiVOutTAq1Yj8cAIlBeI3ZQXvw9t2xHIT6Mwpq8Zl7sPqPMu3_3kf3nTSq4bG4w9ye-3g50GZ65xLsuEiU9jpq64a1ZBiK0XlllcooygeS2HGPrzzU-Gv_eRn8_05T7mMn_6b-EvYPTw9nubTo9nHZ3CbhJqjhXvQ26yv3HO4Zb5sLur1i6AJPwHlSQnc
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fb9MwELfGQLAX_qN1DDASPEFF4rix81jWVVSMqKqYurco_rdNmtKq6ZD2xkeY-Ih8Eu4cJ5SHISHeouRiRzmf72ff-XeEvBkYq8pIx33LFO9zTHOVGhYrPI1kGRlrdWR8sQmR5_LkJJuGOqd4Fqbhh-g23NAy_HyNBm6XxgW2ASTJhGU7m8-iJGFC3CK3ofUUc7rmk7wLIwA6EG2IGaFOyHyH9z9svv2nT_oNNDfhqvc34wf__aUPyf0ANemwGRuPyJatHpN77UnkGq5DBfSzqyfkxyTwRoCe6MLRkbVLGshXT39-v_4I3s5QZOXw-2u0rAw9XtagYbj9BRA4yHi_5-yKYoG1CwpwmI7y4fSofT46rz0xk6WHMLE0ZyabhmDk-cyE9RUddlShT8nx-PDrwad-qNfQL5M0iZGWtEQ6eFhRwrpDCKcyxyNrM8eM0yYewO1IOQzsMSfVIIqtUJJpMxBKp8Ykz8h2tajsLqE84Q5mnjhlSnEtUwW4DxSclIDepOGsR961Git0IDPHmhoXhQ-qs6zY_Oc98raTXjYkHjfI7bfKL4Ip1wUT6MF5JqHT191jMEKMrJSVXVyCjMRoLAYZe-S9Hwp_7aeYzw5mLGUi3vs38Vfk7nQ0Lo4m-efnZAdlmrzCfbK9Xl3aF-SO_rY-r1cvvRn8AkbsCDI
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=Integration+of+Deep+Learning%E2%80%90Based+Inversion+and+Upscaled+Mass%E2%80%90Transfer+Model+for+DNAPL+Mass%E2%80%90Discharge+Estimation+and+Uncertainty+Assessment&rft.jtitle=Water+resources+research&rft.au=Kang%2C+Xueyuan&rft.au=Kokkinaki%2C+Amalia&rft.au=Shi%2C+Xiaoqing&rft.au=Yoon%2C+Hongkyu&rft.date=2022-10-01&rft.issn=0043-1397&rft.volume=58&rft.issue=10+p.e2022WR033277-&rft_id=info:doi/10.1029%2F2022WR033277&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