Comparing Physics‐Based, Conceptual and Machine‐Learning Models to Predict Groundwater Levels by BMA
Groundwater level observations are used as decision variables for aquifer management, often in conjunction with models to provide predictions for operational forecasting. In this study, we compare different model classes for this task: a spatially explicit 3D groundwater flow model (MODFLOW), an eig...
Uloženo v:
| Vydáno v: | Ground water Ročník 63; číslo 4; s. 484 - 505 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Malden, US
Blackwell Publishing Ltd
01.07.2025
Ground Water Publishing Company |
| Témata: | |
| ISSN: | 0017-467X, 1745-6584, 1745-6584 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Groundwater level observations are used as decision variables for aquifer management, often in conjunction with models to provide predictions for operational forecasting. In this study, we compare different model classes for this task: a spatially explicit 3D groundwater flow model (MODFLOW), an eigenmodel, a transfer‐function model, and three machine learning models, namely, multi‐layer perceptron models, long short‐term memory models, and random forest models. The models differ widely in their complexity, input requirements, calibration effort, and run‐times. They are tested on four groundwater level time series from the Wairau Aquifer in New Zealand to investigate the potential of the data‐driven approaches to outperform the MODFLOW model in predicting individual target wells. Further, we wish to reveal whether the MODFLOW model has advantages in predicting all four wells simultaneously because it can use the available information in a physics‐based, integrated manner, or whether structural limitations spoil this effect. Our results demonstrate that data‐driven models with low input requirements and short run‐times are competitive candidates for local groundwater level predictions even for system states that lie outside the calibration data range. There is no “single best” model that performs best in all cases, which motivates ensemble forecasting with different model classes using Bayesian model averaging. The obtained Bayesian model weights clearly favor MODFLOW when targeting all wells simultaneously, even though the competing approaches had the chance to fine‐tune for each tested well individually. This is a remarkable result that strengthens the argument for physics‐based approaches even for seemingly “simple” groundwater level prediction tasks. |
|---|---|
| AbstractList | Groundwater level observations are used as decision variables for aquifer management, often in conjunction with models to provide predictions for operational forecasting. In this study, we compare different model classes for this task: a spatially explicit 3D groundwater flow model (MODFLOW), an eigenmodel, a transfer-function model, and three machine learning models, namely, multi-layer perceptron models, long short-term memory models, and random forest models. The models differ widely in their complexity, input requirements, calibration effort, and run-times. They are tested on four groundwater level time series from the Wairau Aquifer in New Zealand to investigate the potential of the data-driven approaches to outperform the MODFLOW model in predicting individual target wells. Further, we wish to reveal whether the MODFLOW model has advantages in predicting all four wells simultaneously because it can use the available information in a physics-based, integrated manner, or whether structural limitations spoil this effect. Our results demonstrate that data-driven models with low input requirements and short run-times are competitive candidates for local groundwater level predictions even for system states that lie outside the calibration data range. There is no "single best" model that performs best in all cases, which motivates ensemble forecasting with different model classes using Bayesian model averaging. The obtained Bayesian model weights clearly favor MODFLOW when targeting all wells simultaneously, even though the competing approaches had the chance to fine-tune for each tested well individually. This is a remarkable result that strengthens the argument for physics-based approaches even for seemingly "simple" groundwater level prediction tasks.Groundwater level observations are used as decision variables for aquifer management, often in conjunction with models to provide predictions for operational forecasting. In this study, we compare different model classes for this task: a spatially explicit 3D groundwater flow model (MODFLOW), an eigenmodel, a transfer-function model, and three machine learning models, namely, multi-layer perceptron models, long short-term memory models, and random forest models. The models differ widely in their complexity, input requirements, calibration effort, and run-times. They are tested on four groundwater level time series from the Wairau Aquifer in New Zealand to investigate the potential of the data-driven approaches to outperform the MODFLOW model in predicting individual target wells. Further, we wish to reveal whether the MODFLOW model has advantages in predicting all four wells simultaneously because it can use the available information in a physics-based, integrated manner, or whether structural limitations spoil this effect. Our results demonstrate that data-driven models with low input requirements and short run-times are competitive candidates for local groundwater level predictions even for system states that lie outside the calibration data range. There is no "single best" model that performs best in all cases, which motivates ensemble forecasting with different model classes using Bayesian model averaging. The obtained Bayesian model weights clearly favor MODFLOW when targeting all wells simultaneously, even though the competing approaches had the chance to fine-tune for each tested well individually. This is a remarkable result that strengthens the argument for physics-based approaches even for seemingly "simple" groundwater level prediction tasks. Groundwater level observations are used as decision variables for aquifer management, often in conjunction with models to provide predictions for operational forecasting. In this study, we compare different model classes for this task: a spatially explicit 3D groundwater flow model (MODFLOW), an eigenmodel, a transfer‐function model, and three machine learning models, namely, multi‐layer perceptron models, long short‐term memory models, and random forest models. The models differ widely in their complexity, input requirements, calibration effort, and run‐times. They are tested on four groundwater level time series from the Wairau Aquifer in New Zealand to investigate the potential of the data‐driven approaches to outperform the MODFLOW model in predicting individual target wells. Further, we wish to reveal whether the MODFLOW model has advantages in predicting all four wells simultaneously because it can use the available information in a physics‐based, integrated manner, or whether structural limitations spoil this effect. Our results demonstrate that data‐driven models with low input requirements and short run‐times are competitive candidates for local groundwater level predictions even for system states that lie outside the calibration data range. There is no “single best” model that performs best in all cases, which motivates ensemble forecasting with different model classes using Bayesian model averaging. The obtained Bayesian model weights clearly favor MODFLOW when targeting all wells simultaneously, even though the competing approaches had the chance to fine‐tune for each tested well individually. This is a remarkable result that strengthens the argument for physics‐based approaches even for seemingly “simple” groundwater level prediction tasks. |
| Author | Delgadillo, Alvaro Oliver Crespo Wöhling, Thomas Kraft, Moritz Guthke, Anneli |
| AuthorAffiliation | 1 Chair of Hydrology Dresden University of Technology (TUD) 01069 Dresden Germany 2 University of Stuttgart, Stuttgart Center for Simulation Science (SC SimTech) 70569 Stuttgart Germany |
| AuthorAffiliation_xml | – name: 2 University of Stuttgart, Stuttgart Center for Simulation Science (SC SimTech) 70569 Stuttgart Germany – name: 1 Chair of Hydrology Dresden University of Technology (TUD) 01069 Dresden Germany |
| Author_xml | – sequence: 1 givenname: Thomas orcidid: 0000-0003-2963-0965 surname: Wöhling fullname: Wöhling, Thomas email: thomas.woehling@tu-dresden.de – sequence: 2 givenname: Alvaro Oliver Crespo surname: Delgadillo fullname: Delgadillo, Alvaro Oliver Crespo organization: Dresden University of Technology (TUD) – sequence: 3 givenname: Moritz surname: Kraft fullname: Kraft, Moritz organization: Dresden University of Technology (TUD) – sequence: 4 givenname: Anneli surname: Guthke fullname: Guthke, Anneli organization: University of Stuttgart, Stuttgart Center for Simulation Science (SC SimTech) |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40256895$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kc1uEzEUhS1URNPChgdAI7FBiCn-HY9XKI0gICWiiyLYWR77TjLVxA72TKvseIQ-Y58Eh5QKWHA3vtL57tGxzgk68sEDQs8JPiN53q5uzHBGGK_lIzQhkouyEjU_QhOMiSx5Jb8do5OUrjDGTGH1BB1zTEVVKzFB61nYbE3s_Kq4WO9SZ9Pdj9tzk8C9KWbBW9gOo-kL412xNHbdecj6Akz0-5NlcNCnYgjFRQTX2aGYxzB6lwNBLBZwvVebXXG-nD5Fj1vTJ3h2_56iLx_eX84-lovP80-z6aI0nDFZNkY55WgrGsxrQYHUljFLAdcNMXmlLXMKc8uhwgC4bWsl64ZVTQvMSUvZKXp38N2OzQacBT9E0-tt7DYm7nQwnf5b8d1ar8K1JpRKirHKDq_uHWL4PkIa9KZLFvreeAhj0owoykTFapbRl_-gV2GMPv9PM8oIVkIKnKkXf0Z6yPK7hQy8PgA2hpQitA8IwXpfsd5XrH9VnGFygG-6Hnb_IfX86_TycPMT0m2rGA |
| Cites_doi | 10.1029/2011WR011471 10.1016/j.scitotenv.2020.141220 10.3390/w12010005 10.1038/s41598‐020‐60698‐9 10.3133/tm6A16 10.1016/j.jher.2017.11.004 10.1002/2014WR016292 10.5194/hess‐23‐4323‐2019 10.1016/j.advwatres.2012.10.001 10.1038/s41467‐022‐28770‐2 10.1016/j.watres.2024.121249 10.1111/gwat.12925 10.1029/2005WR004828 10.1088/1748‐9326/ab8e8c 10.1023/A:1010933404324 10.13189/cea.2022.100304 10.5194/hess‐23‐3057‐2019 10.5194/hess‐2024‐111 10.1007/s12145‐021‐00654‐x 10.1029/2009WR008933 10.1111/gwat.12625 10.1016/j.jhydrol.2017.07.021 10.5194/hess‐28‐2167‐2024 10.1029/wr019i001p00087 10.1016/j.jhydrol.2015.07.047 10.5194/hess‐27‐2397‐2023 10.1016/j.catena.2015.10.010 10.1007/s13201‐018‐0742‐6 10.1007/s10040‐013‐1029‐5 10.5194/hess-12-975-2008 10.1111/gwat.12819 10.1111/j.1745‐6584.2007.00382.x 10.3390/w11051098 10.1016/j.jhydrol.2022.127630 10.1029/2019WR027009 10.1029/2020WR029500 10.1007/s11269‐018‐2126‐y 10.1111/j.1745-6584.2003.tb02580.x 10.1016/j.scitotenv.2021.146948 10.1016/j.jhydrol.2012.02.031 10.1016/j.gsd.2019.100237 10.1007/s12665‐014‐3608‐8 10.1016/j.jhydrol.2018.12.037 10.1016/j.scitotenv.2014.01.001 10.1016/j.jhydrol.2009.08.003 10.1080/00949650410001729472 10.1016/j.scitotenv.2023.168760 10.1016/j.jhydrol.2020.124871 10.3133/tm6A37 10.1002/joc.1350 10.1016/j.jhydrol.2021.126735 10.1016/j.jhydrol.2004.12.001 10.1029/2010wr010174 10.2307/3315929 10.1002/2013WR014800 10.1016/j.jhydrol.2021.127347 10.1016/j.jhydrol.2021.126674 10.1080/00288306.1981.10422739 10.1016/j.jhydrol.2011.08.002 10.1111/gwat.12927 10.1007/s12665‐013‐2306‐2 10.1029/2007WR006735 10.1016/j.matcom.2005.02.023 10.5194/hess‐25‐1671‐2021 10.1016/j.jhydrol.2005.02.026 10.1016/j.jhydrol.2013.07.012 10.1002/wrcr.20496 10.1029/2007WR006678 10.1016/j.jhydrol.2016.03.026 10.1111/gwat.12554 10.1029/2010WR009265 10.5675/HyWa 10.1029/2001WR001136 10.1016/j.envsoft.2012.06.003 10.1214/ss/1009212519 10.1162/neco.1997.9.8.1735 10.1016/j.ejrh.2020.100715 10.1016/j.jhydrol.2012.01.045 10.1016/j.advwatres.2019.01.006 10.3389/frwa.2020.573034 10.1007/s11069‐010‐9603‐9 10.1002/2014WR016062 10.1007/s10898‐020‐00912‐0 10.1016/j.neucom.2022.03.014 10.1007/978-3-642-38739-5 10.1002/hyp.8214 10.3133/sir20105168 10.1002/2017WR021902 10.2166/nh.2016.264 10.1016/j.jhydrol.2018.01.045 10.1016/j.jhydrol.2011.06.013 10.1007/s12665‐023‐11012‐z 10.1038/s41586‐023‐06879‐8 10.1016/j.jhydrol.2019.01.072 10.1002/9783527611515 |
| ContentType | Journal Article |
| Copyright | 2025 The Author(s). published by Wiley Periodicals LLC on behalf of National Ground Water Association. 2025 The Author(s). Groundwater published by Wiley Periodicals LLC on behalf of National Ground Water Association. 2025. This work is published under Creative Commons Attribution License~https://creativecommons.org/licenses/by/3.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: 2025 The Author(s). published by Wiley Periodicals LLC on behalf of National Ground Water Association. – notice: 2025 The Author(s). Groundwater published by Wiley Periodicals LLC on behalf of National Ground Water Association. – notice: 2025. This work is published under Creative Commons Attribution License~https://creativecommons.org/licenses/by/3.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | 24P AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QH 7ST 7UA C1K F1W H96 H97 K9. L.G SOI 7X8 5PM |
| DOI | 10.1111/gwat.13487 |
| DatabaseName | Wiley Online Library Open Access CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Aqualine Environment Abstracts Water Resources Abstracts Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Aquatic Science & Fisheries Abstracts (ASFA) 3: Aquatic Pollution & Environmental Quality ProQuest Health & Medical Complete (Alumni) Aquatic Science & Fisheries Abstracts (ASFA) Professional Environment Abstracts MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources ASFA: Aquatic Sciences and Fisheries Abstracts ProQuest Health & Medical Complete (Alumni) Aqualine Environment Abstracts Aquatic Science & Fisheries Abstracts (ASFA) 3: Aquatic Pollution & Environmental Quality Water Resources Abstracts Environmental Sciences and Pollution Management MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic CrossRef MEDLINE Aquatic Science & Fisheries Abstracts (ASFA) Professional |
| Database_xml | – sequence: 1 dbid: 24P name: Wiley Online Library Open Access url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html sourceTypes: Publisher – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geography Engineering Physics |
| DocumentTitleAlternate | Comparing Physics‐Based, Conceptual and Machine‐Learning Models to Predict Groundwater Levels by BMA |
| EISSN | 1745-6584 |
| EndPage | 505 |
| ExternalDocumentID | PMC12272009 40256895 10_1111_gwat_13487 GWAT13487 |
| Genre | researchArticle Journal Article Comparative Study |
| GeographicLocations | New Zealand |
| GeographicLocations_xml | – name: New Zealand |
| GrantInformation_xml | – fundername: Deutsche Forschungsgemeinschaft funderid: EXC 2075 390740016 – fundername: Ministry for Business Innovation and Employment funderid: 1964‐MLDC149 – fundername: Ministry for Business Innovation and Employment grantid: 1964-MLDC149 – fundername: Deutsche Forschungsgemeinschaft grantid: EXC 2075 390740016 – fundername: ; grantid: EXC 2075 390740016 – fundername: ; grantid: 1964‐MLDC149 |
| GroupedDBID | --- -DZ -~X .3N .DC .GA .Y3 05W 0R~ 10A 186 1OB 1OC 24P 29I 31~ 33P 3SF 4.4 50Y 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52U 52W 52X 53G 5GY 5HH 5LA 5VS 66C 702 7PT 7X2 7X7 7XC 8-0 8-1 8-3 8-4 8-5 88E 88I 8CJ 8FE 8FG 8FH 8FI 8FJ 8G5 8R4 8R5 8UM 930 A03 AAESR AAEVG AAHBH AAHQN AAMMB AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABEML ABJCF ABJNI ABPPZ ABPVW ABUWG ACAHQ ACBWZ ACCZN ACGFO ACGFS ACGOD ACIWK ACNCT ACPOU ACRPL ACSCC ACXBN ACXQS ACYXJ ADBBV ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADXHL ADZMN AEFGJ AEGXH AEIGN AEIMD AENEX AETEA AEUYN AEUYR AEYWJ AFBPY AFFPM AFGKR AFKRA AFRAH AFWVQ AFZJQ AGHNM AGQPQ AGXDD AGYGG AHBTC AHEFC AI. AIAGR AIDQK AIDYY AITYG AIURR AJXKR ALAGY ALIPV ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ASPBG ATCPS ATUGU AUFTA AVWKF AZBYB AZFZN AZQEC AZVAB BAFTC BCR BCU BDRZF BEC BENPR BES BFHJK BGLVJ BHBCM BHPHI BKOMP BKSAR BLC BMNLL BMXJE BNHUX BPHCQ BROTX BRXPI BVXVI BY8 CAG CCPQU COF CS3 D-E D-F D1J D1K DC6 DCZOG DDYGU DPXWK DR2 DRFUL DRSTM DWQXO EBS EJD F00 F01 F04 F5P FEDTE FYUFA FZ0 G-S G.N GNUQQ GODZA GUQSH H.T H.X HCIFZ HF~ HGLYW HMCUK HVGLF HZI HZ~ IAG IAO IEA IEP IOF ITC IX1 J0M K48 K6- L6V LATKE LC2 LC3 LEEKS LH4 LITHE LK5 LOXES LP6 LP7 LUTES LW6 LYRES M0K M1P M2O M2P M7R M7S MEWTI MK4 MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM N04 N05 N9A NF~ O66 O9- OIG P2P P2W P2X P4D PALCI PATMY PCBAR PEA PHGZM PHGZT PPXIY PQGLB PQQKQ PRG PROAC PSQYO PTHSS PYCSY Q.N Q11 Q2X QB0 R.K R05 RIWAO RJQFR ROL RWL RX1 S0X SAMSI SJFOW SUPJJ TAE TN5 UB1 UKHRP V8K VH1 VJK W8V W99 WBKPD WIH WIK WLBEL WOHZO WQJ WXSBR WYISQ XG1 Y6R ZCA ZZTAW ~02 ~IA ~KM ~WT AAYXX AFFHD AIQQE CITATION O8X PJZUB CGR CUY CVF ECM EIF NPM 7QH 7ST 7UA C1K F1W H96 H97 K9. L.G SOI 7X8 5PM |
| ID | FETCH-LOGICAL-a4337-ba9d9d2f5b04852e18c33c2e08b1ac332f3d904c4e60ee0ff8978b36bfe3d7c23 |
| IEDL.DBID | 24P |
| ISICitedReferencesCount | 2 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001470719500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0017-467X 1745-6584 |
| IngestDate | Tue Nov 04 02:03:10 EST 2025 Fri Sep 05 17:29:40 EDT 2025 Sat Nov 08 20:08:19 EST 2025 Mon Jul 21 02:03:49 EDT 2025 Thu Nov 27 00:45:16 EST 2025 Fri Jul 18 09:20:16 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| License | Attribution 2025 The Author(s). Groundwater published by Wiley Periodicals LLC on behalf of National Ground Water Association. This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a4337-ba9d9d2f5b04852e18c33c2e08b1ac332f3d904c4e60ee0ff8978b36bfe3d7c23 |
| Notes | Article impact statement Six model types to predict groundwater levels are compared and combined to provide guidance to modelers for their selection and use. ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Article impact statement: Six model types to predict groundwater levels are compared and combined to provide guidance to modelers for their selection and use. |
| ORCID | 0000-0003-2963-0965 |
| OpenAccessLink | https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fgwat.13487 |
| PMID | 40256895 |
| PQID | 3231095750 |
| PQPubID | 48478 |
| PageCount | 20 |
| ParticipantIDs | pubmedcentral_primary_oai_pubmedcentral_nih_gov_12272009 proquest_miscellaneous_3192356383 proquest_journals_3231095750 pubmed_primary_40256895 crossref_primary_10_1111_gwat_13487 wiley_primary_10_1111_gwat_13487_GWAT13487 |
| PublicationCentury | 2000 |
| PublicationDate | July/August 2025 |
| PublicationDateYYYYMMDD | 2025-07-01 |
| PublicationDate_xml | – month: 07 year: 2025 text: July/August 2025 |
| PublicationDecade | 2020 |
| PublicationPlace | Malden, US |
| PublicationPlace_xml | – name: Malden, US – name: United States – name: Dublin |
| PublicationTitle | Ground water |
| PublicationTitleAlternate | Ground Water |
| PublicationYear | 2025 |
| Publisher | Blackwell Publishing Ltd Ground Water Publishing Company |
| Publisher_xml | – name: Blackwell Publishing Ltd – name: Ground Water Publishing Company |
| References | 2013; 69 1983; 19 2016b 2016a 2018; 567 2019; 11 2015; 73 2024; 625 2021; 600 2021; 602 2020; 15 2011; 57 2020; 12 2025 2020; 10 2024 2001; 45 2017; 552 1997; 9 2023; 82 2005; 69 2018; 8 2011; 409 2011; 407 2015; 531 2019; 23 2013; 53 2006; 26 2005; 75 2022; 608 2022; 606 2018; 32 2003; 41 2024; 28 2016; 47 2021; 81 2019; 9 2021; 783 2015; 51 2019; 32 1981; 24 1995 2012; 38 2021; 57 2018; 18 2006; 42 2010; 46 2020; 31 2017; 55 2022; 13 2008; 46 2008; 44 2022; 10 2012; 48 2019; 572 2009; 45 2021; 25 1987; 1 2013; 21 2019; 57 2019; 125 2011; 12 2020; 56 2014; 476–477 2020; 2 2019; 63 2023; 27 1999; 14 2024; 2024 2005; 309 2011; 26 2014; 50 2022; 489 2002; 38 2013; 49 2012 2011 2010 2005; 313 2008; 14 2009; 377 2005 2003 2020; 586 2020; 747 2021; 14 2024b; 912 2023 2024a; 252 2016; 537 2019 2013; 499 2016 2015 2014 2016; 137 2011; 47 2018; 56 2012; 434–435 2018; 54 2012; 436‐437 e_1_2_8_26_1 e_1_2_8_49_1 e_1_2_8_68_1 e_1_2_8_5_1 e_1_2_8_9_1 e_1_2_8_22_1 e_1_2_8_45_1 e_1_2_8_64_1 e_1_2_8_87_1 e_1_2_8_41_1 e_1_2_8_60_1 e_1_2_8_83_1 e_1_2_8_19_1 MCB (e_1_2_8_56_1) 1987 e_1_2_8_109_1 e_1_2_8_15_1 e_1_2_8_38_1 e_1_2_8_57_1 e_1_2_8_91_1 e_1_2_8_95_1 e_1_2_8_99_1 e_1_2_8_105_1 e_1_2_8_34_1 e_1_2_8_53_1 e_1_2_8_76_1 e_1_2_8_101_1 e_1_2_8_72_1 e_1_2_8_29_1 Basher L.R. (e_1_2_8_11_1) 1995 e_1_2_8_25_1 e_1_2_8_48_1 e_1_2_8_2_1 e_1_2_8_110_1 Doherty J.E. (e_1_2_8_30_1) 2016 e_1_2_8_6_1 e_1_2_8_21_1 e_1_2_8_67_1 Davidson P. (e_1_2_8_28_1) 2011 e_1_2_8_44_1 e_1_2_8_86_1 e_1_2_8_40_1 e_1_2_8_82_1 e_1_2_8_18_1 e_1_2_8_14_1 e_1_2_8_37_1 e_1_2_8_79_1 e_1_2_8_94_1 e_1_2_8_90_1 e_1_2_8_98_1 e_1_2_8_10_1 e_1_2_8_106_1 e_1_2_8_33_1 e_1_2_8_75_1 e_1_2_8_52_1 e_1_2_8_102_1 e_1_2_8_71_1 e_1_2_8_24_1 e_1_2_8_47_1 e_1_2_8_3_1 e_1_2_8_81_1 e_1_2_8_111_1 e_1_2_8_7_1 e_1_2_8_20_1 e_1_2_8_43_1 e_1_2_8_66_1 e_1_2_8_89_1 e_1_2_8_62_1 e_1_2_8_85_1 e_1_2_8_17_1 e_1_2_8_13_1 e_1_2_8_36_1 e_1_2_8_59_1 e_1_2_8_70_1 e_1_2_8_97_1 e_1_2_8_32_1 e_1_2_8_55_1 Murphy K.P. (e_1_2_8_61_1) 2012 e_1_2_8_78_1 e_1_2_8_107_1 e_1_2_8_51_1 e_1_2_8_74_1 e_1_2_8_103_1 e_1_2_8_93_1 e_1_2_8_46_1 e_1_2_8_27_1 e_1_2_8_69_1 e_1_2_8_80_1 e_1_2_8_4_1 e_1_2_8_8_1 e_1_2_8_42_1 e_1_2_8_88_1 e_1_2_8_23_1 e_1_2_8_65_1 Pedregosa F. (e_1_2_8_63_1) 2011; 12 e_1_2_8_84_1 e_1_2_8_112_1 e_1_2_8_39_1 e_1_2_8_35_1 e_1_2_8_16_1 e_1_2_8_58_1 Doherty J.E. (e_1_2_8_31_1) 2016 e_1_2_8_92_1 e_1_2_8_96_1 e_1_2_8_100_1 e_1_2_8_77_1 e_1_2_8_12_1 e_1_2_8_54_1 e_1_2_8_108_1 e_1_2_8_73_1 e_1_2_8_50_1 e_1_2_8_104_1 |
| References_xml | – year: 2011 – volume: 14 start-page: 382 issue: 4 year: 1999 end-page: 417 article-title: Bayesian model averaging: A tutorial publication-title: Statistical Science – volume: 12 start-page: 2825 year: 2011 end-page: 2830 article-title: Scikit‐learn: Machine learning in Python publication-title: Journal of Machine Learning Research – year: 2005 – volume: 50 start-page: 9484 issue: 12 year: 2014 end-page: 9513 article-title: Model selection on solid ground: Rigorous comparison of nine ways to evaluate Bayesian model evidence publication-title: Water Resources Research – volume: 434–435 start-page: 78 year: 2012 end-page: 94 article-title: Comparing methods for estimating flow duration curves at ungauged sites publication-title: Journal of Hydrology – volume: 45 start-page: 5 issue: 1 year: 2001 end-page: 32 article-title: Random forests publication-title: Machine Learning – volume: 81 start-page: 203 issue: 1 year: 2021 end-page: 231 article-title: Surrogate optimization of deep neural networks for groundwater predictions publication-title: Journal of Global Optimization – volume: 602 issue: 11 year: 2021 article-title: Comparison of physical and data‐driven models to forecast groundwater level changes with the inclusion of GRACE – A case study over the state of Victoria, Australia publication-title: Journal of Hydrology – volume: 57 start-page: 826 issue: 6 year: 2019 end-page: 833 article-title: Solving groundwater flow problems with time series analysis: You may not even need another model publication-title: Groundwater – volume: 309 start-page: 229 issue: 1 year: 2005 end-page: 240 article-title: Groundwater level forecasting using artificial neural networks publication-title: Journal of Hydrology – volume: 137 start-page: 360 year: 2016 end-page: 372 article-title: Application of GIS‐based data driven random forest and maximum entropy models for groundwater potential mapping: A case study at Mehran Region, Iran publication-title: Catena – volume: 15 issue: 9 year: 2020 article-title: Groundwater sustainability: A review of the interactions between science and policy publication-title: Environmental Research Letters – year: 2014 – volume: 2 year: 2020 article-title: Impact of input feature selection on groundwater level prediction from a multi‐layer perceptron neural network publication-title: Frontiers in Water – volume: 252 year: 2024a article-title: Groundwater level forecasting with machine learning models: A review publication-title: Water Research – year: 2016a – volume: 537 start-page: 45 year: 2016 end-page: 60 article-title: An overview of current applications, challenges, and future trends in distributed process‐based models in hydrology publication-title: Journal of Hydrology – year: 2025 – volume: 31 issue: 10 year: 2020 article-title: Detecting the cause of change using uncertain data: Natural and anthropogenic factors contributing to declining groundwater levels and flows of the Wairau Plain aquifer, New Zealand publication-title: Journal of Hydrology: Regional Studies – volume: 47 year: 2011 article-title: Multiresponse multilayer vadose zone model calibration using Markov chain Monte Carlo simulation and field water retention data publication-title: Water Resources Research – year: 2019 – volume: 747 year: 2020 article-title: Eigenmodels to forecast groundwater levels in unconfined river‐fed aquifers during flow recession publication-title: Science of the Total Environment – volume: 49 start-page: 6459 issue: 10 year: 2013 end-page: 6473 article-title: Bridging groundwater models and decision support with a Bayesian network publication-title: Water Resources Research – volume: 377 start-page: 80 issue: 1–2 year: 2009 end-page: 91 article-title: Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling publication-title: Journal of Hydrology – volume: 476–477 start-page: 189 year: 2014 end-page: 206 article-title: Predictive modeling of groundwater nitrate pollution using random Forest and multisource variables related to intrinsic and specific vulnerability: A case study in an agricultural setting (southern Spain) publication-title: Science of the Total Environment – volume: 23 start-page: 4323 issue: 10 year: 2019 end-page: 4331 article-title: Technical note: Inherent benchmark or not? Comparing Nash–Sutcliffe and Kling–Gupta efficiency scores publication-title: Hydrology and Earth System Sciences – volume: 572 start-page: 336 year: 2019 end-page: 351 article-title: A review of the artificial intelligence methods in groundwater level modeling publication-title: Journal of Hydrology – volume: 436‐437 start-page: 13 year: 2012 end-page: 34 article-title: Three‐dimensional geological modelling and multivariate statistical analysis of water chemistry data to analyse and visualise aquifer structure and groundwater composition in the Wairau Plain, Marlborough District, New Zealand publication-title: Journal of Hydrology – volume: 13 start-page: 1221 issue: 1 year: 2022 article-title: Deep learning shows declining groundwater levels in Germany until 2100 due to climate change publication-title: Nature Communications – volume: 552 start-page: 684 year: 2017 end-page: 703 article-title: Predicting nitrate discharge dynamics in mesoscale catchments using the lumped StreamGEM model and Bayesian parameter inference publication-title: Journal of Hydrology – volume: 313 start-page: 166 issue: 3 year: 2005 end-page: 181 article-title: Modeling of stream‐aquifer interaction: The embedded multireservoir model publication-title: Journal of Hydrology – volume: 47 start-page: 69 issue: S1 year: 2016 end-page: 83 article-title: Comparison of random forests and other statistical methods for the prediction of lake water level: A case study of the Poyang lake in China publication-title: Hydrology Research – volume: 783 year: 2021 article-title: Groundwater level modeling framework by combining the wavelet transform with a long short‐term memory data‐driven model publication-title: Science of the Total Environment – volume: 38 start-page: 23‐1 issue: 12 year: 2002 end-page: 23‐12 article-title: Transfer function‐noise modeling in continuous time using predefined impulse response functions publication-title: Water Resources Research – volume: 46 start-page: 30 issue: 1 year: 2008 end-page: 40 article-title: Modeling time series of ground water head fluctuations subjected to multiple stresses publication-title: Groundwater – year: 2016 – volume: 69 start-page: 12 issue: 1 year: 2005 end-page: 20 article-title: Realistic forecasting of groundwater level, based on the eigenstructure of aquifer dynamics publication-title: Mathematics and Computers in Simulation – volume: 24 start-page: 477 year: 1981 end-page: 490 article-title: Late quaternary geology of the Wairau Plain, Marlborough, New Zealand publication-title: New Zealand Journal of Geology and Geophysics – year: 2010 – volume: 27 start-page: 2397 issue: 13 year: 2023 end-page: 2411 article-title: When best is the enemy of good – Critical evaluation of performance criteria in hydrological models publication-title: Hydrology and Earth System Sciences – volume: 608 year: 2022 article-title: Data‐driven models for accurate groundwater level prediction and their practical significance in groundwater management publication-title: Journal of Hydrology – volume: 32 start-page: 5041 issue: 15 year: 2018 end-page: 5052 article-title: Multilayer feed forward models in groundwater level forecasting using meteorological data in public management publication-title: Water Resources Management – volume: 44 year: 2008 article-title: Framework for understanding structural errors (FUSE): A modular framework to diagnose differences between hydrological models publication-title: Water Resources Research – volume: 63 start-page: 130 issue: H3 year: 2019 end-page: 140 article-title: Natürliche und anthropogene Einflussfaktoren auf das hydrologische Regime des Wairau Plain Aquifer in Neuseeland publication-title: Hydrologie und Wasserbewirtschaftung – volume: 45 year: 2009 article-title: Calibration‐constrained Monte Carlo analysis of highly parameterized models using subspace techniques publication-title: Water Resources Research – volume: 57 start-page: 877 issue: 6 year: 2019 end-page: 885 article-title: Pastas: Open source software for the analysis of groundwater time series publication-title: Groundwater – volume: 47 issue: 11 year: 2011 article-title: Elements of a flexible approach for conceptual hydrological modeling: 1. Motivation and theoretical development publication-title: Water Resources Research – year: 1995 – volume: 75 start-page: 629 issue: 8 year: 2005 end-page: 643 article-title: An empirical comparison of ensemble methods based on classification trees publication-title: Journal of Statistical Computation and Simulation – volume: 625 start-page: 715 issue: 7996 year: 2024 end-page: 721 article-title: Rapid groundwater decline and some cases of recovery in aquifers globally publication-title: Nature – volume: 26 start-page: 1435 issue: 10 year: 2011 end-page: 1448 article-title: A conceptual‐numerical model to simulate hydraulic head in aquifers that are hydraulically connected to surface water bodies publication-title: Hydrological Processes – volume: 21 start-page: 1865 issue: 8 year: 2013 end-page: 1887 article-title: Groundwater‐level prediction using multiple linear regression and artificial neural network techniques: A comparative assessment publication-title: Hydrogeology Journal – year: 2016b – volume: 57 start-page: 167 issue: 2 year: 2011 end-page: 184 article-title: Forecasting groundwater level fluctuations for rainfall‐induced landslide publication-title: Natural Hazards – volume: 1 year: 1987 – volume: 586 year: 2020 article-title: Adaptive management in groundwater planning and development: A review of theory and applications publication-title: Journal of Hydrology – volume: 18 start-page: 63 year: 2018 end-page: 76 article-title: Groundwater level fluctuations simulation and prediction by ANFIS‐ and hybrid Wavelet‐ANFIS/Fuzzy C‐Means (FCM) clustering models: Application to the Miandarband plain publication-title: Journal of Hydro‐Environment Research – volume: 28 start-page: 2167 issue: 9 year: 2024 end-page: 2178 article-title: Towards understanding the influence of seasons on low‐groundwater periods based on explainable machine learning publication-title: Hydrology and Earth System Sciences – volume: 10 start-page: 784 issue: 3 year: 2022 end-page: 799 article-title: Groundwater level forecasting using multiple linear regression and artificial neural network approaches publication-title: Civil Engineering and Architecture – volume: 14 start-page: 1269 issue: 3 year: 2021 end-page: 1283 article-title: Groundwater level as an input to monthly predicting of water level using various machine learning algorithms publication-title: Earth Science Informatics – volume: 125 start-page: 41 year: 2019 end-page: 56 article-title: Simplification error analysis for groundwater predictions with reduced order models publication-title: Advances in Water Resources – volume: 407 start-page: 28 issue: 1 year: 2011 end-page: 40 article-title: A wavelet neural network conjunction model for groundwater level forecasting publication-title: Journal of Hydrology – volume: 56 start-page: 647 issue: 4 year: 2018 end-page: 666 article-title: Quantifying river‐groundwater interactions of New Zealand's gravel‐bed rivers: The Wairau Plain publication-title: Groundwater – year: 2024 – volume: 56 issue: 9 year: 2020 article-title: Automatic model structure identification for conceptual hydrologic models publication-title: Water Resources Research – volume: 25 start-page: 1671 issue: 3 year: 2021 end-page: 1687 article-title: Groundwater level forecasting with artificial neural networks: A comparison of long short‐term memory (LSTM), convolutional neural networks (CNNs), and non‐linear autoregressive networks with exogenous input (NARX) publication-title: Hydrology and Earth System Sciences – volume: 8 start-page: 125 issue: 5 year: 2018 article-title: Short‐term prediction of groundwater level using improved random forest regression with a combination of random features publication-title: Applied Water Science – volume: 499 start-page: 324 year: 2013 end-page: 338 article-title: Hydrological evaluation of satellite‐based rainfall estimates over the Volta and Baro‐Akobo Basin publication-title: Journal of Hydrology – volume: 19 start-page: 87 issue: 1 year: 1983 end-page: 93 article-title: An eigenvalue numerical technique for solving unsteady linear groundwater models continuously in time publication-title: Water Resources Research – volume: 32 start-page: 269 issue: 3 year: 2019 end-page: 283 article-title: Improvement over bayes prediction in small samples in the presence of model uncertainty publication-title: Canadian Journal of Statistics – volume: 12 issue: 1 year: 2020 article-title: Groundwater estimation from major physical hydrology components using artificial neural networks and deep learning publication-title: Water – volume: 11 issue: 5 year: 2019 article-title: Forecasting groundwater table in a flood prone Coastal City with long short‐term memory and recurrent neural networks publication-title: Water – volume: 41 start-page: 170 issue: 2 year: 2003 end-page: 177 article-title: Ground water model calibration using pilot points and regularization publication-title: Groundwater – volume: 9 start-page: 1735 issue: 11 year: 1997 end-page: 1780 article-title: Long short‐term memory publication-title: Neural Computation – volume: 912 year: 2024b article-title: Groundwater level forecasting using ensemble coactive neuro‐fuzzy inference system publication-title: Science of the Total Environment – volume: 54 start-page: 1688 issue: 3 year: 2018 end-page: 1715 article-title: A primer for model selection: The decisive role of model complexity publication-title: Water Resources Research – volume: 57 start-page: 834 issue: 6 year: 2019 end-page: 843 article-title: Automated time series modeling for piezometers in the national database of The Netherlands publication-title: Groundwater – volume: 57 issue: 12 year: 2021 article-title: Global groundwater modeling and monitoring: Opportunities and challenges publication-title: Water Resources Research – volume: 23 start-page: 3057 issue: 7 year: 2019 end-page: 3080 article-title: Assessing the performance of global hydrological models for capturing peak river flows in the Amazon basin publication-title: Hydrology and Earth System Sciences – volume: 82 start-page: 339 issue: 13 year: 2023 article-title: A data‐driven approach for modelling Karst spring discharge using transfer function noise models publication-title: Environmental Earth Sciences – year: 2015 – volume: 409 start-page: 94 issue: 1 year: 2011 end-page: 103 article-title: Topographic controls on overland flow generation in a forest – An ensemble tree approach publication-title: Journal of Hydrology – volume: 2024 start-page: 1 year: 2024 end-page: 21 article-title: Data‐driven modeling of hydraulic head time series: Results and lessons learned from the 2022 groundwater modeling challenge publication-title: Hydrology and Earth System Sciences Discussions – volume: 73 start-page: 3119 issue: 7 year: 2015 end-page: 3136 article-title: On the statistical forecasting of groundwater levels in unconfined aquifer systems publication-title: Environmental Earth Sciences – volume: 606 year: 2022 article-title: Lumped geohydrological modelling for long‐term predictions of groundwater storage and depletion publication-title: Journal of Hydrology – year: 2003 – volume: 10 start-page: 3904 issue: 1 year: 2020 article-title: A comparative study among machine learning and numerical models for simulating groundwater dynamics in the Heihe River Basin, northwestern China publication-title: Scientific Reports – volume: 50 start-page: 8330 issue: 10 year: 2014 end-page: 8355 article-title: Nonlinear time‐series modeling of unconfined groundwater head publication-title: Water Resources Research – volume: 46 year: 2010 article-title: A formal likelihood function for parameter and predictive inference of hydrologic models with correlated, heteroscedastic and non‐Gaussian errors publication-title: Water Resorces Research – volume: 26 start-page: 2097 issue: 14 year: 2006 end-page: 2115 article-title: Thin plate smoothing spline interpolation of daily rainfall for New Zealand using a climatological rainfall surface publication-title: International Journal of Climatology – volume: 42 issue: 10 year: 2006 article-title: Effect of temporally correlated recharge on fluctuations of groundwater levels publication-title: Water Resources Research – year: 2012 – volume: 14 start-page: 975 year: 2008 end-page: 987 article-title: Dynamic analysis of groundwater discharge and partial‐area contribution to Pukemanga stream, New Zealand publication-title: Hydrology and Earth System Sciences – volume: 489 start-page: 271 year: 2022 end-page: 308 article-title: Groundwater level prediction using machine learning models: A comprehensive review publication-title: Neurocomputing – volume: 69 start-page: 453 issue: 2 year: 2013 end-page: 468 article-title: Evaluating multiple performance criteria to calibrate the distributed hydrological model of the Upper Neckar catchment publication-title: Environmental Earth Sciences – volume: 53 start-page: 109 year: 2013 end-page: 117 article-title: A terrain‐following grid transform and preconditioner for parallel, large‐scale, integrated hydrologic modeling publication-title: Advances in Water Resources – volume: 51 start-page: 2825 issue: 4 year: 2015 end-page: 2846 article-title: Bayesian model averaging to explore the worth of data for soil‐plant model selection and prediction publication-title: Water Resources Research – volume: 567 start-page: 743 issue: 12 year: 2018 end-page: 758 article-title: Forecasting groundwater levels using nonlinear autoregressive networks with exogenous input (NARX) publication-title: Journal of Hydrology – year: 2023 – volume: 600 year: 2021 article-title: Goodness‐of‐fit criteria for hydrological models: Model calibration and performance assessment publication-title: Journal of Hydrology – volume: 531 start-page: 96 issue: 1 year: 2015 end-page: 110 article-title: Finding the right balance between groundwater model complexity and experimental effort via Bayesian model selection publication-title: Journal of Hydrology – volume: 572 start-page: 96 year: 2019 end-page: 107 article-title: The hydrologists guide to Bayesian model selection, averaging and combination publication-title: Journal of Hydrology – volume: 48 issue: 6 year: 2012 article-title: Reduced order parameter estimation using quasilinearization and quadratic programming publication-title: Water Resources Research – volume: 55 start-page: 646 issue: 5 year: 2017 end-page: 650 article-title: Defensible model complexity: A call for data‐based and goal‐oriented model choice publication-title: Groundwater – volume: 38 start-page: 178 year: 2012 end-page: 190 article-title: Software for hydrogeologic time series analysis, interfacing data with physical insight publication-title: Environmental Modelling & Software – volume: 9 year: 2019 article-title: Developing comparative mathematic models, BN and ANN for forecasting of groundwater levels publication-title: Groundwater for Sustainable Development – ident: e_1_2_8_81_1 doi: 10.1029/2011WR011471 – ident: e_1_2_8_96_1 doi: 10.1016/j.scitotenv.2020.141220 – ident: e_1_2_8_4_1 doi: 10.3390/w12010005 – ident: e_1_2_8_21_1 doi: 10.1038/s41598‐020‐60698‐9 – volume-title: Water and Soil Resources of the Wairau: Water Resources year: 1987 ident: e_1_2_8_56_1 – ident: e_1_2_8_43_1 doi: 10.3133/tm6A16 – ident: e_1_2_8_111_1 doi: 10.1016/j.jher.2017.11.004 – ident: e_1_2_8_99_1 doi: 10.1002/2014WR016292 – ident: e_1_2_8_51_1 doi: 10.5194/hess‐23‐4323‐2019 – ident: e_1_2_8_55_1 doi: 10.1016/j.advwatres.2012.10.001 – ident: e_1_2_8_106_1 doi: 10.1038/s41467‐022‐28770‐2 – ident: e_1_2_8_14_1 doi: 10.1016/j.watres.2024.121249 – ident: e_1_2_8_25_1 doi: 10.1111/gwat.12925 – ident: e_1_2_8_112_1 doi: 10.1029/2005WR004828 – ident: e_1_2_8_86_1 – volume-title: PEST, Model‐Independent Parameter Estimation User Manual Part II: PEST Utility Support Software year: 2016 ident: e_1_2_8_31_1 – ident: e_1_2_8_35_1 doi: 10.1088/1748‐9326/ab8e8c – ident: e_1_2_8_18_1 doi: 10.1023/A:1010933404324 – volume-title: PEST, Model‐Independent Parameter Estimation, User Manual Part I year: 2016 ident: e_1_2_8_30_1 – ident: e_1_2_8_6_1 doi: 10.13189/cea.2022.100304 – ident: e_1_2_8_90_1 doi: 10.5194/hess‐23‐3057‐2019 – ident: e_1_2_8_24_1 doi: 10.5194/hess‐2024‐111 – volume-title: Geomorphology of the Wairau Plains Implications for Floodplain Management Planning year: 1995 ident: e_1_2_8_11_1 – ident: e_1_2_8_76_1 doi: 10.1007/s12145‐021‐00654‐x – ident: e_1_2_8_79_1 doi: 10.1029/2009WR008933 – ident: e_1_2_8_98_1 doi: 10.1111/gwat.12625 – ident: e_1_2_8_103_1 doi: 10.1016/j.jhydrol.2017.07.021 – ident: e_1_2_8_105_1 doi: 10.5194/hess‐28‐2167‐2024 – ident: e_1_2_8_75_1 doi: 10.1029/wr019i001p00087 – ident: e_1_2_8_77_1 doi: 10.1016/j.jhydrol.2015.07.047 – ident: e_1_2_8_22_1 doi: 10.5194/hess‐27‐2397‐2023 – ident: e_1_2_8_67_1 doi: 10.1016/j.catena.2015.10.010 – ident: e_1_2_8_91_1 doi: 10.1007/s13201‐018‐0742‐6 – ident: e_1_2_8_73_1 doi: 10.1007/s10040‐013‐1029‐5 – ident: e_1_2_8_13_1 doi: 10.5194/hess-12-975-2008 – ident: e_1_2_8_110_1 doi: 10.1111/gwat.12819 – ident: e_1_2_8_8_1 doi: 10.1111/j.1745‐6584.2007.00382.x – ident: e_1_2_8_17_1 doi: 10.3390/w11051098 – ident: e_1_2_8_83_1 doi: 10.1016/j.jhydrol.2022.127630 – ident: e_1_2_8_82_1 doi: 10.1029/2019WR027009 – ident: e_1_2_8_26_1 doi: 10.1029/2020WR029500 – ident: e_1_2_8_52_1 doi: 10.1007/s11269‐018‐2126‐y – ident: e_1_2_8_19_1 – ident: e_1_2_8_32_1 doi: 10.1111/j.1745-6584.2003.tb02580.x – ident: e_1_2_8_104_1 doi: 10.1016/j.scitotenv.2021.146948 – ident: e_1_2_8_16_1 doi: 10.1016/j.jhydrol.2012.02.031 – ident: e_1_2_8_57_1 doi: 10.1016/j.gsd.2019.100237 – ident: e_1_2_8_72_1 doi: 10.1007/s12665‐014‐3608‐8 – ident: e_1_2_8_69_1 doi: 10.1016/j.jhydrol.2018.12.037 – ident: e_1_2_8_70_1 doi: 10.1016/j.scitotenv.2014.01.001 – ident: e_1_2_8_40_1 doi: 10.1016/j.jhydrol.2009.08.003 – ident: e_1_2_8_42_1 doi: 10.1080/00949650410001729472 – ident: e_1_2_8_15_1 doi: 10.1016/j.scitotenv.2023.168760 – ident: e_1_2_8_88_1 doi: 10.1016/j.jhydrol.2020.124871 – ident: e_1_2_8_62_1 doi: 10.3133/tm6A37 – ident: e_1_2_8_92_1 – ident: e_1_2_8_84_1 doi: 10.1002/joc.1350 – ident: e_1_2_8_109_1 doi: 10.1016/j.jhydrol.2021.126735 – ident: e_1_2_8_27_1 doi: 10.1016/j.jhydrol.2004.12.001 – ident: e_1_2_8_59_1 – ident: e_1_2_8_37_1 doi: 10.1029/2010wr010174 – ident: e_1_2_8_93_1 – ident: e_1_2_8_102_1 doi: 10.2307/3315929 – ident: e_1_2_8_64_1 doi: 10.1002/2013WR014800 – ident: e_1_2_8_34_1 doi: 10.1016/j.jhydrol.2021.127347 – ident: e_1_2_8_5_1 doi: 10.1016/j.jhydrol.2021.126674 – ident: e_1_2_8_20_1 doi: 10.1080/00288306.1981.10422739 – ident: e_1_2_8_58_1 – ident: e_1_2_8_54_1 doi: 10.1016/j.jhydrol.2011.08.002 – ident: e_1_2_8_10_1 doi: 10.1111/gwat.12927 – ident: e_1_2_8_100_1 doi: 10.1007/s12665‐013‐2306‐2 – ident: e_1_2_8_23_1 doi: 10.1029/2007WR006735 – ident: e_1_2_8_94_1 – ident: e_1_2_8_12_1 doi: 10.1016/j.matcom.2005.02.023 – ident: e_1_2_8_107_1 doi: 10.5194/hess‐25‐1671‐2021 – ident: e_1_2_8_66_1 doi: 10.1016/j.jhydrol.2005.02.026 – ident: e_1_2_8_87_1 doi: 10.1016/j.jhydrol.2013.07.012 – ident: e_1_2_8_38_1 doi: 10.1002/wrcr.20496 – ident: e_1_2_8_89_1 doi: 10.1029/2007WR006678 – ident: e_1_2_8_36_1 doi: 10.1016/j.jhydrol.2016.03.026 – volume-title: Machine Learning – A Probabilistic Perspective year: 2012 ident: e_1_2_8_61_1 – ident: e_1_2_8_41_1 doi: 10.1111/gwat.12554 – volume-title: Groundwaters of Marlborough year: 2011 ident: e_1_2_8_28_1 – ident: e_1_2_8_101_1 doi: 10.1029/2010WR009265 – ident: e_1_2_8_95_1 doi: 10.5675/HyWa – ident: e_1_2_8_9_1 doi: 10.1029/2001WR001136 – ident: e_1_2_8_7_1 doi: 10.1016/j.envsoft.2012.06.003 – ident: e_1_2_8_45_1 doi: 10.1214/ss/1009212519 – ident: e_1_2_8_44_1 doi: 10.1162/neco.1997.9.8.1735 – ident: e_1_2_8_97_1 doi: 10.1016/j.ejrh.2020.100715 – ident: e_1_2_8_68_1 doi: 10.1016/j.jhydrol.2012.01.045 – ident: e_1_2_8_39_1 doi: 10.1016/j.advwatres.2019.01.006 – ident: e_1_2_8_74_1 doi: 10.3389/frwa.2020.573034 – volume: 12 start-page: 2825 year: 2011 ident: e_1_2_8_63_1 article-title: Scikit‐learn: Machine learning in Python publication-title: Journal of Machine Learning Research – ident: e_1_2_8_48_1 doi: 10.1007/s11069‐010‐9603‐9 – ident: e_1_2_8_78_1 doi: 10.1002/2014WR016062 – ident: e_1_2_8_60_1 doi: 10.1007/s10898‐020‐00912‐0 – ident: e_1_2_8_85_1 doi: 10.1016/j.neucom.2022.03.014 – ident: e_1_2_8_2_1 – ident: e_1_2_8_29_1 doi: 10.1007/978-3-642-38739-5 – ident: e_1_2_8_65_1 doi: 10.1002/hyp.8214 – ident: e_1_2_8_33_1 doi: 10.3133/sir20105168 – ident: e_1_2_8_47_1 doi: 10.1002/2017WR021902 – ident: e_1_2_8_53_1 doi: 10.2166/nh.2016.264 – ident: e_1_2_8_108_1 doi: 10.1016/j.jhydrol.2018.01.045 – ident: e_1_2_8_3_1 doi: 10.1016/j.jhydrol.2011.06.013 – ident: e_1_2_8_71_1 doi: 10.1007/s12665‐023‐11012‐z – ident: e_1_2_8_49_1 – ident: e_1_2_8_50_1 doi: 10.1038/s41586‐023‐06879‐8 – ident: e_1_2_8_46_1 doi: 10.1016/j.jhydrol.2019.01.072 – ident: e_1_2_8_80_1 doi: 10.1002/9783527611515 |
| SSID | ssj0003909 |
| Score | 2.4405591 |
| Snippet | Groundwater level observations are used as decision variables for aquifer management, often in conjunction with models to provide predictions for operational... |
| SourceID | pubmedcentral proquest pubmed crossref wiley |
| SourceType | Open Access Repository Aggregation Database Index Database Publisher |
| StartPage | 484 |
| SubjectTerms | Aquifer management Aquifers Bayesian analysis Bayesian theory Calibration Decision trees Environmental Monitoring - methods Forecasting Groundwater Groundwater - analysis Groundwater flow Groundwater levels Learning algorithms Machine Learning Mathematical models Models, Theoretical New Zealand Physics Predictions Probability theory Research Paper Spoil Three dimensional flow Water Movements Wells |
| Title | Comparing Physics‐Based, Conceptual and Machine‐Learning Models to Predict Groundwater Levels by BMA |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fgwat.13487 https://www.ncbi.nlm.nih.gov/pubmed/40256895 https://www.proquest.com/docview/3231095750 https://www.proquest.com/docview/3192356383 https://pubmed.ncbi.nlm.nih.gov/PMC12272009 |
| Volume | 63 |
| WOSCitedRecordID | wos001470719500001&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 Full Collection 2020 customDbUrl: eissn: 1745-6584 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0003909 issn: 0017-467X 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/eLvHCXMwpV1Lb9QwEB6VFoly4FEopJTKCE6IIMd2NrHEZbuwcGirFWrF3iLHdnYroSzaZEG98RP4jfySjp0Hu6qEhLhEluwklufhbzzjGYBXRcSSQnIdUmO0czOiSFlKw9gwHpuoKFKufLGJ5OwsnU7lZAvedXdhmvwQ_YGbkwyvr52Aq7xaE_LZD1W_jTgC7luwE0U8cTzNxKTXw2jNy04PozqYtslJXRzPn3c3t6MbGPNmqOQ6hPV70Pj-_83-AdxrsScZNszyELZsuQd31zIS7sGdtij6_OoRzEdNjcJyRnycqK5-__x1jLueeUNGzW3HFX5OlYac-pBMi_1tvtYZcUXWvlakXpDJ0jmDauKOuUqDM7JLcuJilSqSX5Hj0-FjuBh_OB99CtvCDKESnCdhrqSRhhVxjvIfMxulmnPNLE3zSGGTFdxIKrSwA2otRYKjrZrzQV5YbhLN-D5sl4vSPgVSCKEGTKuE5u5KsFBoMQkrc8RpUhgZBfCyo0_2rcm_kXV2i1vDzK9hAIcd6bJWBquMO-gqEY7SAF703Sg9ziWiSrtY4RgHcGPUQTyAJw2l-98IBwdTGQeQbvBAP8Bl5t7sKS_nPkN3xJx7m8oAXnsm-MvUs49fhue-dfAvg5_BLnOViH3g8CFs18uVfQ639ff6sloeeUHAZzJNj2Dn_efxxck1TYoRAw |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fb9MwED9Bh7TtgT-DscAAI3hCZHJsp4kfu0IZoq0m1Im-RU7stJOmFDUpaG98BD4jnwSfk4ZWk5AQb5bsJI7vj3_nO98BvM4DFuWSZz7VOkM3oxUpQ6kfasZDHeR5zJUrNhGNx_F0Ks-b2By8C1Pnh2gP3FAynL5GAccD6Q0pn31X1UnALeK-DTvC8lHYgZ13nwcXw1YVW4NerlWx1QjTJj8phvL8eXp7R7oBM29GS26iWLcNDe795w_ch7sN_iS9mmEewC1THMD-RlbCA9htCqPPrx_CvF_XKSxmxMWKZuWvHz9P7c6n35J-feNxZV-nCk1GLizT2P4mZ-uMYKG1q5JUC3K-RIdQRfCoq9B2RmZJhhivVJL0mpyOeo_gYvB-0j_zm-IMvhKcR36qpJaa5WFqdUDITBBnnGfM0DgNlG2ynGtJRSZMlxpDLdGtvZrybpobrqOM8UPoFIvCHAHJhVBdlqmIpngtWChrNQkjU4vVpNAy8ODVmkDJ1zoHR7K2XXANE7eGHhyvaZc0clgmHOGrtJCUevCy7bYShG4RVZjFyo5BkBta_uEePK5J3X5GICSMZehBvMUE7QDMzr3dU1zOXZbugKGLm0oP3jgu-MvUkw9fehPXevIvg1_A7tlkNEyGH8efnsIew8rELpD4GDrVcmWewZ3sW3VZLp83cvEbYXsT-A |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NjtMwEB7Bglg48LP8BRYwgtOKIMd2mvjYLRQQu1UPi-gtcmKnXWmVrtoUtDcegWfkSZhx0tBqJSTELZKdxPJ4xt94xt8AvC4jkZRaFiG3tqAwI6qU4zyMrZCxjcoylcYXm0hGo3Qy0eM2N4fuwjT8EN2BG2mGt9ek4O7clhtaPv1u6reRRMR9Fa6pGI0sETurcWeI0Z3Xa0OM9mDSspNSIs-fd7f3o0sg83Ku5CaG9ZvQ8M5_Dv8u3G7RJ-s3y-UeXHHVHtza4CTcg922LPrs4j7MBk2VwmrKfKZosfz14-ch7nv2DRs09x1X-DlTWXbskzIdtreMrVNGZdbOlqyes_GCwkE1o4OuyuKI3IIdUbbSkuUX7PC4_wC-DN-fDD6GbWmG0CgpkzA32moryjhHCxALF6WFlIVwPM0jg4-ilFZzVSjX485xFDl6q7ns5aWTNimEfAg71bxyj4GVSpmeKEzCc7oUrAz6TMrpHJGaVlZHAbxaCyg7bxg4srXnQnOY-TkMYH8tu6zVwmUmCbxqBKQ8gJddM-oPBUVM5eYr7EMQN0YrJAN41Ii6-40iQJjqOIB0axF0HYibe7ulOp15ju5IUICb6wAO_Cr4y9CzD1_7J_7pyb90fgE3xu-G2dGn0eencFNQWWKfRbwPO_Vi5Z7B9eJbfbpcPPdK8Rv4MBHh |
| 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=Comparing+Physics%E2%80%90Based%2C+Conceptual+and+Machine%E2%80%90Learning+Models+to+Predict+Groundwater+Levels+by+BMA&rft.jtitle=Ground+water&rft.au=W%C3%B6hling%2C+Thomas&rft.au=Delgadillo%2C+Alvaro+Oliver+Crespo&rft.au=Kraft%2C+Moritz&rft.au=Guthke%2C+Anneli&rft.date=2025-07-01&rft.pub=Ground+Water+Publishing+Company&rft.issn=0017-467X&rft.eissn=1745-6584&rft.volume=63&rft.issue=4&rft.spage=484&rft.epage=505&rft_id=info:doi/10.1111%2Fgwat.13487&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0017-467X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0017-467X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0017-467X&client=summon |