NWTOPT – A hyperparameter optimization approach for selection of environmental model solver settings
Hyperparameter optimization approaches were applied to improve performance and accuracy of groundwater flow models. Freely available new software, NWTOPT, is described that uses Tree of Parzen Estimators (TPE) and Random Search algorithms to optimize MODFLOW-NWT's solver settings. We ran 3500 t...
Gespeichert in:
| Veröffentlicht in: | Environmental modelling & software : with environment data news Jg. 147; S. 105250 |
|---|---|
| Hauptverfasser: | , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Oxford
Elsevier Ltd
01.01.2022
Elsevier Science Ltd |
| Schlagworte: | |
| ISSN: | 1364-8152, 1873-6726 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Hyperparameter optimization approaches were applied to improve performance and accuracy of groundwater flow models. Freely available new software, NWTOPT, is described that uses Tree of Parzen Estimators (TPE) and Random Search algorithms to optimize MODFLOW-NWT's solver settings. We ran 3500 trials on a steady-state and transient model. To quantify the performance of candidate solver settings, we defined a loss function based on time elapsed and mass balance error of the MODFLOW-NWT forward run. Before optimization the steady-state model ran in ∼12 min and the transient model ran in ∼5 h with acceptable mass balance error (<1%). After optimization runtimes were reduced to ∼2.7 min (steady state) and ∼48 min (transient) with errors below 0.1%. In both cases TPE found hyperparameters that resulted in faster running and lower error models than those found by Random Search. The time to complete the optimization trials was also shorter with the TPE algorithm.
•NWTOPT customizes off-the-shelf software for seamless application to MODFLOWNWT solver settings.•NWTOPT uses high-throughput computing to test multiple solver settings simultaneously.•The NWTOPT performance metric “loss” captures both aspects of desirable MODFLOW-NWT runs – short run times and low mass balance errors.•Benefits over manually selected solver settings are demonstrated using both a steady state and transient MODFLOW-NWT model.•The Tree of Parzen Estimator algorithm performed better than a Random Search approach for both steady state and transient models. |
|---|---|
| AbstractList | Hyperparameter optimization approaches were applied to improve performance and accuracy of groundwater flow models. Freely available new software, NWTOPT, is described that uses Tree of Parzen Estimators (TPE) and Random Search algorithms to optimize MODFLOW-NWT's solver settings. We ran 3500 trials on a steady-state and transient model. To quantify the performance of candidate solver settings, we defined a loss function based on time elapsed and mass balance error of the MODFLOW-NWT forward run. Before optimization the steady-state model ran in ∼12 min and the transient model ran in ∼5 h with acceptable mass balance error (<1%). After optimization runtimes were reduced to ∼2.7 min (steady state) and ∼48 min (transient) with errors below 0.1%. In both cases TPE found hyperparameters that resulted in faster running and lower error models than those found by Random Search. The time to complete the optimization trials was also shorter with the TPE algorithm.
•NWTOPT customizes off-the-shelf software for seamless application to MODFLOWNWT solver settings.•NWTOPT uses high-throughput computing to test multiple solver settings simultaneously.•The NWTOPT performance metric “loss” captures both aspects of desirable MODFLOW-NWT runs – short run times and low mass balance errors.•Benefits over manually selected solver settings are demonstrated using both a steady state and transient MODFLOW-NWT model.•The Tree of Parzen Estimator algorithm performed better than a Random Search approach for both steady state and transient models. Hyperparameter optimization approaches were applied to improve performance and accuracy of groundwater flow models. Freely available new software, NWTOPT, is described that uses Tree of Parzen Estimators (TPE) and Random Search algorithms to optimize MODFLOW-NWT's solver settings. We ran 3500 trials on a steady-state and transient model. To quantify the performance of candidate solver settings, we defined a loss function based on time elapsed and mass balance error of the MODFLOW-NWT forward run. Before optimization the steady-state model ran in ∼12 min and the transient model ran in ∼5 h with acceptable mass balance error (<1%). After optimization runtimes were reduced to ∼2.7 min (steady state) and ∼48 min (transient) with errors below 0.1%. In both cases TPE found hyperparameters that resulted in faster running and lower error models than those found by Random Search. The time to complete the optimization trials was also shorter with the TPE algorithm. |
| ArticleNumber | 105250 |
| Author | Hunt, Randall J. Newcomer, Max W. |
| Author_xml | – sequence: 1 givenname: Max W. surname: Newcomer fullname: Newcomer, Max W. email: mnewcomer@usgs.gov – sequence: 2 givenname: Randall J. surname: Hunt fullname: Hunt, Randall J. email: rjhunt@usgs.gov |
| BookMark | eNqFkM9KAzEQh4MoqNVHEAJevGxNsrvZFQ8i4j8Q9VDxGNJkoim7yZqkBT35Dr6hT2LaevIiBDIMv29m-HbRpvMOEDqgZEwJ5cezMbhF9CaNGWE092pWkw20Q9umLHjD-GauS14VLa3ZNtqNcUYIyXW1g8z98-ThcYK_P7_wOX59HyAMMsgeEgTsh2R7-yGT9Q7LYQheqldsfMAROlCrtjc4b7fBux5ckh3uvYYOR98tYJlLybqXuIe2jOwi7P_-I_R0dTm5uCnuHq5vL87vClXRJhVNe6IrMtU1LVvemlrLykwr3XCiwegSmGGtpGDA8PpEKU5UCS1njeSS6EpBOUJH67n51rc5xCR6GxV0nXTg51Ewnj20NCM5evgnOvPz4PJ1OcVKUrEyvxGq1ykVfIwBjBiC7WV4F5SIpX0xE7_2xdK-WNvP3OkfTtm0EpmCtN2_9NmahuxqYSGIqCw4BdqG7F1ob_-Z8AN2l6j0 |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2025_3526885 crossref_primary_10_1111_gwat_13270 crossref_primary_10_1007_s11440_022_01779_z crossref_primary_10_1007_s00704_024_04947_1 crossref_primary_10_1016_j_envsoft_2025_106489 crossref_primary_10_1016_j_engappai_2023_107559 crossref_primary_10_1080_15623599_2024_2304392 |
| Cites_doi | 10.1111/gwat.12320 10.1016/j.envsoft.2018.03.025 10.1111/j.1745-6584.2010.00699.x 10.1177/0278364904045481 10.1016/j.envsoft.2018.06.007 10.1111/gwat.13106 10.25080/Majora-8b375195-003 |
| ContentType | Journal Article |
| Copyright | 2021 Copyright Elsevier Science Ltd. Jan 2022 |
| Copyright_xml | – notice: 2021 – notice: Copyright Elsevier Science Ltd. Jan 2022 |
| DBID | 6I. AAFTH AAYXX CITATION 7QH 7SC 7ST 7UA 8FD C1K FR3 JQ2 KR7 L7M L~C L~D SOI 7S9 L.6 |
| DOI | 10.1016/j.envsoft.2021.105250 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef Aqualine Computer and Information Systems Abstracts Environment Abstracts Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management Engineering Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Environment Abstracts AGRICOLA AGRICOLA - Academic |
| DatabaseTitle | CrossRef Civil Engineering Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Aqualine Environment Abstracts Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management Computer and Information Systems Abstracts Professional AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | Civil Engineering Abstracts AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Ecology Computer Science Environmental Sciences |
| EISSN | 1873-6726 |
| ExternalDocumentID | 10_1016_j_envsoft_2021_105250 S1364815221002929 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 1B1 1RT 1~. 1~5 29G 4.4 457 4G. 53G 5GY 5VS 6I. 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAFTH AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN AAYOK ABBOA ABFNM ABFYP ABJNI ABLST ABMAC ABXDB ABYKQ ACDAQ ACGFS ACIWK ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD AEBSH AEKER AENEX AFKWA AFRAH AFTJW AFXIZ AGHFR AGUBO AGYEJ AHEUO AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV AKIFW ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BKOJK BLECG BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HVGLF HZ~ IHE J1W KCYFY KOM M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSJ SSV SSZ T5K UHS ~02 ~G- 9DU AAHBH AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD 7QH 7SC 7ST 7UA 8FD AGCQF C1K FR3 JQ2 KR7 L7M L~C L~D SOI 7S9 L.6 |
| ID | FETCH-LOGICAL-c417t-789d40bd513868f5da4fb4d760defd3e2f28a1efef659cc60c3e8627a6a0d4ce3 |
| ISICitedReferencesCount | 8 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000744254300002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1364-8152 |
| IngestDate | Sat Sep 27 23:57:57 EDT 2025 Wed Aug 13 08:12:42 EDT 2025 Sat Nov 29 07:01:05 EST 2025 Tue Nov 18 22:20:44 EST 2025 Fri Feb 23 02:41:04 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Hyperparameter Parameter estimation Uncertainty Calibration Groundwater modeling Optimization |
| Language | English |
| License | This is an open access article under the CC BY license. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c417t-789d40bd513868f5da4fb4d760defd3e2f28a1efef659cc60c3e8627a6a0d4ce3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| OpenAccessLink | https://dx.doi.org/10.1016/j.envsoft.2021.105250 |
| PQID | 2623042342 |
| PQPubID | 2047471 |
| ParticipantIDs | proquest_miscellaneous_2636481627 proquest_journals_2623042342 crossref_primary_10_1016_j_envsoft_2021_105250 crossref_citationtrail_10_1016_j_envsoft_2021_105250 elsevier_sciencedirect_doi_10_1016_j_envsoft_2021_105250 |
| PublicationCentury | 2000 |
| PublicationDate | January 2022 2022-01-00 20220101 |
| PublicationDateYYYYMMDD | 2022-01-01 |
| PublicationDate_xml | – month: 01 year: 2022 text: January 2022 |
| PublicationDecade | 2020 |
| PublicationPlace | Oxford |
| PublicationPlace_xml | – name: Oxford |
| PublicationTitle | Environmental modelling & software : with environment data news |
| PublicationYear | 2022 |
| Publisher | Elsevier Ltd Elsevier Science Ltd |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier Science Ltd |
| References | White, Hunt, Fienen, Doherty (bib20) 2020 Haserodt, Hunt, Fienen, Feinstein (bib8) 2021 Newcomer, Hunt (bib16) 2021 (bib9) 2021 Rossetto, De Filippis, Borsi, Foglia, Cannata, Criollo, Vázquez-Suñé (bib19) 2018; 107 Bergstra, Bengio (bib3) 2012; 13 Hunt, White, Duncan, Haugh, Doherty (bib11) 2021; 59 LaValle, Branicky, Lindemann (bib14) 2004; 23 Markstrom, Niswonger, Regan, Prudic, Barlow (bib15) 2008 Doherty (bib6) 2021 Panday, Langevin, Niswonger, Ibaraki, Hughes (bib18) 2013; Book 6 Bergstra, Yamins, Cox (bib5) 2013 Anderson, Woessner, Hunt (bib1) 2015 Hunt, Luchette, Schreüder, Rumbaugh, Doherty, Tonkin, Rumbaugh (bib10) 2010; 48 Langevin, Hughes, Banta, Niswonger, Panday, Provost (bib13) 2017 Bakinam, Goodall, Zell, Voce, Morsy, Sadler, Yuan, Malik (bib2) 2018; 105 Bergstra, Yamins, Cox (bib4) 2013; vol. 28 Koehrsen (bib12) 2018 Fienen, Hunt (bib7) 2015; 53 Niswonger, Panday, Ibaraki (bib17) 2011 LaValle (10.1016/j.envsoft.2021.105250_bib14) 2004; 23 Doherty (10.1016/j.envsoft.2021.105250_bib6) 2021 Anderson (10.1016/j.envsoft.2021.105250_bib1) 2015 Bergstra (10.1016/j.envsoft.2021.105250_bib4) 2013; vol. 28 Bakinam (10.1016/j.envsoft.2021.105250_bib2) 2018; 105 Fienen (10.1016/j.envsoft.2021.105250_bib7) 2015; 53 Langevin (10.1016/j.envsoft.2021.105250_bib13) 2017 Rossetto (10.1016/j.envsoft.2021.105250_bib19) 2018; 107 (10.1016/j.envsoft.2021.105250_bib9) 2021 Hunt (10.1016/j.envsoft.2021.105250_bib11) 2021; 59 Bergstra (10.1016/j.envsoft.2021.105250_bib5) 2013 Haserodt (10.1016/j.envsoft.2021.105250_bib8) 2021 Niswonger (10.1016/j.envsoft.2021.105250_bib17) 2011 Koehrsen (10.1016/j.envsoft.2021.105250_bib12) 2018 Bergstra (10.1016/j.envsoft.2021.105250_bib3) 2012; 13 Panday (10.1016/j.envsoft.2021.105250_bib18) 2013; Book 6 White (10.1016/j.envsoft.2021.105250_bib20) 2020 Hunt (10.1016/j.envsoft.2021.105250_bib10) 2010; 48 Markstrom (10.1016/j.envsoft.2021.105250_bib15) 2008 Newcomer (10.1016/j.envsoft.2021.105250_bib16) 2021 |
| References_xml | – volume: 48 start-page: 360 year: 2010 end-page: 365 ident: bib10 article-title: Using a Cloud to replenish parched groundwater modeling efforts publication-title: Groundwater – year: 2011 ident: bib17 article-title: MODFLOW-NWT, A Newton formulation for MODFLOW-2005 – volume: 107 start-page: 210 year: 2018 end-page: 230 ident: bib19 article-title: Integrating free and open source tools and distributed modelling codes in GIS environment for data-based groundwater management publication-title: Environ. Model. Software – volume: 53 start-page: 180 year: 2015 end-page: 184 ident: bib7 article-title: High-throughput computing vs. High-performance computing for groundwater applications publication-title: Groundwater – year: 2008 ident: bib15 article-title: GSFLOW-coupled ground-water and surface-water FLOW model based on the integration of the precipitation-runoff modeling system (PRMS) and the modular ground-water flow model (MODFLOW-2005) – volume: 59 start-page: 788 year: 2021 end-page: 798 ident: bib11 article-title: Evaluating lower computational burden approaches for calibration of large environmental models publication-title: Groundwater – year: 2021 ident: bib9 article-title: HTCondor Version 9.0 Manual – volume: Book 6 start-page: 66 year: 2013 ident: bib18 article-title: MODFLOW-USG version 1: an unstructured grid version of MODFLOW for simulating groundwater flow and tightly coupled processes using a control volume finite-difference formulation publication-title: U.S. Geological Survey Techniques and Methods Report – volume: 105 start-page: 217 year: 2018 end-page: 229 ident: bib2 article-title: Integrating scientific cyberinfrastructures to improve reproducibility in computational hydrology: example for HydroShare and GeoTrust publication-title: Environ. Model. Software – year: 2021 ident: bib16 article-title: NWTOPT Software and Examples – year: 2015 ident: bib1 publication-title: Applied Groundwater Modeling: Simulation of Flow and Advective Transport – start-page: 353 year: 2021 ident: bib6 article-title: PEST and its Utility Support Software: Brisbane, Australia – year: 2013 ident: bib5 article-title: Hyperopt: a Python library for optimizing the hyperparameters of machine learning algorithms publication-title: Proceedings of the 12th Python in Science Conference – year: 2020 ident: bib20 article-title: Approaches to highly parameterized inversion: PEST++ Version 5, a software suite for parameter estimation, uncertainty analysis, management optimization and sensitivity analysis – volume: 13 start-page: 281 year: 2012 end-page: 305 ident: bib3 article-title: Random search for hyper-parameter optimization publication-title: JMLR – start-page: 94 p. year: 2021 ident: bib8 article-title: Groundwater/surface-water interactions in the Partridge River Basin and evaluation of hypothetical future mine pits, Minnesota publication-title: U.S. Geological Survey Scientific Investigations Report 2021-5038 – year: 2018 ident: bib12 article-title: A Conceptual Explanation of Bayesian Hyperparameter Optimization for Machine Learning – year: 2017 ident: bib13 article-title: Documentation for the MODFLOW 6 groundwater flow model – volume: vol. 28 year: 2013 ident: bib4 article-title: Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures publication-title: Proceedings of the 30th International Conference on Machine Learning – volume: 23 start-page: 673 year: 2004 end-page: 692 ident: bib14 article-title: On the relationship between classical grid search and probabilistic roadmaps publication-title: Int. J. Robot Res. – volume: 53 start-page: 180 issue: 2 year: 2015 ident: 10.1016/j.envsoft.2021.105250_bib7 article-title: High-throughput computing vs. High-performance computing for groundwater applications publication-title: Groundwater doi: 10.1111/gwat.12320 – volume: vol. 28 year: 2013 ident: 10.1016/j.envsoft.2021.105250_bib4 article-title: Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures – volume: Book 6 start-page: 66 year: 2013 ident: 10.1016/j.envsoft.2021.105250_bib18 article-title: MODFLOW-USG version 1: an unstructured grid version of MODFLOW for simulating groundwater flow and tightly coupled processes using a control volume finite-difference formulation publication-title: U.S. Geological Survey Techniques and Methods Report – volume: 105 start-page: 217 year: 2018 ident: 10.1016/j.envsoft.2021.105250_bib2 article-title: Integrating scientific cyberinfrastructures to improve reproducibility in computational hydrology: example for HydroShare and GeoTrust publication-title: Environ. Model. Software doi: 10.1016/j.envsoft.2018.03.025 – volume: 13 start-page: 281 issue: 10 year: 2012 ident: 10.1016/j.envsoft.2021.105250_bib3 article-title: Random search for hyper-parameter optimization publication-title: JMLR – year: 2008 ident: 10.1016/j.envsoft.2021.105250_bib15 – start-page: 353 year: 2021 ident: 10.1016/j.envsoft.2021.105250_bib6 – volume: 48 start-page: 360 issue: 3 year: 2010 ident: 10.1016/j.envsoft.2021.105250_bib10 article-title: Using a Cloud to replenish parched groundwater modeling efforts publication-title: Groundwater doi: 10.1111/j.1745-6584.2010.00699.x – year: 2015 ident: 10.1016/j.envsoft.2021.105250_bib1 – volume: 23 start-page: 673 issue: 7–8 year: 2004 ident: 10.1016/j.envsoft.2021.105250_bib14 article-title: On the relationship between classical grid search and probabilistic roadmaps publication-title: Int. J. Robot Res. doi: 10.1177/0278364904045481 – year: 2011 ident: 10.1016/j.envsoft.2021.105250_bib17 – year: 2020 ident: 10.1016/j.envsoft.2021.105250_bib20 – year: 2021 ident: 10.1016/j.envsoft.2021.105250_bib9 – volume: 107 start-page: 210 year: 2018 ident: 10.1016/j.envsoft.2021.105250_bib19 article-title: Integrating free and open source tools and distributed modelling codes in GIS environment for data-based groundwater management publication-title: Environ. Model. Software doi: 10.1016/j.envsoft.2018.06.007 – year: 2021 ident: 10.1016/j.envsoft.2021.105250_bib16 – volume: 59 start-page: 788 issue: 6 year: 2021 ident: 10.1016/j.envsoft.2021.105250_bib11 article-title: Evaluating lower computational burden approaches for calibration of large environmental models publication-title: Groundwater doi: 10.1111/gwat.13106 – year: 2017 ident: 10.1016/j.envsoft.2021.105250_bib13 – year: 2013 ident: 10.1016/j.envsoft.2021.105250_bib5 article-title: Hyperopt: a Python library for optimizing the hyperparameters of machine learning algorithms doi: 10.25080/Majora-8b375195-003 – year: 2018 ident: 10.1016/j.envsoft.2021.105250_bib12 – start-page: 94 p. year: 2021 ident: 10.1016/j.envsoft.2021.105250_bib8 article-title: Groundwater/surface-water interactions in the Partridge River Basin and evaluation of hypothetical future mine pits, Minnesota publication-title: U.S. Geological Survey Scientific Investigations Report 2021-5038 |
| SSID | ssj0001524 |
| Score | 2.3878186 |
| Snippet | Hyperparameter optimization approaches were applied to improve performance and accuracy of groundwater flow models. Freely available new software, NWTOPT, is... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 105250 |
| SubjectTerms | Algorithms Calibration computer software Environmental modeling environmental models Errors Groundwater Groundwater availability Groundwater flow Groundwater modeling Hyperparameter Mass balance Optimization Parameter estimation Performance enhancement Run time (computers) Search algorithms Solvers Steady state models Uncertainty |
| Title | NWTOPT – A hyperparameter optimization approach for selection of environmental model solver settings |
| URI | https://dx.doi.org/10.1016/j.envsoft.2021.105250 https://www.proquest.com/docview/2623042342 https://www.proquest.com/docview/2636481627 |
| Volume | 147 |
| WOSCitedRecordID | wos000744254300002&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: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-6726 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001524 issn: 1364-8152 databaseCode: AIEXJ dateStart: 19970101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3NjtMwELZKFyQ48FNYUViQkbhFKYnj2s6xQkWwEmUFRdtblMS2llU3XbXdUm6ceAHekCdhHDtp2gUtIHGJKtc_SebLZDyZ-Qah5yTmKWWh9EPJcp9mLPDjKBB-Fuso45qJVGVlsQk-GonJJD5qtb5VuTCrKS8KsV7H5_9V1NAGwjaps38h7npSaIDfIHQ4gtjh-EeCHx2P3x2NvSqKIYJH_wQ2m3ND8n1mgl-8GaiJM5d_WZOKl_GGi7IqjrMhGzlwJsXElMzx4NRXhv9ZleHSiy2__uXuU-uHYDBMLz-bGDPjgChdv43JPROl6jXNe9C8cGcsmN6ma--4t0Gf5Ul4bxwg06l32Gu6LQjZcVvU-TSb4CWjfiNGfRFaTtuesm2CRz7jNq--1tmWpvOS_reuiNMeXIS5Mtj_k9CUMiaW3XaHWvuDWc8sRwwRLRiK19Ae4bDFaqO9wZvh5LB-p0MfWx7Znd8mF-zFLxf7nZWz874vjZjxXXTb7T7wwKLmHmqpooPuVJU9sFP0HXRjWJKZf-mgWw3Cyg7a3xJy1X9xH2mLOvzj63c8wNt4w0284QpvGPCGa7zhmcZbeMMlgLDFG67w9gB9fDUcv3ztuxIefk5DvvS5iCUNMtkPI8GE7suU6oxKzgKptIwU0USkodJKs36c5yzIIwV7bJ6yNJA0V9E-ahezQj1EOKA651KoFOah8IZOwaziMhVZHtBMUNpFtLrlSe747U2ZlWlSBTKeJk5SiZFUYiXVRb162LkleLlqgKjkmTgr1VqfCYDwqqEHlfwTpzEWCWHmuwyJKOmiZ_XfoOTNl7u0ULML06cEKtyYR_---mN0c_MgHqD2cn6hnqDr-Wr5aTF_6hD_ExHh1JM |
| linkProvider | Elsevier |
| 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=NWTOPT+%E2%80%93+A+hyperparameter+optimization+approach+for+selection+of+environmental+model+solver+settings&rft.jtitle=Environmental+modelling+%26+software+%3A+with+environment+data+news&rft.au=Newcomer%2C+Max+W.&rft.au=Hunt%2C+Randall+J.&rft.date=2022-01-01&rft.pub=Elsevier+Ltd&rft.issn=1364-8152&rft.eissn=1873-6726&rft.volume=147&rft_id=info:doi/10.1016%2Fj.envsoft.2021.105250&rft.externalDocID=S1364815221002929 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1364-8152&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1364-8152&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1364-8152&client=summon |