A Fortran-Python Interface for Integrating Machine Learning Parameterization into Earth System Models
Parameterizations in Earth System Models (ESMs) are subject to biases and uncertainties arising from subjective empirical assumptions and incomplete understanding of the underlying physical processes. Recently, the growing representational capability of machine learning (ML) in solving complex probl...
Gespeichert in:
| Veröffentlicht in: | Geoscientific model development Jg. 18; H. 6 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
United States
Copernicus Publications, EGU
24.03.2025
|
| Schlagworte: | |
| ISSN: | 1991-9603 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Parameterizations in Earth System Models (ESMs) are subject to biases and uncertainties arising from subjective empirical assumptions and incomplete understanding of the underlying physical processes. Recently, the growing representational capability of machine learning (ML) in solving complex problems has spawned immense interests in climate science applications. Specifically, ML-based parameterizations have been developed to represent convection, radiation and microphysics processes in ESMs by learning from observations or high-resolution simulations, which have the potential to improve the accuracies and alleviate the uncertainties. Previous works have developed some surrogate models for these processes using ML. These surrogate models need to be coupled with the dynamical core of ESMs to investigate the effectiveness and their performance in a coupled system. In this study, we present a novel Fortran-Python interface designed to seamlessly integrate ML parameterizations into ESMs. This interface showcases high versatility by supporting popular ML frameworks like PyTorch, TensorFlow, and Scikit-learn. We demonstrate the interface's modularity and reusability through two cases: a ML trigger function for convection parameterization and a ML wildfire model. We conduct a comprehensive evaluation of memory usage and computational overhead resulting from the integration of Python codes into the Fortran ESMs. By leveraging this flexible interface, ML parameterizations can be effectively developed, tested, and integrated into ESMs. |
|---|---|
| AbstractList | Parameterizations in Earth System Models (ESMs) are subject to biases and uncertainties arising from subjective empirical assumptions and incomplete understanding of the underlying physical processes. Recently, the growing representational capability of machine learning (ML) in solving complex problems has spawned immense interests in climate science applications. Specifically, ML-based parameterizations have been developed to represent convection, radiation and microphysics processes in ESMs by learning from observations or high-resolution simulations, which have the potential to improve the accuracies and alleviate the uncertainties. Previous works have developed some surrogate models for these processes using ML. These surrogate models need to be coupled with the dynamical core of ESMs to investigate the effectiveness and their performance in a coupled system. In this study, we present a novel Fortran-Python interface designed to seamlessly integrate ML parameterizations into ESMs. This interface showcases high versatility by supporting popular ML frameworks like PyTorch, TensorFlow, and Scikit-learn. We demonstrate the interface's modularity and reusability through two cases: a ML trigger function for convection parameterization and a ML wildfire model. We conduct a comprehensive evaluation of memory usage and computational overhead resulting from the integration of Python codes into the Fortran ESMs. By leveraging this flexible interface, ML parameterizations can be effectively developed, tested, and integrated into ESMs. |
| Author | Morcrette, Cyril Liu, Ye Van Weverberg, Kwinten Lin, Wuyin Rodrigues, Joana Zhang, Meng Xie, Shaocheng Zhang, Tao |
| Author_xml | – sequence: 1 orcidid: 0000000257001966 fullname: Zhang, Tao organization: Brookhaven National Laboratory (BNL), Upton, NY (United States)] (ORCID:0000000257001966 – sequence: 2 orcidid: 0000000242408472 fullname: Morcrette, Cyril organization: Exeter Met Office (United Kingdom); Univ. of Exeter (United Kingdom)] (ORCID:0000000242408472 – sequence: 3 fullname: Zhang, Meng organization: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States) – sequence: 4 fullname: Lin, Wuyin organization: Brookhaven National Laboratory (BNL), Upton, NY (United States) – sequence: 5 orcidid: 0000000189315145 fullname: Xie, Shaocheng organization: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)] (ORCID:0000000189315145 – sequence: 6 orcidid: 0000000151318412 fullname: Liu, Ye organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:0000000151318412 – sequence: 7 orcidid: 0000000253977320 fullname: Van Weverberg, Kwinten organization: Ghent Univ. (Belgium); Royal Meteorological Institute of Belgium (Belgium)] (ORCID:0000000253977320 – sequence: 8 fullname: Rodrigues, Joana organization: Exeter Met Office (United Kingdom) |
| BackLink | https://www.osti.gov/servlets/purl/2514350$$D View this record in Osti.gov |
| BookMark | eNotjE1vAiEURVnYpNp21T9Auqd9MAwMS2O0NdHUpO4NMA9nGoUE2NhfX_uxujk3594ZmcQUkZBHDs8tN_LleO6ZACGZNhMy5cZwZhQ0t2RWyieAMlrpKcE5XaVcs41sd6lDinQdK-ZgPdKQ8i8ds61jPNKt9cMYkW7Q5vhT7Gy2Z7zq49fVuG7HWBNd2lwH-nEpFc90m3o8lXtyE-yp4MN_3pH9arlfvLHN--t6Md-wpKRhPSB4jsBdB75z2oHQzmlQtmu4NlJJ1ChCEzQq16rWidA705ogoJMgoLkjT3-3qdTxUPxY0Q8-xYi-HkTLZdNC8w0XCld0 |
| ContentType | Journal Article |
| CorporateAuthor | Brookhaven National Laboratory (BNL), Upton, NY (United States) |
| CorporateAuthor_xml | – name: Brookhaven National Laboratory (BNL), Upton, NY (United States) |
| DBID | OIOZB OTOTI |
| DOI | 10.5194/gmd-2024-79 |
| DatabaseName | OSTI.GOV - Hybrid OSTI.GOV |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geology Environmental Sciences |
| ExternalDocumentID | 2514350 |
| GroupedDBID | 5VS 8R4 8R5 AAFWJ ABDBF ACUHS ADBBV AENEX AFPKN AHGZY ALMA_UNASSIGNED_HOLDINGS BCNDV ESX GROUPED_DOAJ H13 IAO IEA IEP ISR ITC KQ8 OIOZB OK1 OTOTI P2P Q2X RKB RNS TR2 TUS |
| ID | FETCH-LOGICAL-o649-d0e0c1e01b80c8b7b027bb706a83179464e7e2f3f7e6b565b2fdb959f20840203 |
| ISSN | 1991-9603 |
| IngestDate | Mon Aug 04 02:20:20 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6 |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-o649-d0e0c1e01b80c8b7b027bb706a83179464e7e2f3f7e6b565b2fdb959f20840203 |
| Notes | BNL--227547-2025-JAAM AC05-76RL01830; SC0012704; AC52-07NA27344 USDOE Office of Science (SC), Biological and Environmental Research (BER) |
| ORCID | 0000000189315145 0000000242408472 0000000253977320 0000000257001966 0000000151318412 |
| OpenAccessLink | http://dx.doi.org/10.5194/gmd-2024-79 |
| ParticipantIDs | osti_scitechconnect_2514350 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-03-24 |
| PublicationDateYYYYMMDD | 2025-03-24 |
| PublicationDate_xml | – month: 03 year: 2025 text: 2025-03-24 day: 24 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Geoscientific model development |
| PublicationYear | 2025 |
| Publisher | Copernicus Publications, EGU |
| Publisher_xml | – name: Copernicus Publications, EGU |
| SSID | ssj0069767 |
| Score | 2.286562 |
| Snippet | Parameterizations in Earth System Models (ESMs) are subject to biases and uncertainties arising from subjective empirical assumptions and incomplete... |
| SourceID | osti |
| SourceType | Open Access Repository |
| SubjectTerms | ENVIRONMENTAL SCIENCES |
| Title | A Fortran-Python Interface for Integrating Machine Learning Parameterization into Earth System Models |
| URI | https://www.osti.gov/servlets/purl/2514350 |
| Volume | 18 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAGF databaseName: Copernicus Publications issn: 1991-9603 databaseCode: RKB dateStart: 20080101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: http://publications.copernicus.org/open-access_journals/open_access_journals_a_z.html omitProxy: false ssIdentifier: ssj0069767 providerName: Copernicus Gesellschaft – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals issn: 1991-9603 databaseCode: DOA dateStart: 20080101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.doaj.org/ omitProxy: false ssIdentifier: ssj0069767 providerName: Directory of Open Access Journals |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Rb9MwELZggLQXBINpY4D8wNsU4TleHD9WU1cmjWkPRextqu3LhATJ1LTT-u93ZztpViEED7xElV1ZTe7L-Xz97jvGPjnnwHgF-CJVOlNeOCIBQGa9gFyV3urKh2YT-uKivLoylymr1IZ2Arquy_t7c_tfTY1jaGwqnf0Hc_eL4gB-RqPjFc2O178y_OjwFENq3IKyyxUJA8SkXzVzUd77LOlDUIrga2BSQieyeoPxJHG1SL45VmeSmkRzOJ7RfztR2zw0T_vZDmPaCURBzMA6iq11ulqsIa2mT01PZ01v5mbuiCkc6Yir-Zrv0X-baLfd4HkUPPi-XCW98JSukMfE15LrdOVJcwt4R27ZPspLBsc_-TZwxMTIwtNV_ntP3bndzQ0A41GFBrr55RETUmWxUc2GorYMQaJ4yp5Jjeep7hwet-8C47PQkaf7AbGokxb-PFgWd_AGffAgFpm-Yi_TIYKPovFfsydQ77Dd8bpmESeT02532ItJ6N68esNgxB9jg_fY4IgNPsAGT9jgHTb4JjY4YYMHbPCIDR6x8ZZNT8fTky9Z6rORNYUyGb6Vwh2BOLKlcKXVVkhtrRbFrMzJXRcKNMgqrzQUFuN_KytvzbGppCgp-5Dvsq26qWGP8cLgShhUWmFA4UM24JWS3hucgEqZfXZAT-0aUUkSxY64XG5xnQzy7o-zB2x7jaf3bGsxX8IH9tzdLX6084_Bhg-PYmtD |
| linkProvider | Directory of Open Access Journals |
| 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=A+Fortran-Python+Interface+for+Integrating+Machine+Learning+Parameterization+into+Earth+System+Models&rft.jtitle=Geoscientific+model+development&rft.au=Zhang%2C+Tao&rft.au=Morcrette%2C+Cyril&rft.au=Zhang%2C+Meng&rft.au=Lin%2C+Wuyin&rft.date=2025-03-24&rft.pub=Copernicus+Publications%2C+EGU&rft.issn=1991-9603&rft.volume=18&rft.issue=6&rft_id=info:doi/10.5194%2Fgmd-2024-79&rft.externalDocID=2514350 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1991-9603&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1991-9603&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1991-9603&client=summon |