A novel filtering method for geodetically determined ocean surface currents using deep learning
Determining an accurate picture of ocean currents is an important societal challenge for oceanographers, aiding our understanding of the vital role currents play in regulating Earth’s climate, and in the dispersal of marine species and pollutants, including microplastics. The geodetic approach, whic...
Uloženo v:
| Vydáno v: | Environmental Data Science Ročník 2 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Cambridge University Press
01.01.2023
|
| Témata: | |
| ISSN: | 2634-4602, 2634-4602 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Determining an accurate picture of ocean currents is an important societal challenge for oceanographers, aiding our understanding of the vital role currents play in regulating Earth’s climate, and in the dispersal of marine species and pollutants, including microplastics. The geodetic approach, which combines satellite observations of sea level and Earth’s gravity, offers the only means to estimate the dominant geostrophic component of these currents globally. Unfortunately, however, geodetically-determined geostrophic currents suffer from high levels of contamination in the form of geodetic noise. Conventional approaches use isotropic spatial filters to improve the signal-to-noise ratio, though this results in high levels of attenuation. Hence, the use of deep learning to improve the geodetic determination of the ocean currents is investigated. Supervised machine learning typically requires clean targets from which to learn. However, such targets do not exist in this case. Therefore, a training dataset is generated by substituting clean targets with naturally smooth climate model data and generative machine learning networks are employed to replicate geodetic noise, providing noisy input and clean target pairs. Prior knowledge of the geodetic noise is exploited to develop a more realistic training dataset. A convolutional denoising autoencoder (CDAE) is then trained on these pairs. The trained CDAE model is then applied to unseen real geodetic ocean currents. It is demonstrated that our method outperforms conventional isotropic filtering in a case study of four key regions: the Gulf Stream, the Kuroshio Current, the Agulhas Current, and the Brazil-Malvinas Confluence Zone. |
|---|---|
| AbstractList | Determining an accurate picture of ocean currents is an important societal challenge for oceanographers, aiding our understanding of the vital role currents play in regulating Earth’s climate, and in the dispersal of marine species and pollutants, including microplastics. The geodetic approach, which combines satellite observations of sea level and Earth’s gravity, offers the only means to estimate the dominant geostrophic component of these currents globally. Unfortunately, however, geodetically-determined geostrophic currents suffer from high levels of contamination in the form of geodetic noise. Conventional approaches use isotropic spatial filters to improve the signal-to-noise ratio, though this results in high levels of attenuation. Hence, the use of deep learning to improve the geodetic determination of the ocean currents is investigated. Supervised machine learning typically requires clean targets from which to learn. However, such targets do not exist in this case. Therefore, a training dataset is generated by substituting clean targets with naturally smooth climate model data and generative machine learning networks are employed to replicate geodetic noise, providing noisy input and clean target pairs. Prior knowledge of the geodetic noise is exploited to develop a more realistic training dataset. A convolutional denoising autoencoder (CDAE) is then trained on these pairs. The trained CDAE model is then applied to unseen real geodetic ocean currents. It is demonstrated that our method outperforms conventional isotropic filtering in a case study of four key regions: the Gulf Stream, the Kuroshio Current, the Agulhas Current, and the Brazil-Malvinas Confluence Zone. Determining an accurate picture of ocean currents is an important societal challenge for oceanographers, aiding our understanding of the vital role currents play in regulating Earth's climate, and in the dispersal of marine species and pollutants, including microplastics. The geodetic approach, which combines satellite observations of sea level and Earth's gravity, offers the only means to estimate the dominant geostrophic component of these currents globally. Unfortunately, however, geodetically-determined geostrophic currents suffer from high levels of contamination in the form of geodetic noise. Conventional approaches use isotropic spatial filters to improve the signal to noise ratio, though this results in high levels of attenuation. Hence, the use of deep learning to improve the geodetic determination of the ocean currents is investigated. Supervised machine learning typically requires clean targets from which to learn. However, such targets do not exist in this case. Therefore, a training dataset is generated by substituting clean targets with naturally smooth climate model data and generative machine learning networks are employed to replicate geodetic noise, providing noisy input and clean target pairs. Prior knowledge of the geodetic noise is exploited to develop a more realistic training dataset. A convolutional denoising autoencoder (CDAE) is then trained on these pairs. The trained CDAE model is then applied to unseen real geodetic ocean currents. It is demonstrated that our method outperforms conventional isotropic filtering in a case study of four key regions: the Gulf Stream, the Kuroshio Current, the Agulhas Current and the Brazil-Malvinas Confluence Zone. Impact Statement Although ocean currents play a crucial role in regulating Earth's climate and in the dispersal of marine species and pollutants, such as microplastics, they are difficult to measure accurately. Satellite observations offer the only means by which ocean currents can be estimated across the entire global ocean. However, these estimates are severely contaminated by noise. Removal of this noise by conventional filtering methods leads to blurred currents. Therefore, this work presents a novel deep learning method that successfully removes noise, while greatly reducing the current attenuation, allowing more accurate estimates of current speed and position to be determined. The method may have more general applicability to other geophysical observations where filtering is required to remove noise. |
| ArticleNumber | e44 |
| Author | Gibbs, Laura Bingham, Rory J. Paiement, Adeline |
| Author_xml | – sequence: 1 givenname: Laura orcidid: 0000-0002-2649-8826 surname: Gibbs fullname: Gibbs, Laura – sequence: 2 givenname: Rory J. surname: Bingham fullname: Bingham, Rory J. – sequence: 3 givenname: Adeline surname: Paiement fullname: Paiement, Adeline |
| BackLink | https://hal.science/hal-04285643$$DView record in HAL |
| BookMark | eNptkU9rGzEQxUVJIG6SU76AriHY1b9daY_GtEnA0Et7FrPSrKMgS0FaG_ztu1uH0JaeZubx3g-G95lcpJyQkDvOVpxx_QV9XQkm5ErxT2QhWqmWqmXi4o_9itzW-soYk4ILrZoFsWua8hEjHUIcsYS0o3scX7KnQy50h9njGBzEeKLThmUfEnqaHUKi9VAGcEjdoRRMY6WHOuc94huNCCVN1w25HCBWvH2f1-Tnt68_Nk_L7ffH5816u3RSs3HpBiZR9Y3svQHtgHsUrhtM0_ccWimE0RyF73ohm8Fp4Zwyqpemg45r7ZS8Js9nrs_wat9K2EM52QzB_hZy2Vko0ycRrWtBtm0nVMeFYqB64zQ0aHqjWi49m1j3Z9YLxL9QT-utnTWmhGlaJY988j6cva7kWgsOHwHO7FyLnWqxcy1WzW7-j9uFEcaQ01ggxP9mfgE3iZJJ |
| CitedBy_id | crossref_primary_10_1080_08839514_2024_2323827 |
| Cites_doi | 10.1007/BF01386390 10.1029/2019MS001829 10.1175/JPO-D-11-0159.1 10.1029/2019MS002015 10.1002/2014GL061904 10.1007/s00190-011-0485-8 10.1038/ngeo689 10.5194/os-17-789-2021 10.1007/s00024-015-1050-9 10.1002/grl.50716 10.1126/science.1109496 10.3390/rs13193935 10.1016/j.aquaculture.2003.09.030 10.5880/icgem.2016.002 10.1029/2000JC900096 10.1137/1.9781611975673.71 10.1038/s41586-020-2573-5 10.5670/oceanog.2013.07 10.22033/ESGF/CMIP6.3817 10.1016/j.patcog.2016.06.008 10.1109/TIP.2017.2662206 10.5194/os-18-1477-2022 10.1007/s00382-014-2308-0 10.1029/2004GL019920 10.1016/j.neunet.2014.09.003 10.1029/2021GL097214 10.1029/2019MS001683 10.1109/IGARSS47720.2021.9554896 10.1145/383259.383296 10.1021/es202816c 10.1023/A:1026104216284 10.1007/s11200-015-1114-4 10.22033/ESGF/CMIP6.1902 10.1109/TIP.2003.819861 10.1038/ngeo1523 10.1080/01431161003743165 10.1016/j.oceaneng.2018.09.016 10.5194/essd-11-647-2019 10.1175/2008JTECHO568.1 10.1029/2005JC003128 10.5880/icgem.2015.1 10.1029/2006GL026267 10.3390/rs15112910 10.5194/gmd-12-3241-2019 10.1029/97PA03707 10.1175/JCLI-D-12-00296.1 |
| ContentType | Journal Article |
| Copyright | Attribution |
| Copyright_xml | – notice: Attribution |
| DBID | AAYXX CITATION 1XC VOOES DOA |
| DOI | 10.1017/eds.2023.41 |
| DatabaseName | CrossRef Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2634-4602 |
| ExternalDocumentID | oai_doaj_org_article_c6a36692491240a4b8c7a5e8b84613d0 oai:HAL:hal-04285643v1 10_1017_eds_2023_41 |
| GroupedDBID | 09C 09E 0R~ AANRG AASVR AAYXX ABGDZ ABVZP ABXHF ACAJB ACDLN ACFCP ACZWT ADDNB ADKIL ADVJH AEBAK AFRIC AFZFC AGABE AGBYD AGJUD AHIPN AHRGI AKMAY ALMA_UNASSIGNED_HOLDINGS AQJOH ARCSS BLZWO CCQAD CITATION CJCSC GROUPED_DOAJ IKXGN IPYYG M~E OK1 RCA ROL WFFJZ 1XC VOOES |
| ID | FETCH-LOGICAL-c370t-cf03e4b53bd8a7ca1de2c9f85bb1a6322871e2d9b235fc72cc484b389a9177c43 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001223645700044&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2634-4602 |
| IngestDate | Tue Oct 14 19:02:07 EDT 2025 Tue Oct 14 20:19:08 EDT 2025 Tue Nov 18 21:05:36 EST 2025 Sat Nov 29 06:17:00 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | geostrophic currents deep learning mean dynamic topography filtering generative networks |
| Language | English |
| License | http://creativecommons.org/licenses/by/4.0 Attribution: http://creativecommons.org/licenses/by |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c370t-cf03e4b53bd8a7ca1de2c9f85bb1a6322871e2d9b235fc72cc484b389a9177c43 |
| ORCID | 0000-0002-2649-8826 0000-0003-0609-5672 0000-0001-5114-1514 |
| OpenAccessLink | https://doaj.org/article/c6a36692491240a4b8c7a5e8b84613d0 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_c6a36692491240a4b8c7a5e8b84613d0 hal_primary_oai_HAL_hal_04285643v1 crossref_primary_10_1017_eds_2023_41 crossref_citationtrail_10_1017_eds_2023_41 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-01-01 |
| PublicationDateYYYYMMDD | 2023-01-01 |
| PublicationDate_xml | – month: 01 year: 2023 text: 2023-01-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Environmental Data Science |
| PublicationYear | 2023 |
| Publisher | Cambridge University Press |
| Publisher_xml | – name: Cambridge University Press |
| References | Gretton (S2634460223000419_r23) 2012; 13 S2634460223000419_r61 Hershey (S2634460223000419_r26) 2007 S2634460223000419_r63 S2634460223000419_r65 S2634460223000419_r64 Zhang (S2634460223000419_r67) 2017b Kingma (S2634460223000419_r30) 2014 S2634460223000419_r66 S2634460223000419_r25 S2634460223000419_r69 S2634460223000419_r68 S2634460223000419_r24 S2634460223000419_r16 S2634460223000419_r15 S2634460223000419_r59 S2634460223000419_r18 S2634460223000419_r19 Ronneberger (S2634460223000419_r44) 2015 S2634460223000419_r32 S2634460223000419_r34 S2634460223000419_r33 S2634460223000419_r36 S2634460223000419_r35 El-Kaddoury (S2634460223000419_r17) 2019 Giorgetta (S2634460223000419_r20) 2012 S2634460223000419_r29 S2634460223000419_r28 Xie (S2634460223000419_r62) 2012 Goodfellow (S2634460223000419_r22) 2014 Tolstikhin (S2634460223000419_r55) 2017 Sakamoto (S2634460223000419_r45) 2012; 90 Radford (S2634460223000419_r41) 2015 S2634460223000419_r40 Goni (S2634460223000419_r21) 2015 S2634460223000419_r43 S2634460223000419_r42 S2634460223000419_r47 S2634460223000419_r46 S2634460223000419_r37 S2634460223000419_r39 Chen (S2634460223000419_r10) 2018 Merino (S2634460223000419_r38) 2009; 1 S2634460223000419_r50 Kingma (S2634460223000419_r31) 2013 S2634460223000419_r52 S2634460223000419_r51 Andersen (S2634460223000419_r1) 2018 S2634460223000419_r54 S2634460223000419_r53 S2634460223000419_r56 S2634460223000419_r12 S2634460223000419_r14 S2634460223000419_r58 S2634460223000419_r13 S2634460223000419_r49 S2634460223000419_r5 S2634460223000419_r48 S2634460223000419_r4 S2634460223000419_r7 Derakhshani (S2634460223000419_r11) 2019 S2634460223000419_r6 Higgins (S2634460223000419_r27) 2017 S2634460223000419_r9 S2634460223000419_r8 Vincent (S2634460223000419_r57) 2010; 11 Wei (S2634460223000419_r60) 2018; 47 S2634460223000419_r3 S2634460223000419_r2 |
| References_xml | – volume-title: 25 Years of Progress in Radar Altimetry Symposium year: 2018 ident: S2634460223000419_r1 – volume: 11 start-page: 3371 year: 2010 ident: S2634460223000419_r57 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: Journal of Machine Learning Research – ident: S2634460223000419_r12 doi: 10.1007/BF01386390 – ident: S2634460223000419_r25 doi: 10.1029/2019MS001829 – volume: 13 start-page: 723 year: 2012 ident: S2634460223000419_r23 article-title: A kernel two-sample test publication-title: Journal of Machine Learning Research – volume-title: The Atmospheric General Circulation Model ECHAM6: Model Description year: 2012 ident: S2634460223000419_r20 – volume: 47 start-page: 425 year: 2018 ident: S2634460223000419_r60 article-title: The determination of an ultra-high gravity field model SGG-UGM-1 by combining EGM2008 gravity anomaly and GOCE observation data publication-title: Acta Geodaetica et Cartographica Sinica – start-page: 3155 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2018 ident: S2634460223000419_r10 – ident: S2634460223000419_r40 doi: 10.1175/JPO-D-11-0159.1 – ident: S2634460223000419_r15 doi: 10.1029/2019MS002015 – ident: S2634460223000419_r4 doi: 10.1002/2014GL061904 – ident: S2634460223000419_r32 doi: 10.1007/s00190-011-0485-8 – volume-title: Proceedings of the 6th International Conference on Learning Representations year: 2017 ident: S2634460223000419_r55 – start-page: 1 volume-title: International Conference on Mobile, Secure, and Programmable Networking year: 2019 ident: S2634460223000419_r17 – ident: S2634460223000419_r33 doi: 10.1038/ngeo689 – volume-title: IEEE International Conference on Acoustics, Speech and Signal Processing year: 2007 ident: S2634460223000419_r26 – ident: S2634460223000419_r39 doi: 10.5194/os-17-789-2021 – ident: S2634460223000419_r64 – ident: S2634460223000419_r47 doi: 10.1007/s00024-015-1050-9 – ident: S2634460223000419_r7 doi: 10.1002/grl.50716 – volume-title: Proceedings of the 3rd International Conference on Learning Representations year: 2014 ident: S2634460223000419_r30 – ident: S2634460223000419_r52 doi: 10.1126/science.1109496 – ident: S2634460223000419_r37 doi: 10.3390/rs13193935 – ident: S2634460223000419_r68 – ident: S2634460223000419_r13 doi: 10.1016/j.aquaculture.2003.09.030 – ident: S2634460223000419_r43 doi: 10.5880/icgem.2016.002 – ident: S2634460223000419_r69 doi: 10.1029/2000JC900096 – ident: S2634460223000419_r9 doi: 10.1137/1.9781611975673.71 – ident: S2634460223000419_r6 doi: 10.1038/s41586-020-2573-5 – volume-title: Proceedings of the 4th International Conference on Learning Representations year: 2015 ident: S2634460223000419_r41 – ident: S2634460223000419_r53 doi: 10.5670/oceanog.2013.07 – ident: S2634460223000419_r50 doi: 10.22033/ESGF/CMIP6.3817 – ident: S2634460223000419_r35 doi: 10.1016/j.patcog.2016.06.008 – ident: S2634460223000419_r66 doi: 10.1109/TIP.2017.2662206 – volume-title: Proceedings of the 2nd International Conference on Learning Representations year: 2013 ident: S2634460223000419_r31 – volume: 90 start-page: 325 year: 2012 ident: S2634460223000419_r45 article-title: MIROC4h—A new high-resolution atmosphere-ocean coupled general circulation model publication-title: Journal of the Meteorological Society of Japan – ident: S2634460223000419_r63 doi: 10.5194/os-18-1477-2022 – ident: S2634460223000419_r36 doi: 10.1007/s00382-014-2308-0 – ident: S2634460223000419_r54 doi: 10.1029/2004GL019920 – ident: S2634460223000419_r49 doi: 10.1016/j.neunet.2014.09.003 – ident: S2634460223000419_r56 doi: 10.1029/2021GL097214 – start-page: 9201 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2019 ident: S2634460223000419_r11 – ident: S2634460223000419_r58 doi: 10.1029/2019MS001683 – ident: S2634460223000419_r34 doi: 10.1109/IGARSS47720.2021.9554896 – start-page: 234 volume-title: International Conference on Medical Image Computing and Computer-Assisted Intervention year: 2015 ident: S2634460223000419_r44 – ident: S2634460223000419_r16 doi: 10.1145/383259.383296 – ident: S2634460223000419_r8 doi: 10.1021/es202816c – ident: S2634460223000419_r14 doi: 10.1023/A:1026104216284 – start-page: 2672 volume-title: Advances in Neural Information Processing Systems year: 2014 ident: S2634460223000419_r22 – start-page: 3929 volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition year: 2017b ident: S2634460223000419_r67 – ident: S2634460223000419_r19 doi: 10.1007/s11200-015-1114-4 – ident: S2634460223000419_r42 doi: 10.22033/ESGF/CMIP6.1902 – start-page: 350 volume-title: Advances in Neural Information Processing Systems year: 2012 ident: S2634460223000419_r62 – ident: S2634460223000419_r59 doi: 10.1109/TIP.2003.819861 – ident: S2634460223000419_r46 doi: 10.1038/ngeo1523 – volume: 1 start-page: 47 year: 2009 ident: S2634460223000419_r38 article-title: Ocean currents and their impact on marine life publication-title: Marine Ecology – ident: S2634460223000419_r2 doi: 10.1080/01431161003743165 – ident: S2634460223000419_r51 doi: 10.1016/j.oceaneng.2018.09.016 – start-page: 1 volume-title: Mathematical Modelling and Numerical Simulation of Oil Pollution Problems 2 year: 2015 ident: S2634460223000419_r21 – ident: S2634460223000419_r28 doi: 10.5194/essd-11-647-2019 – ident: S2634460223000419_r3 doi: 10.1175/2008JTECHO568.1 – ident: S2634460223000419_r29 doi: 10.1029/2005JC003128 – volume-title: Proceedings of the 5th International Conference on Learning Representations year: 2017 ident: S2634460223000419_r27 – ident: S2634460223000419_r18 doi: 10.5880/icgem.2015.1 – ident: S2634460223000419_r65 doi: 10.1029/2006GL026267 – ident: S2634460223000419_r48 doi: 10.3390/rs15112910 – ident: S2634460223000419_r24 doi: 10.5194/gmd-12-3241-2019 – ident: S2634460223000419_r5 doi: 10.1029/97PA03707 – ident: S2634460223000419_r61 doi: 10.1175/JCLI-D-12-00296.1 |
| SSID | ssj0003212745 |
| Score | 2.2128408 |
| Snippet | Determining an accurate picture of ocean currents is an important societal challenge for oceanographers, aiding our understanding of the vital role currents... |
| SourceID | doaj hal crossref |
| SourceType | Open Website Open Access Repository Enrichment Source Index Database |
| SubjectTerms | Computer Science Deep learning filtering generative networks geostrophic currents mean dynamic topography Signal and Image Processing |
| Title | A novel filtering method for geodetically determined ocean surface currents using deep learning |
| URI | https://hal.science/hal-04285643 https://doaj.org/article/c6a36692491240a4b8c7a5e8b84613d0 |
| Volume | 2 |
| WOSCitedRecordID | wos001223645700044&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: PRVAEN databaseName: Cambridge Journals: All Gold Open Access Journals customDbUrl: eissn: 2634-4602 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0003212745 issn: 2634-4602 databaseCode: IKXGN dateStart: 20220101 isFulltext: true titleUrlDefault: http://journals.cambridge.org/action/login providerName: Cambridge University Press – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2634-4602 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0003212745 issn: 2634-4602 databaseCode: DOA dateStart: 20220101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2634-4602 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0003212745 issn: 2634-4602 databaseCode: M~E dateStart: 20210101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NSwMxEA1SPXgRRcX6RRBPwupmk2x2j1XUilI8KPQW8lmFsi1tLfjvnWy2pQXBi9cwZMOb3byZ7OQNQpeFUcQRRhJPNE9YmemktNQlGdWp1VYRo2tPv4her-j3y9eVVl-hJizKA0fgbkyuaJ6HLAGYKFVMF0Yo7goNxEmorbP1VJQryVTYg2kQLme8uZAXNKKdDeLcGb1mZI2CaqV-IJaPxUFqTSwPu2iniQhxJ65kD224ah_JDq5GczfE_jP8zgZ-wbHXM4YgEw_cyMbLh8NvbJuCFmcxcJGq8PRr4pVx2ETppSkOte0DsHNj3DSJGByg94f7t7tu0vRCSAwV6SwxPqWOaU61LZQAgK3LTOkLrjVROXyVkPi4zJY6o9wbkRnDCqYhGlGQjwnD6CFqVaPKHSEMSOZKcONhk2Q2YwXMHWT0c04894630dUCHmkaofDQr2IoY0WYkIClDFhKRtrocmk8jvoYv5vdBpyXJkHUuh4AV8vG1fIvV7fRBXhpbY5u50WGsZD5cQiu5uT4P550grbDwuNRyylqzSZf7gxtmfnsczo5r1-1c7T59Nx_7P0A9FfZ5w |
| 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+novel+filtering+method+for+geodetically-determined+ocean+surface+currents+using+deep+learning&rft.jtitle=Environmental+Data+Science&rft.au=Gibbs%2C+Laura&rft.au=Bingham%2C+Rory+J&rft.au=Paiement%2C+Adeline&rft.date=2023-01-01&rft.pub=Cambridge+University+Press&rft.eissn=2634-4602&rft_id=info:doi/10.1017%2Feds.2023.41&rft.externalDBID=HAS_PDF_LINK&rft.externalDocID=oai%3AHAL%3Ahal-04285643v1 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2634-4602&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2634-4602&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2634-4602&client=summon |