Deep Learning-Based Temperature and Salinity Reconstruction and derived Geostrophic Currents in the Pan-Arctic Ocean with 3-Day resolution on EASE-Grid 2.0 at 25km (Version 1)

Werner-Pelletier, Nicolas; Crespin, Julia; Rosquete-Estevez, Aleida; Sánchez-Urrea, María; Hoareau, Nina; Martin, Mario; Umbert, Marta

Deep Learning-Based Reconstruction of Temperature and Salinity in the Arctic Ocean and derived Geostrophic Currents (Version 1)

doi:10.26050/WDCC/DLRec-AO_v1

Werner-Pelletier, Nicolas et al.

ExperimentDOI

FRESH-CARE machine learning OCEAN CURRENTS Salinity Temperature

Summary: This dataset collection provides observation-constrained reconstructions of Arctic Ocean hydrography and diagnostic geostrophic circulation for the period 2011–2021. The datasets were generated using a Long Short-Term Memory neural network trained with in situ hydrographic profiles and satellite-derived surface information, including sea surface temperature, sea surface salinity, and absolute dynamic topography. The framework estimates temperature and salinity anomalies relative to GLORYS12V1 reanalysis, which are then used to obtain reconstructed three-dimensional temperature and salinity fields on 102 WOA standard depth levels at 3-day temporal resolution. The collection includes one pan-Arctic product on a 25 km EASE2 grid and four regional 6.25 km products covering the main Arctic gateways: Bering Strait, Davis Strait, Fram Strait, and the Barents Sea Opening. The datasets also include model-based uncertainty estimates, surface input fields and absolute dynamic height, supporting studies of Arctic freshwater variability, circulation change, and climate model evaluation.
Project: FRESH-CARE (Unraveling FRESHwater and ocean Currents changes in the Arctic using REmote sensing)
Contact: Nicolas Werner-Pelletier (
nicolaswerner@nullicm.csic.es
0009-0003-4679-6948)
Location(s): Fram Strait
Arctic Ocean
Arctic region
Bering Strait
Davis Strait
Barents Sea
Spatial Coverage: Longitude -180 to 180 Latitude 60 to 90
Temporal Coverage: 2011-01-04 to 2021-12-28 (standard)
Use constraints: Creative Commons Attribution 4.0 International (https://creativecommons.org/licenses/by/4.0/)
Data Catalog: World Data Center for Climate
Size: 101.74 GiB (109246037209 Byte)
Format: NetCDF
Status: completely archived
Creation Date: 2026-07-01
Review Date: 2026-07-07

Find data Export dataset acronyms

Cite as: Werner-Pelletier, Nicolas; Crespin, Julia; Rosquete-Estevez, Aleida; Sánchez-Urrea, María; Hoareau, Nina; Martin, Mario; Umbert, Marta (2026). Deep Learning-Based Temperature and Salinity Reconstruction and derived Geostrophic Currents in the Pan-Arctic Ocean with 3-Day resolution on EASE-Grid 2.0 at 25km (Version 1). World Data Center for Climate (WDCC) at DKRZ. https://doi.org/10.26050/WDCC/DLRec-AO_v1

BibTeX RIS

Funding: European Research Council
Grant/Award No: 101164517 - ERC Horizon Europe FRESH-CARE
Gobierno de España / Agencia Estatal de Investigación
Grant/Award No: CEX2024-001494-S - Acreditación de Centro de Excelencia Severo Ochoa
Ministerio de Ciencia e Innovación
Grant/Award No: PRE2021-099346 - Contrato predoctoral para la formación de doctores

FAIR

F-UJI result: total 76.92 %

Description: Summary:
Findable: 6 of 7 level;
Accessible: 3 of 7 level;
Interoperable: 6 of 6 level;
Reusable: 5 of 6 level
Method: F-UJI WDCC service v3.5.0 metrics_v0.8
Method Description: Checks performed by WDCC. Metrics documentation: https://doi.org/10.5281/zenodo.15045911 Metric Version: metrics_v0.8
Method Url: https://www.f-uji.net
Result Date: 2026-07-07

Scientific Quality Assurance (SQA)

SQA - Scientific Quality Assurance 'approved by author'

Result Date: 2026-07-07

Technical Quality Assurance (TQA)

TQA - Technical Quality Assurance 'approved by WDCC'

Description: 1. Number of data sets is correct and > 0: passed;
2. Size of every data set is > 0: passed;
3. The data sets and corresponding metadata are accessible: passed;
4. The data sizes are controlled and correct: passed;
5. The spatial-temporal coverage description (metadata) is consistent to the data: passed;
6. The format is correct: passed;
7. Variable description and data are consistent: passed
Method: WDCC-TQA checklist
Method Description: Checks performed by WDCC. The list of TQA metrics are documented in the 'WDCC User Guide for Data Publication' Chapter 8.1.1
Method Url: https://www.wdc-climate.de/docs/WDCC_User_Guide.pdf
Result Date: 2026-07-07

Contact type	Person	ORCID	Organization
Contact	Nicolas Werner-Pelletier	0009-0003-4679-6948	Institut de Ciències del Mar (ICM-CSIC)
Author	Nicolas Werner-Pelletier	0009-0003-4679-6948	Institut de Ciències del Mar (ICM-CSIC)
Author	Dr. Julia Crespin	0000-0003-4779-6985	Institut de Ciències del Mar (ICM-CSIC)
Author	Aleida Rosquete-Estevez	0009-0001-8919-8206	Institut de Ciències del Mar (ICM-CSIC)
Author	María Sánchez-Urrea	0009-0008-8972-158X	Institut de Ciències del Mar (ICM-CSIC)
Author	Dr. Nina Hoareau	0000-0002-4796-8735	Institut de Ciències del Mar (ICM-CSIC)
Author	Dr. Mario Martin	0000-0002-4125-6630	Universitat Politècnica de Catalunya
Author	Dr. Marta Umbert	0000-0002-0748-7566	Institut de Ciències del Mar (ICM-CSIC)
Investigator	Nicolas Werner-Pelletier	0009-0003-4679-6948	Institut de Ciències del Mar (ICM-CSIC)
Funder	-	-	European Research Council
Funder	-	-	Gobierno de España / Agencia Estatal de Investigación
Funder	-	-	Ministerio de Ciencia e Innovación

Is documented by

[1] DOI Buongiorno Nardelli, Bruno. (2020). A Deep Learning Network to Retrieve Ocean Hydrographic Profiles from Combined Satellite and In Situ Measurements. doi:10.3390/rs12193151

[2] DOI Buongiorno Nardelli, Bruno; Cavaliere, Davide; Charles, Elodie; Ciani, Daniele. (2022). Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms. doi:10.3390/rs14051159

[3] DOI Smith, Philip A. H.; Sørensen, Kristian Aa.; Buongiorno Nardelli, Bruno; Chauhan, Anshul; Christensen, Asbjørn; St. John, Michael; Rodrigues, Filipe; Mariani, Patrizio. (2023). Reconstruction of subsurface ocean state variables using Convolutional Neural Networks with combined satellite and in situ data. doi:10.3389/fmars.2023.1218514

[4] DOI Tian, Tian; Cheng, Lijing; Wang, Gongjie; Abraham, John; Wei, Wangxu; Ren, Shihe; Zhu, Jiang; Song, Junqiang; Leng, Hongze. (2022). Reconstructing ocean subsurface salinity at high resolution using a machine learning approach. doi:10.5194/essd-14-5037-2022

[5] DOI Hochreiter, Sepp; Schmidhuber, Jürgen. (1997). Long Short-Term Memory. doi:10.1162/neco.1997.9.8.1735

[6] Sutskever, Ilya; Vinyals, Oriol; Le, Quoc V. (2014). Sequence to Sequence Learning with Neural Networks. https://doi.org/10.48550/arXiv.1409.3215

[7] DOI Chen, Ge; Huang, Baoxiang; Chen, Xiaoyan; Ge, Linyao; Radenkovic, Milena; Ma, Ying. (2022). Deep blue AI: A new bridge from data to knowledge for the ocean science. doi:10.1016/j.dsr.2022.103886

Is compiled by

[1] Pelletier, Nicolas Werner. (2026). Barcelona-Polar-Lab/fresh_care_wp2_ocean_lstm: v1.0.0 — Initial release (v1.0.0). https://doi.org/10.5281/zenodo.20744925

Is derived from

[1] DOI Li, Jinlong; Wu, Xiangyu; Wang, Xidong. (2025). An Arctic Ocean Thermohaline Dataset. doi:10.1038/s41597-025-05855-3

[2] Copernicus Marine Service. (2026). ESA SST CCI and C3S reprocessed sea surface temperature analyses. https://doi.org/10.48670/moi-00169

[3] DOI Boutin, J.; Reul, N.; Koehler, J.; Martin, A.; Catany, R.; Guimbard, S.; Rouffi, F.; Vergely, J. L.; Arias, M.; Chakroun, M.; Corato, G.; Estella‐Perez, V.; Hasson, A.; Josey, S.; Khvorostyanov, D.; Kolodziejczyk, N.; Mignot, J.; Olivier, L.; Reverdin, G.; Stammer, D.; Supply, A.; Thouvenin‐Masson, C.; Turiel, A.; Vialard, J.; Cipollini, P.; Donlon, C.; Sabia, R.; Mecklenburg, S. (2021). Satellite‐Based Sea Surface Salinity Designed for Ocean and Climate Studies. doi:10.1029/2021jc017676

[4] Copernicus Marine Service. (2023). Global Ocean Physics Reanalysis. https://doi.org/10.48670/moi-00021

[5] DOI Jean-Michel, Lellouche; Eric, Greiner; Romain, Bourdallé-Badie; Gilles, Garric; Angélique, Melet; Marie, Drévillon; Clément, Bricaud; Mathieu, Hamon; Olivier, Le Galloudec; Charly, Regnier; Tony, Candela; Charles-Emmanuel, Testut; Florent, Gasparin; Giovanni, Ruggiero; Mounir, Benkiran; Yann, Drillet; Pierre-Yves, Le Traon. (2021). The Copernicus Global 1/12° Oceanic and Sea Ice GLORYS12 Reanalysis. doi:10.3389/feart.2021.698876

[6] DOI CNES; CLS. (2026). Experimental Polar Ocean Along-track Level-3 Sea Surface Heights (Version 2.0). doi:10.24400/527896/AVISO-2026.004

[7] DOI Prandi, Pierre; Poisson, Jean-Christophe; Faugère, Yannice; Guillot, Amandine; Dibarboure, Gérald. (2021). Arctic sea surface height maps from multi-altimeter combination. doi:10.5194/essd-13-5469-2021

[8] DOI Veillard, Pierre; Prandi, Pierre; Pujol, Marie-Isabelle; Daguzé, Jean-Alexis; Piras, Fanny; Dibarboure, Gérald; Faugère, Yannice. (2024). Arctic and Southern Ocean polar sea level maps and along-tracks from multi-mission satellite altimetry from 2011 to 2021. doi:10.3389/fmars.2024.1419132

[9] DOI EUMETSAT OSI SAF. (2017). Global Sea Ice Concentration (netCDF) - DMSP. EUMETSAT. doi:10.15770/EUM_SAF_OSI_NRT_2004

[10] DOI GEBCO Bathymetric Compilation Group 2025. (2025). The GEBCO_2025 Grid - a continuous terrain model for oceans and land at 15 arc-second intervals. doi:10.5285/37c52e96-24ea-67ce-e063-7086abc05f29

[11] Reagan, J.R.; Garcia, H.E.; Boyer, T.P.; Baranova, O.K.; Bouchard, C.;Cross, S.L.; Dukhovskoy, D.; Grodsky, A.; Locarnini, R.A.; Mishonov, A.V.; Paver, C.R.; Seidov, D.; Wang, Z.; National Centers for Environmental Information (U.S.). Ocean Climate Laboratory. (2023). World Ocean Atlas 2023: Product Documentation. https://doi.org/10.25923/a78k-gq49

[12] DOI Brodzik, Mary J.; Billingsley, Brendan; Haran, Terry; Raup, Bruce; Savoie, Matthew H. (2012). EASE-Grid 2.0: Incremental but Significant Improvements for Earth-Gridded Data Sets. doi:10.3390/ijgi1010032

Attached Datasets ( 5 )

Details for selected entry

Parent project(s)

Unraveling FRESHwater and ocean Currents changes in the Arctic using REmote sensing

[Entry acronym: DLRec-AO_v1] [Entry id: 5370436]