Articles | Volume 18, issue 4
https://doi.org/10.5194/os-18-1221-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/os-18-1221-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
25 Aug 2022
Research article |
| 25 Aug 2022
| 25 Aug 2022
Four-dimensional temperature, salinity and mixed-layer depth in the Gulf Stream, reconstructed from remote-sensing and in situ observations with neural networks
Etienne Pauthenet
CORRESPONDING AUTHOR
Ifremer, Univ. Brest, CNRS, IRD, Laboratoire d'Océanographie Physique et Spatiale (LOPS), IUEM, 29280, Plouzané, France
Loïc Bachelot
Ifremer, Univ. Brest, CNRS, IRD, Service Ingénierie des Systèmes d'Information (PDG-IRSI-ISI), IUEM, 29280, Plouzané, France
Kevin Balem
Ifremer, Univ. Brest, CNRS, IRD, Laboratoire d'Océanographie Physique et Spatiale (LOPS), IUEM, 29280, Plouzané, France
Guillaume Maze
Ifremer, Univ. Brest, CNRS, IRD, Laboratoire d'Océanographie Physique et Spatiale (LOPS), IUEM, 29280, Plouzané, France
Anne-Marie Tréguier
Ifremer, Univ. Brest, CNRS, IRD, Laboratoire d'Océanographie Physique et Spatiale (LOPS), IUEM, 29280, Plouzané, France
Fabien Roquet
Department of Marine Sciences, University of Gothenburg, Gothenburg, Sweden
Ronan Fablet
IMT Atlantique, CNRS UMR Lab-STICC, Brest, France
Pierre Tandeo
IMT Atlantique, CNRS UMR Lab-STICC, Brest, France
Related authors
Jean-Baptiste Sallée, Lucie Vignes, Audrey Minière, Nadine Steiger, Etienne Pauthenet, Antonio Lourenco, Kevin Speer, Peter Lazarevich, and Keith Nicholls
EGUsphere, https://doi.org/10.5194/egusphere-2023-2952, https://doi.org/10.5194/egusphere-2023-2952, 2023
Short summary
Short summary
In the Weddell Sea, one of the regional seas fringing Antarctica, we investigated how warm deep currents and cold waters containing freshwater released from the Antarctic are connected. We used autonomous observation devices never been used in this region previously that allow us to track the movement and characteristics of water-masses under the sea ice. Our findings show a dynamic interaction between warm-masses, providing key insights to understand climate-related changes in the region.
Sofia Allende, Anne Marie Treguier, Camille Lique, Clément de Boyer Montégut, François Massonnet, Thierry Fichefet, and Antoine Barthélemy
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2024-49, https://doi.org/10.5194/gmd-2024-49, 2024
Preprint under review for GMD
Short summary
Short summary
We study the parameters involved in the turbulent kinetic energy mixed layer penetration scheme of the NEMO model in Arctic sea ice-covered regions. This evaluation reveals the impact of these parameters on mixed layer depth, sea surface temperature and salinity, and ocean stratification. Our findings also demonstrate considerable impacts on sea ice thickness and sea ice concentration, emphasizing the importance of accurate ocean mixing representation in understanding Arctic climate dynamics.
Paul Platzer, Pierre Tandeo, Pierre Ailliot, and Bertrand Chapron
EGUsphere, https://doi.org/10.5194/egusphere-2023-2997, https://doi.org/10.5194/egusphere-2023-2997, 2024
Short summary
Short summary
Old observations are necessary to understand the atmosphere. When direct observations are not available, one can use indirect observations such as tide gauges, which measure the sea-level in portal cities. The sea level rises when local air pressure decreases, and when wind pushes water towards the coast. Several centuries-long tide gauge records are available. We show that these can be complementary to direct pressure observations for studying storms and anticyclones in the 19th century.
Jean-Baptiste Sallée, Lucie Vignes, Audrey Minière, Nadine Steiger, Etienne Pauthenet, Antonio Lourenco, Kevin Speer, Peter Lazarevich, and Keith Nicholls
EGUsphere, https://doi.org/10.5194/egusphere-2023-2952, https://doi.org/10.5194/egusphere-2023-2952, 2023
Short summary
Short summary
In the Weddell Sea, one of the regional seas fringing Antarctica, we investigated how warm deep currents and cold waters containing freshwater released from the Antarctic are connected. We used autonomous observation devices never been used in this region previously that allow us to track the movement and characteristics of water-masses under the sea ice. Our findings show a dynamic interaction between warm-masses, providing key insights to understand climate-related changes in the region.
Trevor J. McDougall, Paul M. Barker, Rainer Feistel, and Fabien Roquet
Ocean Sci., 19, 1719–1741, https://doi.org/10.5194/os-19-1719-2023, https://doi.org/10.5194/os-19-1719-2023, 2023
Short summary
Short summary
A thermodynamic potential is derived, with the temperature argument being Conservative Temperature. All thermodynamic quantities can be derived from this new thermodynamic potential function, and it enables the accurate (to computer machine precision) calculation of the in situ temperature and entropy of seawater. This new thermodynamic potential function adds fundamental thermodynamic justification to the adoption of Conservative Temperature in oceanography in 2010.
Théo Picard, Jonathan Gula, Ronan Fablet, Jeremy Collin, and Laurent Mémery
EGUsphere, https://doi.org/10.5194/egusphere-2023-2777, https://doi.org/10.5194/egusphere-2023-2777, 2023
Short summary
Short summary
The biological carbon pump plays a major role in climate. Plankton uptake and transform CO2 into organic carbon, creating particles that sink down to the ocean floor. Sediment traps catch these particles and measure the carbon stored in the abyss. But the surface origin of particles is unknown because ocean currents alter their path. In this study, we train an AI to predict the origin of these particles. This new tool allows a better link between deep ocean observations and satellite images.
Pierre Le Bras, Florian Sévellec, Pierre Tandeo, Juan Ruiz, and Pierre Ailliot
EGUsphere, https://doi.org/10.5194/egusphere-2023-2649, https://doi.org/10.5194/egusphere-2023-2649, 2023
Short summary
Short summary
The goal of this paper is to weight several dynamic models in order to improve the representativeness of a system. It is illustrated using a set of versions of an idealized model describing the Atlantic Meridional Overturning Circulation. The low-cost method is based on data-driven forecasts. It enables model performance to be evaluated on their dynamics. Taking into account both model performance and codependency, the derived weights outperform benchmarks in reconstructing a model distribution.
Romain Caneill, Fabien Roquet, and Jonas Nycander
EGUsphere, https://doi.org/10.5194/egusphere-2023-2404, https://doi.org/10.5194/egusphere-2023-2404, 2023
Short summary
Short summary
In winter, heat loss increases density at the surface of the Southern Ocean. This increase of density creates a mixed layer deeper than 250m only in a narrow deep mixing band (DMB) located around 50°S. We found that north of the DMB, the stratification is too strong to be eroded, so mixed layers are shallower. The density of cold water is almost not impacted by temperature changes. Thus, heat loss does not increase significantly the density south of the DMB, so no deep mixed layers are produced.
Anne Marie Treguier, Clement de Boyer Montégut, Alexandra Bozec, Eric P. Chassignet, Baylor Fox-Kemper, Andy McC. Hogg, Doroteaciro Iovino, Andrew E. Kiss, Julien Le Sommer, Yiwen Li, Pengfei Lin, Camille Lique, Hailong Liu, Guillaume Serazin, Dmitry Sidorenko, Qiang Wang, Xiaobio Xu, and Steve Yeager
Geosci. Model Dev., 16, 3849–3872, https://doi.org/10.5194/gmd-16-3849-2023, https://doi.org/10.5194/gmd-16-3849-2023, 2023
Short summary
Short summary
The ocean mixed layer is the interface between the ocean interior and the atmosphere and plays a key role in climate variability. We evaluate the performance of the new generation of ocean models for climate studies, designed to resolve
ocean eddies, which are the largest source of ocean variability and modulate the mixed-layer properties. We find that the mixed-layer depth is better represented in eddy-rich models but, unfortunately, not uniformly across the globe and not in all models.
Pierre Tandeo, Pierre Ailliot, and Florian Sévellec
Nonlin. Processes Geophys., 30, 129–137, https://doi.org/10.5194/npg-30-129-2023, https://doi.org/10.5194/npg-30-129-2023, 2023
Short summary
Short summary
The goal of this paper is to obtain probabilistic predictions of a partially observed dynamical system without knowing the model equations. It is illustrated using the three-dimensional Lorenz system, where only two components are observed. The proposed data-driven procedure is low-cost, is easy to implement, uses linear and Gaussian assumptions and requires only a small amount of data. It is based on an iterative linear Kalman smoother with a state augmentation.
Robin Marcille, Maxime Thiébaut, Pierre Tandeo, and Jean-François Filipot
Wind Energ. Sci., 8, 771–786, https://doi.org/10.5194/wes-8-771-2023, https://doi.org/10.5194/wes-8-771-2023, 2023
Short summary
Short summary
A novel data-driven method is proposed to design an optimal sensor network for the reconstruction of offshore wind resources. Based on unsupervised learning of numerical weather prediction wind data, it provides a simple yet efficient method for the siting of sensors, outperforming state-of-the-art methods for this application. It is applied in the main French offshore wind energy development areas to provide guidelines for the deployment of floating lidars for wind resource assessment.
Maxime Beauchamp, Quentin Febvre, Hugo Georgenthum, and Ronan Fablet
Geosci. Model Dev., 16, 2119–2147, https://doi.org/10.5194/gmd-16-2119-2023, https://doi.org/10.5194/gmd-16-2119-2023, 2023
Short summary
Short summary
4DVarNet is a learning-based method based on traditional data assimilation (DA). This new class of algorithms can be used to provide efficient reconstructions of a dynamical system based on single observations. We provide a 4DVarNet application to sea surface height reconstructions based on nadir and future Surface Water and Ocean and Topography data. It outperforms other methods, from optimal interpolation to sophisticated DA algorithms. This work is part of on-going AI Chair Oceanix projects.
Juan Ruiz, Pierre Ailliot, Thi Tuyet Trang Chau, Pierre Le Bras, Valérie Monbet, Florian Sévellec, and Pierre Tandeo
Geosci. Model Dev., 15, 7203–7220, https://doi.org/10.5194/gmd-15-7203-2022, https://doi.org/10.5194/gmd-15-7203-2022, 2022
Short summary
Short summary
We present a new approach to validate numerical simulations of the current climate. The method can take advantage of existing climate simulations produced by different centers combining an analog forecasting approach with data assimilation to quantify how well a particular model reproduces a sequence of observed values. The method can be applied with different observations types and is implemented locally in space and time significantly reducing the associated computational cost.
R. Fablet, M. M. Amar, Q. Febvre, M. Beauchamp, and B. Chapron
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2021, 295–302, https://doi.org/10.5194/isprs-annals-V-3-2021-295-2021, https://doi.org/10.5194/isprs-annals-V-3-2021-295-2021, 2021
Olivier Pannekoucke and Ronan Fablet
Geosci. Model Dev., 13, 3373–3382, https://doi.org/10.5194/gmd-13-3373-2020, https://doi.org/10.5194/gmd-13-3373-2020, 2020
Short summary
Short summary
Learning physics from data using a deep neural network is a challenge that requires an appropriate but unknown network architecture. The package introduced here helps to design an architecture by translating known physical equations into a network, which the experimenter completes to capture unknown physical processes. A test bed is introduced to illustrate how this learning allows us to focus on truly unknown physical processes in the hope of making better use of data and digital resources.
Mathieu Le Corre, Jonathan Gula, and Anne-Marie Tréguier
Ocean Sci., 16, 451–468, https://doi.org/10.5194/os-16-451-2020, https://doi.org/10.5194/os-16-451-2020, 2020
Short summary
Short summary
The ocean circulation is crucial for the climate, and the North Atlantic subpolar gyre is a key component of the meridional heat transport. In this study we use a high-resolution simulation with bottom-following coordinates to investigate the gyre dynamics. We show that nonlinear processes, underestimated in most climate models, control the circulation in the gyre interior. This result contrasts with the classical theory putting forward wind effects on the large-scale circulation.
Damien G. Desbruyères, Herlé Mercier, Guillaume Maze, and Nathalie Daniault
Ocean Sci., 15, 809–817, https://doi.org/10.5194/os-15-809-2019, https://doi.org/10.5194/os-15-809-2019, 2019
Short summary
Short summary
In the North Atlantic, ocean currents transport warm waters northward in the upper water column, and cold waters southwards at depth. This circulation is here reconstructed from surface data and thermodynamics theory. Its driving role in recent temperature changes (1993–2017) in the North Atlantic is evidenced, and predictions of near-future variability (5 years) are provided and discussed.
Stephen M. Griffies, Gokhan Danabasoglu, Paul J. Durack, Alistair J. Adcroft, V. Balaji, Claus W. Böning, Eric P. Chassignet, Enrique Curchitser, Julie Deshayes, Helge Drange, Baylor Fox-Kemper, Peter J. Gleckler, Jonathan M. Gregory, Helmuth Haak, Robert W. Hallberg, Patrick Heimbach, Helene T. Hewitt, David M. Holland, Tatiana Ilyina, Johann H. Jungclaus, Yoshiki Komuro, John P. Krasting, William G. Large, Simon J. Marsland, Simona Masina, Trevor J. McDougall, A. J. George Nurser, James C. Orr, Anna Pirani, Fangli Qiao, Ronald J. Stouffer, Karl E. Taylor, Anne Marie Treguier, Hiroyuki Tsujino, Petteri Uotila, Maria Valdivieso, Qiang Wang, Michael Winton, and Stephen G. Yeager
Geosci. Model Dev., 9, 3231–3296, https://doi.org/10.5194/gmd-9-3231-2016, https://doi.org/10.5194/gmd-9-3231-2016, 2016
Short summary
Short summary
The Ocean Model Intercomparison Project (OMIP) aims to provide a framework for evaluating, understanding, and improving the ocean and sea-ice components of global climate and earth system models contributing to the Coupled Model Intercomparison Project Phase 6 (CMIP6). This document defines OMIP and details a protocol both for simulating global ocean/sea-ice models and for analysing their output.
A. M. Treguier, J. Deshayes, J. Le Sommer, C. Lique, G. Madec, T. Penduff, J.-M. Molines, B. Barnier, R. Bourdalle-Badie, and C. Talandier
Ocean Sci., 10, 243–255, https://doi.org/10.5194/os-10-243-2014, https://doi.org/10.5194/os-10-243-2014, 2014
Cited articles
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M.,
Ghemawat, S., Irving, G., and Isard, M.: Tensorflow: A system for large-scale
machine learning, in: 12th {USENIX} symposium on operating systems
design and implementation ({OSDI} 16), Savannah, GA, USA, 2–4 November 2016,
265–283, ISBN 978-1-931971-33-1, 2016. a
Argo: Argo float data and metadata from Global Data Assembly Centre (Argo
GDAC), SEANOE [data set], https://doi.org/10.17882/42182, 2022. a
Boutin, J., Reul, N., Köhler, J., Martin, A., Catany, R., Guimbard, S.,
Rouffi, F., Vergely, J.-L., Arias, M., and Chakroun, M.: Satellite‐Based
Sea Surface Salinity Designed for Ocean and Climate Studies, J.
Geophys. Res.-Oceans, 126, e2021JC017676, https://doi.org/10.1029/2021JC017676, 2021. a, b, c, d, e
Boutin, J., Vergely, J.-L., Reul, N., Catany, R., Koehler, J., Martin, A., Rouffi, F., Arias, M., Chakroun, M., Corato, G., Estella-Perez, V., Guimbard, S., 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., and Donlon, C.:
ESA Sea Surface Salinity Climate Change Initiative (Sea_Surface_Salinity_cci): weekly and monthly sea surface salinity products, v2.31, for 2010 to 2019, Centre for Environmental Data Analysis, [data set],
https://doi.org/10.5285/4ce685bff631459fb2a30faa699f3fc5, last access: 27 June 2022. a
Breiman, L.: Bagging predictors, Mach. Learn., 24, 123–140,
https://doi.org/10.1007/BF00058655, 1996. a
Buongiorno Nardelli, B.: A Deep Learning Network to Retrieve Ocean Hydrographic
Profiles from Combined Satellite and In Situ Measurements, Remote Sens.,
12, 3151, https://doi.org/10.3390/rs12193151, 2020. a, b, c, d
Buongiorno-Nardelli, B. and Santoleri, R.: Methods for the reconstruction of
vertical profiles from surface data: Multivariate analyses, residual GEM, and
variable temporal signals in the North Pacific Ocean, J. Atmos. Ocean. Tech., 22, 1762–1781, 2005. a
Cabanes, C., Grouazel, A., von Schuckmann, K., Hamon, M., Turpin, V., Coatanoan, C., Paris, F., Guinehut, S., Boone, C., Ferry, N., de Boyer Montégut, C., Carval, T., Reverdin, G., Pouliquen, S., and Le Traon, P.-Y.: The CORA dataset: validation and diagnostics of in-situ ocean temperature and salinity measurements, Ocean Sci., 9, 1–18, https://doi.org/10.5194/os-9-1-2013, 2013. a
Castelao, R. M.: Mesoscale eddies in the South Atlantic Bight and the Gulf
Stream recirculation region: vertical structure, J. Geophy.
Res.-Oceans, 119, 2048–2065, 2014. a
Charantonis, A. A., Badran, F., and Thiria, S.: Retrieving the evolution of
vertical profiles of Chlorophyll-a from satellite observations using Hidden
Markov Models and Self-Organizing Topological Maps, Remote Sens.
Environ., 163, 229–239, 2015. a
Cheng, L., Trenberth, K. E., Fasullo, J., Boyer, T., Abraham, J., and Zhu, J.:
Improved estimates of ocean heat content from 1960 to 2015, Sci. Adv.,
3, e1601545, https://doi.org/10.1126/sciadv.1601545, 2017. a
Chollet, F. and Others: Keras, https://github.com/fchollet/keras (last access: 27 June 2022), 2015. a
Cleveland, R. B., Cleveland, W. S., McRae, J. E., and Terpenning, I.: STL: A
seasonal-trend decomposition, J. Off. Stat., 6, 3–73, 1990. a
CMEMS: Global ocean gridded l4 sea surface heights and derived, [data set], https://www.copernicus.eu/en/access-data/copernicus-services-catalogue/global-ocean-gridded-l4-sea-surface-heights-and-derived, last access: 27 June 2022. a
Contractor, S. and Roughan, M.: Efficacy of Feedforward and LSTM Neural
Networks at Predicting and Gap Filling Coastal Ocean Timeseries: Oxygen,
Nutrients, and Temperature, Front. Mar. Sci., p. 368, https://doi.org/10.3389/fmars.2021.637759, 2021. a
Davis, X. J., Joyce, T. M., and Kwon, Y.-O.: Prediction of silver hake
distribution on the Northeast US shelf based on the Gulf Stream path index,
Cont. Shelf Res., 138, 51–64, 2017. a
Deb, K., Pratap, A., Agarwal, S., and Meyarivan, T.: A fast and elitist
multiobjective genetic algorithm: NSGA-II, IEEE T. Evolut. Comput., 6, 182–197, 2002. a
Drévillon, M., Fernandez, E., and Lellouche, J. M.:
Glorys global ocean physics reanalysis GLOBAL_MULTIYEAR_PHY_001_030, [data set], https://doi.org/10.48670/moi-00021,
last access: 27 June 2022. a
Durack, P. J., Gleckler, P. J., Landerer, F. W., and Taylor, K. E.: Quantifying
underestimates of long-term upper-ocean warming, Nat. Clim. Change, 4,
999–1005, 2014. a
Ezer, T., Atkinson, L. P., Corlett, W. B., and Blanco, J. L.: Gulf Stream's
induced sea level rise and variability along the US mid‐Atlantic coast,
J. Geophys. Res.-Oceans, 118, 685–697, 2013. a
Fablet, R., Amar, M. M., Febvre, Q., Beauchamp, M., and Chapron, B.: End-to-end
physics-informed representation learning for satellite ocean remote sensing
data: Applications to satellite altimetry and sea surface currents., ISPRS
Annals of the Photogrammetry, Remote Sensing and Spatial Information
Sciences, V-3-2021, 295–302, https://doi.org/10.5194/isprs-annals-V-3-2021-295-2021,
2021. a
Forget, G. and Wunsch, C.: Estimated Global Hydrographic Variability, J. Phys. Oceanogr., 37, 1997–2008, https://doi.org/10.1175/JPO3072.1, 2007. a
Forget, G., Campin, J.-M., Heimbach, P., Hill, C. N., Ponte, R. M., and Wunsch, C.: ECCO version 4: an integrated framework for non-linear inverse modeling and global ocean state estimation, Geosci. Model Dev., 8, 3071–3104, https://doi.org/10.5194/gmd-8-3071-2015, 2015. a, b
Foster, D., Gagne, D. J., and Whitt, D. B.:Probabilistic Machine Learning Estimation of Ocean Mixed Layer Depth From Dense Satellite and Sparse In Situ Observations, J. Adv. Model. Earth Syst., 13, https://doi.org/10.1029/2021MS002474, 2021. a
Gaillard, F., Reynaud, T., Thierry, V., Kolodziejczyk, N., and Von Schuckmann,
K.: In situ–based reanalysis of the global ocean temperature and salinity
with ISAS: Variability of the heat content and steric height, J.
Climate, 29, 1305–1323, 2016. a
Gardner, M. W. and Dorling, S.: Artificial neural networks (the multilayer
perceptron) – a review of applications in the atmospheric sciences,
Atmos. Environ., 32, 2627–2636, 1998. a
Good, S. A., Embury, O., Bulgin, C. E., and Mittaz, J.: ESA Sea Surface Temperature Climate Change Initiative (SST_cci): Level 4 Analysis Climate Data Record, version 2.1., Centre for Environmental Data Analysis, 22 August https://doi.org/10.5285/62c0f97b1eac4e0197a674870afe1ee6, 2019. a, b
Gou, Y., Zhang, T., Liu, J., Wei, L., and Cui, J.: DeepOcean: A General Deep
Learning Framework for Spatio-Temporal Ocean Sensing Data Prediction, IEEE
Access, 8, 79192–79202, https://doi.org/10.1109/ACCESS.2020.2990939, 2020. a
Gueye, M. B., Niang, A., Arnault, S., Thiria, S., and Crépon, M.: Neural
approach to inverting complex system: Application to ocean salinity profile
estimation from surface parameters, Comput. Geosci., 72, 201–209,
2014. a
Guinehut, S., Dhomps, A.-L., Larnicol, G., and Le Traon, P.-Y.: High resolution 3-D temperature and salinity fields derived from in situ and satellite observations, Ocean Sci., 8, 845–857, https://doi.org/10.5194/os-8-845-2012, 2012. a, b, c, d
Hoyer, S. and Hamman, J.: xarray: N-D labeled Arrays and Datasets in Python, Journal of Open Research Software, 5, p. 10. https://doi.org/10.5334/jors.148, 2017. a
Jeong, Y., Hwang, J., Park, J., Jang, C., and Jo, Y.-H.: Reconstructed 3-D
Ocean Temperature Derived from Remotely Sensed Sea Surface Measurements for
Mixed Layer Depth Analysis, Remote Sens., 11, p. 3018, https://doi.org/10.3390/rs11243018,
2019. a
Jiang, F., Ma, J., Wang, B., Shen, F., and Yuan, L.: Ocean Observation Data
Prediction for Argo Data Quality Control Using Deep Bidirectional LSTM
Network, Secur. Commun. Netw., 2021, 5665386,
https://doi.org/10.1155/2021/5665386, 2021. a
Jouini, M., Lévy, M., Crépon, M., and Thiria, S.: Reconstruction of
satellite chlorophyll images under heavy cloud coverage using a neural
classification method, Remote Sens. Environ., 131, 232–246, 2013. a
Karpatne, A., Watkins, W., Read, J., and Kumar, V.: Physics-guided neural
networks (pgnn): An application in lake temperature modeling, arXiv [preprint], https://doi.org/10.48550/arXiv.1710.11431, 2017. a
Kaur, H., Nori, H., Jenkins, S., Caruana, R., Wallach, H., and Wortman Vaughan,
J.: Interpreting Interpretability: Understanding Data Scientists' Use of
Interpretability Tools for Machine Learning, in: Proceedings of the 2020 CHI
Conference on Human Factors in Computing Systems, Honolulu, HI, USA
25–30 April 2020, 1–14, 2020. a
Khosravi, A., Nahavandi, S., Creighton, D., and Atiya, A. F.: Comprehensive
review of neural network-based prediction intervals and new advances, IEEE
T. Neur. Networ., 22, 1341–1356, 2011. a
Kovesi, P.: Good colour maps: How to design them, arXiv [preprint]
https://doi.org/10.48550/arXiv.1509.03700, 2015. a
Lam, S. K., Pitrou, A., and Seibert, S.: Numba: A llvm-based python jit
compiler, in: Proceedings of the Second Workshop on the LLVM Compiler
Infrastructure in HPC, 15–20 November 2015, Austin, TX, USA, 1–6, https://doi.org/10.1145/2833157.2833162, 2015. a
Lellouche, J.-M., Eric, G., Romain, B.-B., Gilles, G., Angélique, M.,
Marie, D., Clément, B., Mathieu, H., Olivier, L. G., and Charly, R.: The
Copernicus global
Lguensat, R., Sun, M., Fablet, R., Tandeo, P., Mason, E., and Chen, G.:
EddyNet: A deep neural network for pixel-wise classification of oceanic
eddies, in: IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing
Symposium, Valencia, Spain
22–27 July 2018, IEEE, 1764–1767, https://doi.org/10.1109/IGARSS.2018.8518411, 2018. a
Lundberg, S. M. and Lee, S.-I.: A Unified Approach to Interpreting Model
Predictions, Adv. Neur. In., 30, 4765–4774,
https://proceedings.neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf (last access: 27 June 2022),
2017. a
Lu, W.: Subsurface temperature estimation from remote sensing data using a
clustering-neural network method, Remote Sens. Environ., 422,
213–222, https://doi.org/10.1016/j.rse.2019.04.009, 2019. a
Mann, C.: The termination of the Gulf Stream and the beginning of the North
Atlantic Current, Deep Sea Research and Oceanographic Abstracts, 14,
337–359, 1967. a
Maze, G. and Marshall, J.: Diagnosing the observed seasonal cycle of Atlantic
subtropical mode water using potential vorticity and its attendant theorems,
J. Phys. Oceanogr., 41, 1986–1999, 2011. a
Meijers, A. J. S., Bindoff, N. L., and Rintoul, S. R.: Estimating the
Four-Dimensional Structure of the Southern Ocean Using Satellite Altimetry,
J. Atmos. Oceanic Technol., 28, 548–568, 2010. a
Meinen, C. S. and Watts, D. R.: Vertical structure and transport on a transect
across the North Atlantic Current near 42 N: Time series and mean, J. Geophys. Res.-Oceans, 105, 21869–21891, 2000. a
Meng, L., Yan, C., Zhuang, W., Zhang, W., and Yan, X.-H.: Reconstruction of
Three-Dimensional Temperature and Salinity Fields from Satellite
Observations, J. Geophys. Res.-Oceans, 126, e2021JC017605, https://doi.org/10.1029/2021JC017605, 2021. a
Minobe, S., Kuwano-Yoshida, A., Komori, N., Xie, S.-P., and Small, R. J.:
Influence of the Gulf Stream on the troposphere, Nature, 452, 206–209, 2008. a
Mulet, S., Rio, M.-H., Mignot, A., Guinehut, S., and Morrow, R.: A new estimate
of the global 3D geostrophic ocean circulation based on satellite data and
in-situ measurements, Deep-Sea Res. Pt. II, 77, 70–81, 2012. a
Mulet, S., Rio, M.-H., Etienne, H., Artana, C., Cancet, M., Dibarboure, G., Feng, H., Husson, R., Picot, N., Provost, C., and Strub, P. T.: The new CNES-CLS18 global mean dynamic topography, Ocean Sci., 17, 789–808, https://doi.org/10.5194/os-17-789-2021, 2021. a, b, c
Mulet, S.:
Multi Observation Global Ocean ARMOR3D L4 analysis and multi-year reprocessing, https://doi.org/10.48670/moi-00052, [data set],
last access: 27 June 2022. a
Mulet, S., Rio, M.-H., Etienne, H., Artana, C., Cancet, M., Dibarboure, G., Feng, H., Husson, R., Picot, N., Provost, C., and Strub, P. T.:
CNES-CLS18 Global Mean Dynamic Topography, [data set], https://www.aviso.altimetry.fr/en/data/products/auxiliary-products/mdt/mdt-global-cnes-cls18.html
last access: 27 June 2022. a
Nerem, R. S., Beckley, B. D., Fasullo, J. T., Hamlington, B. D., Masters, D.,
and Mitchum, G. T.: Climate-change–driven accelerated sea-level rise
detected in the altimeter era, P. Natl. Acad.Sci. USA, 115, 2022–2025, 2018. a
New, A., Smeed, D., Czaja, A., Blaker, A., Mecking, J., Mathews, J., and
Sanchez-Franks, A.: Labrador Slope Water connects the subarctic with the Gulf
Stream, Environ. Res. Lett., 16, 084019, https://doi.org/10.1088/1748-9326/ac1293, 2021. a
NOAA: ETOPO1 1 Arc-Minute Global Relief Model, NOAA National Centers for
Environmental Information, https://doi.org/10.7289/V5C8276M, 2009. a, b
NOAA National Geophysical Data Center: ETOPO1 1 Arc-Minute Global Relief Model, NOAA National Centers for Environmental Information, [data set], https://www.ngdc.noaa.gov/mgg/global/ (last access: 27 June 2022), 2009. a
Ouala, S., Herzet, C., and Fablet, R.: Sea surface temperature prediction and
reconstruction using patch-level neural network representations, in: IGARSS
2018-2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, 22–27 July 2018,
5628–5631, IEEE, 2018. a
Pauthenet, E., Bachelot, L., Tréguier, A.-M., Balem, K., Maze, G., Roquet,
F., Fablet, R., and Tandeo, P.: Gulf Stream Daily Temperature, Salinity and
Mixed Layer Depth fields from Ocean Stratification network (OSnet), Zenodo [data set], https://doi.org/10.5281/zenodo.6011144, 2022a. a, b
Pauthenet, E., Bachelot, L., Balem, K., and Maze, G.: euroargodev/OSnet: v1.0, Zenodo [code], https://doi.org/10.5281/zenodo.6913706, 2022b. a, b
Pauthenet, E., Bachelot, L., Balem, K., and Maze, G.:. euroargodev/OSnet-GulfStream: OSnet-GulfStream v1.0, Zenodo [code], https://doi.org/10.5281/zenodo.6913716, 2022c. a, b
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J.,
Carvalhais, N., and Prabhat, P.: Deep learning and process understanding for
data-driven Earth system science, Nature, 566, 195–204,
https://doi.org/10.1038/s41586-019-0912-1, 2019. a
Reul, N., Grodsky, S., Arias, M., Boutin, J., Catany, R., Chapron, B., d'Amico,
F., Dinnat, E., Donlon, C., and Fore, A.: Sea surface salinity estimates from
spaceborne L-band radiometers: An overview of the first decade of observation
(2010–2019), Remote Sens. Environ., 242, 111769, https://doi.org/10.1016/j.rse.2020.111769, 2020. a
Rocklin, M.: Dask: Parallel computation with blocked algorithms and task
scheduling, in: Proceedings of the 14th python in science conference, vol.
130, Citeseer, 6–12 July 2015, Austin, Texas, 130–1366, https://doi.org/10.25080/Majora-7b98e3ed-013, 2015. a
Rosenblatt, F.: Principles of neurodynamics. perceptrons and the theory of
brain mechanisms, Tech. rep., Cornell Aeronautical Lab Inc Buffalo NY, 1961. a
Rossby, T.: The North Atlantic Current and surrounding waters: At the
crossroads, Rev. Geophys., 34, 463–481, 1996. a
Sallée, J.-B., Pellichero, V., Akhoudas, C., Pauthenet, E., Vignes, L.,
Schmidtko, S., Garabato, A. N., Sutherland, P., and Kuusela, M.: Summertime
increases in upper-ocean stratification and mixed-layer depth, Nature, 591,
592–598, https://doi.org/10.1038/s41586-021-03303-x, 2021. a, b
Sammartino, M., Buongiorno Nardelli, B., Marullo, S., and Santoleri, R.: An
Artificial Neural Network to Infer the Mediterranean 3D Chlorophyll-a and
Temperature Fields from Remote Sensing Observations, Remote Sens., 12, p 4123, https://doi.org/10.3390/rs12244123, 2020. a
Schmidtko, S., Johnson, G. C., and Lyman, J. M.: MIMOC: A global monthly
isopycnal upper-ocean climatology with mixed layers, J. Geophys. Res.-Oceans, 118, 1658–1672, https://doi.org/10.1002/jgrc.20122, 2013. a
Shapley, L. S., Kuhn, H., and Tucker, A.: Contributions to the Theory of Games,
Ann. Math. Stud., 28, 307–317, 1953. a
Shrikumar, A., Greenside, P., and Kundaje, A.: Learning important features
through propagating activation differences, in: International Conference on
Machine Learning, 6–11 August 2017,
Sydney, Australia, 3145–3153, PMLR, 2017. a
Siegelman, L., Klein, P., Rivière, P., Thompson, A. F., Torres, H. S.,
Flexas, M., and Menemenlis, D.: Enhanced upward heat transport at deep
submesoscale ocean fronts, Nat. Geosc., 13, 50–55,
https://doi.org/10.1038/s41561-019-0489-1, 2020a. a
Siegelman, L., Klein, P., Thompson, A. F., Torres, H. S., and Menemenlis, D.:
Altimetry-Based Diagnosis of Deep-Reaching Sub-Mesoscale Ocean Fronts,
Fluids, 5, 145, https://doi.org/10.3390/fluids5030145, 2020b. a
Smeed, D. A., Josey, S., Beaulieu, C., Johns, W. E., Moat, B. I.,
Frajka‐Williams, E., Rayner, D., Meinen, C. S., Baringer, M. O., and
Bryden, H. L.: The North Atlantic Ocean is in a state of reduced overturning,
Geophys. Res. Lett., 45, 1527–1533, 2018. a
Sonnewald, M., Lguensat, R., Jones, D. C., Dueben, P., Brajard, J., and Balaji,
V.: Bridging observations, theory and numerical simulation of the ocean using
machine learning, Environ. Res. Lett., 16, 073008,
https://doi.org/10.1088/1748-9326/ac0eb0, 2021. a
Speer, K. and Forget, G.: Global distribution and formation of mode waters, Elsevier, 103, 211–226, 2013. a
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov,
R.: Dropout: a simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 15, 1929–1958, 2014. a
Stammer, D.: Adjusting internal model errors through ocean state estimation,
J. Phys. Oceanogr., 35, 1143–1153, 2005. a
Stramma, L. and Schott, F.: The mean flow field of the tropical Atlantic Ocean,
Deep-Sea Res. Pt. II, 46, 279–303,
1999. a
Štrumbelj, E. and Kononenko, I.: Explaining prediction models and
individual predictions with feature contributions, Knowl. Inf. Syst., 41, 647–665, 2014. a
Su, H., Zhang, T., Lin, M., Lu, W., and Yan, X.-H.: Predicting subsurface
thermohaline structure from remote sensing data based on long short-term
memory neural networks, Remote Sens. Environ., 260, 112465, https://doi.org/10.1016/j.rse.2021.112465, 2021. a
Sun, C. and Watts, D. R.: A circumpolar gravest empirical mode for the Southern
Ocean hydrography, J. Geophys. Res., 106, 2833–2855, 2001. a
Szekely, T., Gourrion, J., Pouliquen, S., and Reverdin, G.: CORA, Coriolis
Ocean Dataset for Reanalysis, SEANOE, Copernicus [data set], https://doi.org/10.17882/46219, 2019. a
Szekely, T., Gourrion, J., Pouliquen, S., and Reverdin, G.:
CORA, Coriolis Ocean Dataset for Reanalysis, [data set], https://www.seanoe.org/data/00351/46219/,
last access: 27 June 2022. a
Tandeo, P., Chapron, B., Ba, S., Autret, E., and Fablet, R.: Segmentation of
mesoscale ocean surface dynamics using satellite SST and SSH observations,
IEEE T. Geosci. Remote, 52, 4227–4235, 2013. a
Taylor, J. R. and Ferrari, R.: Buoyancy and wind-driven convection at mixed
layer density fronts, J. Phys. Oceanogr., 40, 1222–1242, 2010. a
Thyng, K. M., Greene, C. A., Hetland, R. D., Zimmerle, H. M., and DiMarco,
S. F.: True Colors of Oceanography: Guidelines for Effective and Accurate
Colormap Selection, Oceanography, 29, 9–13,
https://doi.org/10.5670/oceanog.2016.66, 2016. a
Toole, J., Curry, R., Joyce, T., McCartney, M., Smethie, B., and Smith, J.:
Line W, monitoring the North Atlantic ocean’s deep western boundary currents, [data set], https://scienceweb.whoi.edu/linew/,
last access: 27 June 2022. a
Wang, C., Tandeo, P., Mouche, A., Stopa, J. E., Gressani, V., Longepe, N.,
Vandemark, D., Foster, R. C., and Chapron, B.: Classification of the global
Sentinel-1 SAR vignettes for ocean surface process studies, Remote Sens. Environ., 234, 111457, https://doi.org/10.1016/j.rse.2019.111457, 2019. a
Wang, G., Cheng, L., Abraham, J., and Li, C.: Consensuses and discrepancies of
basin-scale ocean heat content changes in different ocean analyses, Clim.
Dynam., 50, 2471–2487, https://doi.org/10.1007/s00382-017-3751-5, 2018.
a
Wong, A. P., Wijffels, S. E., Riser, S. C., Pouliquen, S., Hosoda, S.,
Roemmich, D., Gilson, J., Johnson, G. C., Martini, K., and Murphy, D. J.:
Argo data 1999–2019: two million temperature-salinity profiles and
subsurface velocity observations from a global array of profiling floats,
Front. Mar. Sci., 700, https://doi.org/10.3389/fmars.2020.00700, 2020. a
Zhu, X. X., Tuia, D., Mou, L., Xia, G., Zhang, L., Xu, F., and Fraundorfer, F.:
Deep Learning in Remote Sensing: A Comprehensive Review and List of
Resources, IEEE Geoscience and Remote Sensing Magazine, 5, 8–36,
https://doi.org/10.1109/MGRS.2017.2762307, 2017. a
Short summary
Temperature and salinity profiles are essential for studying the ocean’s stratification, but there are not enough of these data. Satellites are able to measure daily maps of the surface ocean. We train a machine to learn the link between the satellite data and the profiles in the Gulf Stream region. We can then use this link to predict profiles at the high resolution of the satellite maps. Our prediction is fast to compute and allows us to get profiles at any locations only from surface data.
Temperature and salinity profiles are essential for studying the ocean’s stratification, but...
