Articles | Volume 20, issue 6
https://doi.org/10.5194/os-20-1707-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Special issue:
https://doi.org/10.5194/os-20-1707-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Monitoring the coastal–offshore water interactions in the Levantine Sea using ocean color and deep supervised learning
Georges Baaklini
CORRESPONDING AUTHOR
LOCEAN Laboratory, Sorbonne University, UPMC Univ Paris 06 CNRS-IRD-MNHN, 4 place Jussieu, 75005 Paris, France
Julien Brajard
Nansen Environmental and Remote Sensing Center, Bergen, Norway
Leila Issa
Department of Computer Science and Mathematics, Lebanese American University, Beirut, Lebanon
Gina Fifani
LOCEAN Laboratory, Sorbonne University, UPMC Univ Paris 06 CNRS-IRD-MNHN, 4 place Jussieu, 75005 Paris, France
Laurent Mortier
LOCEAN Laboratory, Sorbonne University, UPMC Univ Paris 06 CNRS-IRD-MNHN, 4 place Jussieu, 75005 Paris, France
Roy El Hourany
Laboratoire d'Océanologie et de Géosciences, Univ. Littoral Côte d'Opale, Univ. Lille, CNRS, IRD, UMR 8187, LOG, 62930 Wimereux, France
Related authors
Georges Baaklini, Roy El Hourany, Milad Fakhri, Julien Brajard, Leila Issa, Gina Fifani, and Laurent Mortier
Ocean Sci., 18, 1491–1505, https://doi.org/10.5194/os-18-1491-2022, https://doi.org/10.5194/os-18-1491-2022, 2022
Short summary
Short summary
We use machine learning to analyze the long-term variation of the surface currents in the Levantine Sea, located in the eastern Mediterranean Sea. We decompose the circulation into groups based on their physical characteristics and analyze their spatial and temporal variability. We show that most structures of the Levantine Sea are becoming more energetic over time, despite those of the western area remaining the most dominant due to their complex bathymetry and strong currents.
Zikang He, Yiguo Wang, Julien Brajard, Xidong Wang, and Zheqi Shen
The Cryosphere, 19, 3279–3293, https://doi.org/10.5194/tc-19-3279-2025, https://doi.org/10.5194/tc-19-3279-2025, 2025
Short summary
Short summary
Declining Arctic sea ice presents both risks and opportunities for ecosystems, communities, and economic activities. To address prediction errors in dynamical models, we apply machine learning for error correction during prediction (online) or post-processing (offline). Our results show that both methods enhance sea ice predictions, particularly from September to January, with offline corrections outperforming online corrections.
Cyril Palerme, Johannes Röhrs, Thomas Lavergne, Jozef Rusin, Are Frode Kvanum, Atle Macdonald Sørensen, Arne Melsom, Julien Brajard, Martina Idžanović, Marina Durán Moro, and Malte Müller
EGUsphere, https://doi.org/10.5194/egusphere-2025-2001, https://doi.org/10.5194/egusphere-2025-2001, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
We present MET-AICE, a sea ice prediction system based on artificial intelligence techniques that has been running operationally since March 2024. The forecasts are produced daily and provide sea ice concentration predictions for the next 10 days. We evaluate the MET-AICE forecasts from the first year of operation, and we compare them to forecasts produced by a physically-based model (Barents-2.5km). We show that MET-AICE is skillful and provides more accurate forecasts than Barents-2.5km.
Stéphane Doléac, Marina Lévy, Roy El Hourany, and Laurent Bopp
Biogeosciences, 22, 841–862, https://doi.org/10.5194/bg-22-841-2025, https://doi.org/10.5194/bg-22-841-2025, 2025
Short summary
Short summary
The marine biogeochemistry components of Coupled Model Intercomparison Project phase 6 (CMIP6) models vary widely in their process representations. Using an innovative bioregionalization of the North Atlantic, we reveal that this model diversity largely drives the divergence in net primary production projections under a high-emission scenario. The identification of the most mechanistically realistic models allows for a substantial reduction in projection uncertainty.
Léo Edel, Jiping Xie, Anton Korosov, Julien Brajard, and Laurent Bertino
The Cryosphere, 19, 731–752, https://doi.org/10.5194/tc-19-731-2025, https://doi.org/10.5194/tc-19-731-2025, 2025
Short summary
Short summary
This study developed a new method to estimate Arctic sea ice thickness from 1992 to 2010 using a combination of machine learning and data assimilation. By training a machine learning model on data from 2011 to 2022, past errors in sea ice thickness can be corrected, leading to improved estimations. This approach provides insights into historical changes in sea ice thickness, showing a notable decline from 1992 to 2022, and offers a valuable resource for future studies.
Charlotte Durand, Tobias Sebastian Finn, Alban Farchi, Marc Bocquet, Julien Brajard, and Laurent Bertino
EGUsphere, https://doi.org/10.5194/egusphere-2024-4028, https://doi.org/10.5194/egusphere-2024-4028, 2025
Short summary
Short summary
This paper presents a four-dimensional variational data assimilation system based on a neural network emulator for sea-ice thickness, learned from neXtSIM simulation outputs. Testing with simulated and real observation retrievals, the system improves forecasts and bias error, performing comparably to operational methods, demonstrating the promise of sea-ice data-driven data assimilation systems.
Zikang He, Julien Brajard, Yiguo Wang, Xidong Wang, and Zheqi Shen
EGUsphere, https://doi.org/10.5194/egusphere-2025-212, https://doi.org/10.5194/egusphere-2025-212, 2025
Short summary
Short summary
Climate prediction is challenging due to systematic errors in traditional climate models. We addressed this by training a machine learning model to correct these errors and then integrating it with the traditional climate model to form an AI-physics hybrid model. Our study demonstrates that the hybrid model outperforms the original climate model on both short-term and long-term predictions of the atmosphere and ocean.
Alexander Barth, Julien Brajard, Aida Alvera-Azcárate, Bayoumy Mohamed, Charles Troupin, and Jean-Marie Beckers
Ocean Sci., 20, 1567–1584, https://doi.org/10.5194/os-20-1567-2024, https://doi.org/10.5194/os-20-1567-2024, 2024
Short summary
Short summary
Most satellite observations have gaps, for example, due to clouds. This paper presents a method to reconstruct missing data in satellite observations of the chlorophyll a concentration in the Black Sea. Rather than giving a single possible reconstructed field, the discussed method provides an ensemble of possible reconstructions using a generative neural network. The resulting ensemble is validated using techniques from numerical weather prediction and ocean modelling.
Simon Driscoll, Alberto Carrassi, Julien Brajard, Laurent Bertino, Einar Ólason, Marc Bocquet, and Amos Lawless
EGUsphere, https://doi.org/10.5194/egusphere-2024-2476, https://doi.org/10.5194/egusphere-2024-2476, 2024
Short summary
Short summary
The formation and evolution of sea ice melt ponds (ponds of melted water) are complex, insufficiently understood and represented in models with considerable uncertainty. These uncertain representations are not traditionally included in climate models potentially causing the known underestimation of sea ice loss in climate models. Our work creates the first observationally based machine learning model of melt ponds that is also a ready and viable candidate to be included in climate models.
Cyril Palerme, Thomas Lavergne, Jozef Rusin, Arne Melsom, Julien Brajard, Are Frode Kvanum, Atle Macdonald Sørensen, Laurent Bertino, and Malte Müller
The Cryosphere, 18, 2161–2176, https://doi.org/10.5194/tc-18-2161-2024, https://doi.org/10.5194/tc-18-2161-2024, 2024
Short summary
Short summary
Sea ice forecasts are operationally produced using physically based models, but these forecasts are often not accurate enough for maritime operations. In this study, we developed a statistical correction technique using machine learning in order to improve the skill of short-term (up to 10 d) sea ice concentration forecasts produced by the TOPAZ4 model. This technique allows for the reduction of errors from the TOPAZ4 sea ice concentration forecasts by 41 % on average.
Roy El Hourany, Juan Pierella Karlusich, Lucie Zinger, Hubert Loisel, Marina Levy, and Chris Bowler
Ocean Sci., 20, 217–239, https://doi.org/10.5194/os-20-217-2024, https://doi.org/10.5194/os-20-217-2024, 2024
Short summary
Short summary
Satellite observations offer valuable information on phytoplankton abundance and community structure. Here, we employ satellite observations to infer seven phytoplankton groups at a global scale based on a new molecular method from Tara Oceans. The link has been established using machine learning approaches. The output of this work provides excellent tools to collect essential biodiversity variables and a foundation to monitor the evolution of marine biodiversity.
Joelle Habib, Caroline Ulses, Claude Estournel, Milad Fakhri, Patrick Marsaleix, Mireille Pujo-Pay, Marine Fourrier, Laurent Coppola, Alexandre Mignot, Laurent Mortier, and Pascal Conan
Biogeosciences, 20, 3203–3228, https://doi.org/10.5194/bg-20-3203-2023, https://doi.org/10.5194/bg-20-3203-2023, 2023
Short summary
Short summary
The Rhodes Gyre, eastern Mediterranean Sea, is the main Levantine Intermediate Water formation site. In this study, we use a 3D physical–biogeochemical model to investigate the seasonal and interannual variability of organic carbon dynamics in the gyre. Our results show its autotrophic nature and its high interannual variability, with enhanced primary production, downward exports, and onward exports to the surrounding regions during years marked by intense heat losses and deep mixed layers.
Georges Baaklini, Roy El Hourany, Milad Fakhri, Julien Brajard, Leila Issa, Gina Fifani, and Laurent Mortier
Ocean Sci., 18, 1491–1505, https://doi.org/10.5194/os-18-1491-2022, https://doi.org/10.5194/os-18-1491-2022, 2022
Short summary
Short summary
We use machine learning to analyze the long-term variation of the surface currents in the Levantine Sea, located in the eastern Mediterranean Sea. We decompose the circulation into groups based on their physical characteristics and analyze their spatial and temporal variability. We show that most structures of the Levantine Sea are becoming more energetic over time, despite those of the western area remaining the most dominant due to their complex bathymetry and strong currents.
Katia Mallil, Pierre Testor, Anthony Bosse, Félix Margirier, Loic Houpert, Hervé Le Goff, Laurent Mortier, and Ferial Louanchi
Ocean Sci., 18, 937–952, https://doi.org/10.5194/os-18-937-2022, https://doi.org/10.5194/os-18-937-2022, 2022
Short summary
Short summary
Our study documents the circulation in the Algerian Basin of the western Mediterranean Sea using in situ data. It shows that the Algerian Gyres have an impact on the distribution at intermediate depth of Levantine Intermediate Water. They allow a westward transport from the south of Sardinia toward the interior of the Algerian Basin. Temperature and salinity trends of this water mass are also investigated, confirming a recent acceleration of the warming and salinification during the last decade.
Cited articles
Alaguarda, D., Brajard, J., Coulibaly, G., Canesi, M., Douville, E., Le Cornec, F., Lelabousse, C., and Tribollet, A.: 54 years of microboring community history explored by machine learning in a massive coral from Mayotte (Indian Ocean), Front. Mar. Sci., 9, 899398, https://doi.org/10.3389/fmars.2022.899398, 2022. a
Amitai, Y., Lehahn, Y., Lazar, A., and Heifetz, E.: Surface circulation of the eastern Mediterranean Levantine basin: Insights from analyzing 14 years of satellite altimetry data, J. Geophys. Res.-Oceans, 115, C10058, https://doi.org/10.1029/2010JC006147, 2010. a
Atkinson, L. P., Brink, K. H., Davis, R. E., Jones, B. H., Paluszkiewicz, T., and Stuart, D. W.: Mesoscale hydrographic variability in the vicinity of Points Conception and Arguello during April–May 1983: the OPUS 1983 experiment, J. Geophys. Res.-Oceans, 91, 12899–12918, 1986. a
Baaklini, G.: Characterization of the Eastern Mediterranean surface dynamics: Insights from drifter assimilation and machine learning techniques, PhD thesis, Sorbonne Université, https://theses.hal.science/tel-03828273 (last access: 23 April 2024), 2022. a
Baaklini, G., El Hourany, R., Fakhri, M., Brajard, J., Issa, L., Fifani, G., and Mortier, L.: Surface circulation properties in the eastern Mediterranean emphasized using machine learning methods, Ocean Sci., 18, 1491–1505, https://doi.org/10.5194/os-18-1491-2022, 2022. a, b
Barale, V., Jaquet, J.-M., and Ndiaye, M.: Algal blooming patterns and anomalies in the Mediterranean Sea as derived from the SeaWiFS data set (1998–2003), Remote Sens. Environ., 112, 3300–3313, https://doi.org/10.1016/j.rse.2007.10.014, 2008. a
Botha, E. J., Anstee, J. M., Sagar, S., Lehmann, E., and Medeiros, T. A.: Classification of Australian waterbodies across a wide range of optical water types, Remote Sens., 12, 3018–3041, https://doi.org/10.3390/rs12183018, 2020. a
Brenner, S.: High-resolution nested model simulations of the climatological circulation in the southeastern Mediterranean Sea, Ann. Geophys., 21, 267–280, https://doi.org/10.5194/angeo-21-267-2003, 2003. a
Cannizzaro, J. P. and Carder, K. L.: Estimating chlorophyll a concentrations from remote-sensing reflectance in optically shallow waters, Remote Sens. Environ., 101, 13–24, https://doi.org/10.1016/j.rse.2005.12.002, 2006. a
Cipollini, P., Benveniste, J., Bouffard, J., Emery, W., Gommenginger, C., Griffin, D., Høyer, J., Madsen, K., Mercier, F., Miller, L., et al.: The role of altimetry in coastal observing systems, Proceedings of OceanObs, 9, 181–191, https://doi.org/10.5270/OceanObs09.cwp.16, 2010. a
Dong, C., Xu, G., Han, G., Bethel, B. J., Xie, W., and Zhou, S.: Recent developments in artificial intelligence in oceanography, Ocean-Land-Atmosphere Research, 2022 9870950, https://doi.org/10.34133/2022/9870950, 2022. a
Escudier, R., Mourre, B., Juza, M., and Tintoré, J.: Subsurface circulation and mesoscale variability in the Algerian subbasin from altimeter-derived eddy trajectories: ALGERIAN EDDIES PROPAGATION, J. Geophys. Res.-Oceans, 121, 6310–6322, https://doi.org/10.1002/2016JC011760, 2016. a
Fifani, G., Baudena, A., Fakhri, M., Baaklini, G., Faugère, Y., Morrow, R., Mortier, L., and d'Ovidio, F.: Drifting Speed of Lagrangian Fronts and Oil Spill Dispersal at the Ocean Surface, Remote Sens., 13, 4499, https://doi.org/10.3390/rs13224499, 2021. a
GEBCO: GEBCO 2020 Grid, version 2020.0, https://www.gebco.net (last access: 11 July 2024), 2020. a
Han, J. and Moraga, C.: The influence of the sigmoid function parameters on the speed of backpropagation learning, in: International workshop on artificial neural networks, 195–201, Springer, https://link.springer.com/content/pdf/10.1007/3-540-59497-3_175.pdf (last access: 11 July 2024), 1995. a
Jackson, T., Sathyendranath, S., and Mélin, F.: An improved optical classification scheme for the Ocean Colour Essential Climate Variable and its applications, Remote Sens. Environ., 203, 152–161, https://doi.org/10.1016/j.rse.2017.03.036, 2017. a
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, arXiv [preprint], https://doi.org/10.48550/arXiv.1412.6980, 22 December 2014. a
Levy, M. and Martin, A. P.: The influence of mesoscale and submesoscale heterogeneity on ocean biogeochemical reactions: INFLUENCE OF HETEROGENEITY, Global Biogeochem. Cy., 27, 1139–1150, https://doi.org/10.1002/2012GB004518, 2013. a
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, 22–27 July 2018, 1764–1767, https://doi.org/10.1109/IGARSS.2018.8518411, 2018. a
Lillibridge III, J., Hitchcock, G., Rossby, T., Lessard, E., Mork, M., and Golmen, L.: Entrainment and mixing of shelf/slope waters in the near-surface Gulf Stream, J. Geophys. Res.-Oceans, 95, 13065–13087, https://doi.org/10.1029/JC095iC08p13065, 1990. a
Martin Traykovski, L. V. and Sosik, H. M.: Feature-based classification of optical water types in the Northwest Atlantic based on satellite ocean color data, J. Geophys. Res.-Oceans, 108, 3150–3167, https://doi.org/10.1029/2001JC001172, 2003. a
Mélin, F. and Vantrepotte, V.: How optically diverse is the coastal ocean?, Remote Sens. Environ., 160, 235–251, https://doi.org/10.1016/j.rse.2015.01.023, 2015. a
Menna, M., Poulain, P.-M., Zodiatis, G., and Gertman, I.: On the surface circulation of the Levantine sub-basin derived from Lagrangian drifters and satellite altimetry data, Deep-Sea Res. Pt. I, 65, 46–58, https://doi.org/10.1016/j.dsr.2012.02.008, 2012. a, b
Menna, M., Gerin, R., Bussani, A., and Poulain, P.-M.: Satellite-tracked surface drifting buoy (drifter) observations of currents and sea surface temperature in the Mediterranean Sea (1986–2016), nodc.ogs.it [data set], https://doi.org/10.6092/7A8499BC-C5EE-472C-B8B5-03523D1E73E9, 2018. a
Mkhinini, N., Coimbra, A. L. S., Stegner, A., Arsouze, T., Taupier-Letage, I., and Béranger, K.: Long-lived mesoscale eddies in the eastern Mediterranean Sea: Analysis of 20 years of AVISO geostrophic velocities, J. Geophys. Res.-Oceans, 119, 8603–8626, https://doi.org/10.1002/2014JC010176, 2014. a
Moore, T. S., Campbell, J. W., and Dowell, M. D.: A class-based approach to characterizing and mapping the uncertainty of the MODIS ocean chlorophyll product, Remote Sens. Environ., 113, 2424–2430, https://doi.org/10.1016/j.rse.2009.07.016, 2009. a
Moschos, E., Kugusheva, A., Coste, P., and Stegner, A.: Computer Vision for Ocean Eddy Detection in Infrared Imagery, in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Hawaii, 3–7 January 2023, 6395–6404, https://doi.org/10.1109/WACV56688.2023.00633, 2023. a, b
NASA Goddard Space Flight Center, Ocean Ecology Laboratory, Ocean Biology Processing Group: Moderate-resolution Imaging Spectroradiometer (MODIS) Aqua Chlorophyll Data, 2018 Reprocessing, oceancolor.gsfc.nasa.gov [data set], https://doi.org/10.5067/AQUA/MODIS/L3B/CHL/2018, 2024. a
Ou, H. W.: Flow near a continental boundary driven by an oceanic jet, J. Phys. Oceanogr., 24, 966–978, https://doi.org/10.1175/1520-0485(1994)024<0966:FNACBD>2.0.CO;2, 1994. a
Pujol, M.-I. and Larnicol, G.: Mediterranean sea eddy kinetic energy variability from 11 years of altimetric data, J. Mar. Syst., 58, 121–142, https://doi.org/10.1016/j.jmarsys.2005.07.005, 2005. a
Ronneberger, O., Fischer, P., and Brox, T.: U-net: Convolutional networks for biomedical image segmentation, in: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, 5–9 October 2015, Proceedings, Part III 18, 234–241, arXiv [preprint], https://doi.org/10.48550/arXiv.1505.04597, 18 May 2015. a, b
Rosentraub, Z. and Brenner, S.: Circulation over the southeastern continental shelf and slope of the Mediterranean Sea: Direct current measurements, winds, and numerical model simulations, J. Geophys. Res.-Oceans, 112, C11001, https://doi.org/10.1029/2006JC003775, 2007. a
Sarangi, R.: Observation of Oceanic Eddy in the Northeastern Arabian Sea Using Multisensor Remote Sensing Data, Int. J. Oceanogr., 531982, https://doi.org/10.1155/2012/531982, 2012. a
Shaban, M., Salim, R., Abu Khalifeh, H., Khelifi, A., Shalaby, A., El-Mashad, S., Mahmoud, A., Ghazal, M., and El-Baz, A.: A deep-learning framework for the detection of oil spills from SAR data, Sensors, 21, 2351, https://doi.org/10.3390/s21072351, 2021. a
Sonnewald, M., Lguensat, R., Jones, D. C., Dueben, P. D., 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
Spyrakos, E., Vilas, L. G., Palenzuela, J. M. T., and Barton, E. D.: Remote sensing chlorophyll a of optically complex waters (rias Baixas, NW Spain): Application of a regionally specific chlorophyll a algorithm for MERIS full resolution data during an upwelling cycle, Remote Sens. Environ., 115, 2471–2485, https://doi.org/10.1016/j.rse.2011.05.008, 2011. a
SSALTO/DUACS: Processed by SSALTO/DUACS and Distributed by AVISO+, https://www.aviso.altimetry.fr (last access: 11 July 2024), 2022. a
Stern, M. E. and Whitehead, J.: Separation of a boundary jet in a rotating fluid, J. Fluid Mech., 217, 41–69, https://doi.org/10.1017/S0022112090000623, 1990. a
Sun, N., Zhou, Z., Li, Q., and Zhou, X.: Spatiotemporal Prediction of Monthly Sea Subsurface Temperature Fields Using a 3D U-Net-Based Model, Remote Sens., 14, 4890, https://doi.org/10.3390/rs14194890, 2022. a
Sutyrin, G., Stegner, A., Taupier-Letage, I., and Teinturier, S.: Amplification of a surface-intensified eddy drift along a steep shelf in the Eastern Mediterranean Sea, J. Phys. Oceanogr., 39, 1729–1741, https://doi.org/10.1175/2009JPO4106.1, 2009. a
Taupier-Letage, I., Puillat, I., Raimbault, P., and Millot, C.: Biological response to mesoscale eddies in the Algerian Basin, J. Geophys. Res., 108, 3245–3267, https://doi.org/10.1029/1999JC000117, 2003. a
Wei, J., Wang, M., Mikelsons, K., Jiang, L., Kratzer, S., Lee, Z., Moore, T., Sosik, H. M., and Van der Zande, D.: Global satellite water classification data products over oceanic, coastal, and inland waters, Remote Sens. Environ., 282, 113233, https://doi.org/10.1016/j.rse.2022.113233, 2022. a
Zhang, X., Zhao, N., and Han, Z.: A Modified U-Net Model for Predicting the Sea Surface Salinity over the Western Pacific Ocean, Remote Sens., 15, 1684, https://doi.org/10.3390/rs15061684, 2023. a
Short summary
Understanding the flow of the Levantine Sea surface current is not straightforward. We propose a study based on learning techniques to follow interactions between water near the shore and further out at sea. Our results show changes in the coastal currents past 33.8° E, with frequent instances of water breaking away along the Lebanese coast. These events happen quickly and sometimes lead to long-lasting eddies. This study underscores the need for direct observations to improve our knowledge.
Understanding the flow of the Levantine Sea surface current is not straightforward. We propose a...