Articles | Volume 20, issue 4
https://doi.org/10.5194/os-20-1035-2024
© 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-20-1035-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Deep learning for the super resolution of Mediterranean sea surface temperature fields
Consiglio Nazionale delle Ricerche, Istituto di Scienze Marine (CNR-ISMAR), Calata Porta di Massa, 80133 Naples, Italy
Daniele Ciani
Consiglio Nazionale delle Ricerche, Istituto di Scienze Marine (CNR-ISMAR), Via del Fosso del Cavaliere 100, 00133 Rome, Italy
Andrea Pisano
Consiglio Nazionale delle Ricerche, Istituto di Scienze Marine (CNR-ISMAR), Via del Fosso del Cavaliere 100, 00133 Rome, Italy
Bruno Buongiorno Nardelli
Consiglio Nazionale delle Ricerche, Istituto di Scienze Marine (CNR-ISMAR), Calata Porta di Massa, 80133 Naples, Italy
Related authors
Anna Teruzzi, Ali Aydogdu, Carolina Amadio, Emanuela Clementi, Simone Colella, Valeria Di Biagio, Massimiliano Drudi, Claudia Fanelli, Laura Feudale, Alessandro Grandi, Pietro Miraglio, Andrea Pisano, Jenny Pistoia, Marco Reale, Stefano Salon, Gianluca Volpe, and Gianpiero Cossarini
State Planet, 4-osr8, 15, https://doi.org/10.5194/sp-4-osr8-15-2024, https://doi.org/10.5194/sp-4-osr8-15-2024, 2024
Short summary
Short summary
A noticeable cold spell occurred in Eastern Europe at the beginning of 2022 and was the main driver of intense deep-water formation and the associated transport of nutrients to the surface. Southeast of Crete, the availability of both light and nutrients in the surface layer stimulated an anomalous phytoplankton bloom. In the area, chlorophyll concentration (a proxy for bloom intensity) and primary production were considerably higher than usual, suggesting possible impacts on fishery catches.
Karina von Schuckmann, Lorena Moreira, Mathilde Cancet, Flora Gues, Emmanuelle Autret, Jonathan Baker, Clément Bricaud, Romain Bourdalle-Badie, Lluis Castrillo, Lijing Cheng, Frederic Chevallier, Daniele Ciani, Alvaro de Pascual-Collar, Vincenzo De Toma, Marie Drevillon, Claudia Fanelli, Gilles Garric, Marion Gehlen, Rianne Giesen, Kevin Hodges, Doroteaciro Iovino, Simon Jandt-Scheelke, Eric Jansen, Melanie Juza, Ioanna Karagali, Thomas Lavergne, Simona Masina, Ronan McAdam, Audrey Minière, Helen Morrison, Tabea Rebekka Panteleit, Andrea Pisano, Marie-Isabelle Pujol, Ad Stoffelen, Sulian Thual, Simon Van Gennip, Pierre Veillard, Chunxue Yang, and Hao Zuo
State Planet, 4-osr8, 1, https://doi.org/10.5194/sp-4-osr8-1-2024, https://doi.org/10.5194/sp-4-osr8-1-2024, 2024
Karina von Schuckmann, Lorena Moreira, Mathilde Cancet, Flora Gues, Emmanuelle Autret, Ali Aydogdu, Lluis Castrillo, Daniele Ciani, Andrea Cipollone, Emanuela Clementi, Gianpiero Cossarini, Alvaro de Pascual-Collar, Vincenzo De Toma, Marion Gehlen, Rianne Giesen, Marie Drevillon, Claudia Fanelli, Kevin Hodges, Simon Jandt-Scheelke, Eric Jansen, Melanie Juza, Ioanna Karagali, Priidik Lagemaa, Vidar Lien, Leonardo Lima, Vladyslav Lyubartsev, Ilja Maljutenko, Simona Masina, Ronan McAdam, Pietro Miraglio, Helen Morrison, Tabea Rebekka Panteleit, Andrea Pisano, Marie-Isabelle Pujol, Urmas Raudsepp, Roshin Raj, Ad Stoffelen, Simon Van Gennip, Pierre Veillard, and Chunxue Yang
State Planet, 4-osr8, 2, https://doi.org/10.5194/sp-4-osr8-2-2024, https://doi.org/10.5194/sp-4-osr8-2-2024, 2024
Daniele Ciani, Claudia Fanelli, and Bruno Buongiorno Nardelli
EGUsphere, https://doi.org/10.5194/egusphere-2024-1164, https://doi.org/10.5194/egusphere-2024-1164, 2024
Short summary
Short summary
Ocean surface currents are routinely derived from satellite observations of the sea level, allowing a regional to global scale synoptic monitoring. In order to overcome the theoretical and instrumental limits of this methodology, we exploit the synergy of multisensor satellite observations. We rely on deep learning, physics informed algorithms to predict ocean currents from sea surface height and sea surface temperature observations. Results are validated by means of in-situ measurements
Anna Teruzzi, Ali Aydogdu, Carolina Amadio, Emanuela Clementi, Simone Colella, Valeria Di Biagio, Massimiliano Drudi, Claudia Fanelli, Laura Feudale, Alessandro Grandi, Pietro Miraglio, Andrea Pisano, Jenny Pistoia, Marco Reale, Stefano Salon, Gianluca Volpe, and Gianpiero Cossarini
State Planet, 4-osr8, 15, https://doi.org/10.5194/sp-4-osr8-15-2024, https://doi.org/10.5194/sp-4-osr8-15-2024, 2024
Short summary
Short summary
A noticeable cold spell occurred in Eastern Europe at the beginning of 2022 and was the main driver of intense deep-water formation and the associated transport of nutrients to the surface. Southeast of Crete, the availability of both light and nutrients in the surface layer stimulated an anomalous phytoplankton bloom. In the area, chlorophyll concentration (a proxy for bloom intensity) and primary production were considerably higher than usual, suggesting possible impacts on fishery catches.
Karina von Schuckmann, Lorena Moreira, Mathilde Cancet, Flora Gues, Emmanuelle Autret, Jonathan Baker, Clément Bricaud, Romain Bourdalle-Badie, Lluis Castrillo, Lijing Cheng, Frederic Chevallier, Daniele Ciani, Alvaro de Pascual-Collar, Vincenzo De Toma, Marie Drevillon, Claudia Fanelli, Gilles Garric, Marion Gehlen, Rianne Giesen, Kevin Hodges, Doroteaciro Iovino, Simon Jandt-Scheelke, Eric Jansen, Melanie Juza, Ioanna Karagali, Thomas Lavergne, Simona Masina, Ronan McAdam, Audrey Minière, Helen Morrison, Tabea Rebekka Panteleit, Andrea Pisano, Marie-Isabelle Pujol, Ad Stoffelen, Sulian Thual, Simon Van Gennip, Pierre Veillard, Chunxue Yang, and Hao Zuo
State Planet, 4-osr8, 1, https://doi.org/10.5194/sp-4-osr8-1-2024, https://doi.org/10.5194/sp-4-osr8-1-2024, 2024
Karina von Schuckmann, Lorena Moreira, Mathilde Cancet, Flora Gues, Emmanuelle Autret, Ali Aydogdu, Lluis Castrillo, Daniele Ciani, Andrea Cipollone, Emanuela Clementi, Gianpiero Cossarini, Alvaro de Pascual-Collar, Vincenzo De Toma, Marion Gehlen, Rianne Giesen, Marie Drevillon, Claudia Fanelli, Kevin Hodges, Simon Jandt-Scheelke, Eric Jansen, Melanie Juza, Ioanna Karagali, Priidik Lagemaa, Vidar Lien, Leonardo Lima, Vladyslav Lyubartsev, Ilja Maljutenko, Simona Masina, Ronan McAdam, Pietro Miraglio, Helen Morrison, Tabea Rebekka Panteleit, Andrea Pisano, Marie-Isabelle Pujol, Urmas Raudsepp, Roshin Raj, Ad Stoffelen, Simon Van Gennip, Pierre Veillard, and Chunxue Yang
State Planet, 4-osr8, 2, https://doi.org/10.5194/sp-4-osr8-2-2024, https://doi.org/10.5194/sp-4-osr8-2-2024, 2024
Vincenzo de Toma, Daniele Ciani, Yassmin Hesham Essa, Chunxue Yang, Vincenzo Artale, Andrea Pisano, Davide Cavaliere, Rosalia Santoleri, and Andrea Storto
Geosci. Model Dev., 17, 5145–5165, https://doi.org/10.5194/gmd-17-5145-2024, https://doi.org/10.5194/gmd-17-5145-2024, 2024
Short summary
Short summary
This study explores methods to reconstruct diurnal variations in skin sea surface temperature in a model of the Mediterranean Sea. Our new approach, considering chlorophyll concentration, enhances spatial and temporal variations in the warm layer. Comparative analysis shows context-dependent improvements. The proposed "chlorophyll-interactive" method brings the surface net total heat flux closer to zero annually, despite a net heat loss from the ocean to the atmosphere.
Daniele Ciani, Claudia Fanelli, and Bruno Buongiorno Nardelli
EGUsphere, https://doi.org/10.5194/egusphere-2024-1164, https://doi.org/10.5194/egusphere-2024-1164, 2024
Short summary
Short summary
Ocean surface currents are routinely derived from satellite observations of the sea level, allowing a regional to global scale synoptic monitoring. In order to overcome the theoretical and instrumental limits of this methodology, we exploit the synergy of multisensor satellite observations. We rely on deep learning, physics informed algorithms to predict ocean currents from sea surface height and sea surface temperature observations. Results are validated by means of in-situ measurements
Sarah Asdar, Daniele Ciani, and Bruno Buongiorno Nardelli
Earth Syst. Sci. Data, 16, 1029–1046, https://doi.org/10.5194/essd-16-1029-2024, https://doi.org/10.5194/essd-16-1029-2024, 2024
Short summary
Short summary
Estimating 3D currents is crucial for the understanding of ocean dynamics, and a precise knowledge of ocean circulation is essential to ensure a sustainable ocean. In this context, a new high-resolution (1 / 10°) data-driven dataset of 3D ocean currents has been developed within the European Space Agency World Ocean Circulation project, providing 10 years (2010–2019) of horizontal and vertical quasi-geostrophic currents at daily resolution over the North Atlantic Ocean, down to 1500 m depth.
Andrea Pisano, Daniele Ciani, Salvatore Marullo, Rosalia Santoleri, and Bruno Buongiorno Nardelli
Earth Syst. Sci. Data, 14, 4111–4128, https://doi.org/10.5194/essd-14-4111-2022, https://doi.org/10.5194/essd-14-4111-2022, 2022
Short summary
Short summary
A new operational diurnal sea surface temperature (SST) product has been developed within the Copernicus Marine Service, providing gap-free hourly mean SST fields from January 2019 to the present. This product is able to accurately reproduce the diurnal cycle, the typical day–night SST oscillation mainly driven by solar heating, including extreme diurnal warming events. This product can thus represent a valuable dataset to improve the study of those processes that require a subdaily frequency.
Bruno Buongiorno Nardelli
Earth Syst. Sci. Data, 12, 1711–1723, https://doi.org/10.5194/essd-12-1711-2020, https://doi.org/10.5194/essd-12-1711-2020, 2020
Short summary
Short summary
To better understand ocean dynamics and assess their responses and feedbacks to natural and anthropogenic pressures, 3D ocean circulation estimates are needed. Here we present the OMEGA3D product, an observation-based time series (1993–2018) of global 3D ocean currents developed within the European Copernicus Marine Environment Monitoring Service. OMEGA3D provides vertical velocities – an observational barrier due to their small intensity – and full horizontal velocities down to 1500 m depth.
Related subject area
Approach: Remote Sensing | Properties and processes: Mesoscale to submesoscale dynamics
MAESSTRO: Masked Autoencoders for Sea Surface Temperature Reconstruction under Occlusion
Multiple time-scale variations of fronts in the Seto Inland Sea, Japan
Blending 2D topography images from SWOT into the altimeter constellation with the Level-3 multi-mission DUACS system
Monitoring the coastal-offshore water interactions in the Levantine Sea using ocean color and deep supervised learning
Impact of surface and subsurface-intensified eddies on sea surface temperature and chlorophyll a in the northern Indian Ocean utilizing deep learning
Regional mapping of energetic short mesoscale ocean dynamics from altimetry: performances from real observations
Ocean 2D eddy energy fluxes from small mesoscale processes with SWOT
Edwin Goh, Alice Yepremyan, Jinbo Wang, and Brian Wilson
Ocean Sci., 20, 1309–1323, https://doi.org/10.5194/os-20-1309-2024, https://doi.org/10.5194/os-20-1309-2024, 2024
Short summary
Short summary
An AI model was used to fill in missing parts of sea temperature (SST) maps caused by cloud cover. We found masked autoencoders can recreate missing SSTs with less than 0.2 °C error, even when 80 % are missing. This is 5000 times faster than conventional methods tested on a single central processing unit. This can enhance our ability in monitoring global small-scale ocean fronts that affect heat, carbon, and nutrient exchange in the ocean. The method is promising for future research.
Menghong Dong and Xinyu Guo
EGUsphere, https://doi.org/10.5194/egusphere-2024-1667, https://doi.org/10.5194/egusphere-2024-1667, 2024
Short summary
Short summary
We employed a gradient-based algorithm to identify the position and intensity of the fronts in a coastal sea using sea surface temperature data, thereby quantifying their variations. Our study provides a comprehensive analysis of these fronts, elucidating their seasonal variability, intra-tidal dynamics, and the influence of winds on the fronts. By capturing the temporal and spatial dynamics of these fronts, it enhances our understanding of the complex oceanographic processes within this region.
Gerald Dibarboure, Cécile Anadon, Frédéric Briol, Emeline Cadier, Robin Chevrier, Antoine Delepoulle, Yannice Faugère, Alice Laloue, Rosemary Morrow, Nicolas Picot, Pierre Prandi, Marie-Isabelle Pujol, Matthias Raynal, Anaelle Treboutte, and Clément Ubelmann
EGUsphere, https://doi.org/10.5194/egusphere-2024-1501, https://doi.org/10.5194/egusphere-2024-1501, 2024
Short summary
Short summary
The Surface Water and Ocean Topography (SWOT) mission delivers unprecedented swath altimetry products. In this paper, we describe how we extended the Level-3 algorithms to handle SWOT’s unique swath-altimeter data. We also illustrate and discuss the benefits, relevance, and limitations of Level-3 swath-altimeter products for various research domains.
Georges Baaklini, Julien Brajard, Leila Issa, Gina Fifani, Laurent Mortier, and Roy El Hourany
EGUsphere, https://doi.org/10.5194/egusphere-2024-1168, https://doi.org/10.5194/egusphere-2024-1168, 2024
Short summary
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.
Yingjie Liu and Xiaofeng Li
Ocean Sci., 19, 1579–1593, https://doi.org/10.5194/os-19-1579-2023, https://doi.org/10.5194/os-19-1579-2023, 2023
Short summary
Short summary
The study developed a deep learning model that effectively distinguishes between surface- and subsurface-intensified eddies in the northern Indian Ocean by integrating sea surface height and temperature data. The accurate distinction between these types of eddies provides valuable insights into their dynamics and their impact on marine ecosystems in the northern Indian Ocean and contributes to understanding the complex interactions between eddy dynamics and biogeochemical processes in the ocean.
Florian Le Guillou, Lucile Gaultier, Maxime Ballarotta, Sammy Metref, Clément Ubelmann, Emmanuel Cosme, and Marie-Helène Rio
Ocean Sci., 19, 1517–1527, https://doi.org/10.5194/os-19-1517-2023, https://doi.org/10.5194/os-19-1517-2023, 2023
Short summary
Short summary
Altimetry provides sea surface height (SSH) data along one-dimensional tracks. For many applications, the tracks are interpolated in space and time to provide gridded SSH maps. The operational SSH gridded products filter out the small-scale signals measured on the tracks. This paper evaluates the performances of a recently implemented dynamical method to retrieve the small-scale signals from real SSH data. We show a net improvement in the quality of SSH maps when compared to independent data.
Elisa Carli, Rosemary Morrow, Oscar Vergara, Robin Chevrier, and Lionel Renault
Ocean Sci., 19, 1413–1435, https://doi.org/10.5194/os-19-1413-2023, https://doi.org/10.5194/os-19-1413-2023, 2023
Short summary
Short summary
Oceanic eddies are the structures carrying most of the energy in our oceans. They are key to climate regulation and nutrient transport. We prepare for the Surface Water and Ocean Topography mission, studying eddy dynamics in the region south of Africa, where the Indian and Atlantic oceans meet, using models and simulated satellite data. SWOT will provide insights into the structures smaller than what is currently observable, which appear to greatly contribute to eddy kinetic energy and strain.
Cited articles
Balado, J., Olabarria, C., Martínez-Sánchez, J., Rodríguez-Pérez, J. R., and Pedro, A.: Semantic segmentation of major macroalgae in coastal environments using high-resolution ground imagery and deep learning, Int. J. Remote Sens., 42, 1785–1800, 2021. a
Ballarotta, M., Ubelmann, C., Pujol, M.-I., Taburet, G., Fournier, F., Legeais, J.-F., Faugère, Y., Delepoulle, A., Chelton, D., Dibarboure, G., and Picot, N.: On the resolutions of ocean altimetry maps, Ocean Sci., 15, 1091–1109, https://doi.org/10.5194/os-15-1091-2019, 2019. a
Bolton, T. and Zanna, L.: Applications of deep learning to ocean data inference and subgrid parameterization, J. Adv. Model. Earth Sy., 11, 376–399, 2019. a
Bowen, M. M., Emery, W. J., Wilkin, J. L., Tildesley, P. C., Barton, I. J., and Knewtson, R.: Extracting multiyear surface currents from sequential thermal imagery using the maximum cross-correlation technique, J. Atmos. Ocean. Tech., 19, 1665–1676, 2002. a
Bretherton, F. P., Davis, R. E., and Fandry, C.: A technique for objective analysis and design of oceanographic experiments applied to MODE-73, Deep Sea Res., 23, 559–582, 1976. a
Castro, S. L., Emery, W. J., Wick, G. A., and Tandy, W.: Submesoscale sea surface temperature variability from UAV and satellite measurements, Remote Sens.-Basel, 9, 1089, https://doi.org/10.3390/rs9111089, 2017. a
Chang, Y. and Cornillon, P.: A comparison of satellite-derived sea surface temperature fronts using two edge detection algorithms, Deep-Sea Res. Pt. II, 119, 40–47, 2015. a
Ciani, D., Rio, M.-H., Nardelli, B. B., Etienne, H., and Santoleri, R.: Improving the altimeter-derived surface currents using sea surface temperature (SST) data: A sensitivity study to SST products, Remote Sens.-Basel, 12, 1601, https://doi.org/10.3390/rs12101601, 2020. a, b
Coppo, P., Brandani, F., Faraci, M., Sarti, F., Dami, M., Chiarantini, L., Ponticelli, B., Giunti, L., Fossati, E., and Cosi, M.: Leonardo spaceborne infrared payloads for Earth observation: SLSTRs for Copernicus Sentinel 3 and PRISMA hyperspectral camera for PRISMA satellite, Appl. Optics, 59, 6888–6901, 2020. a
Cui, B., Zhang, H., Jing, W., Liu, H., and Cui, J.: SRSe-net: Super-resolution-based semantic segmentation network for green tide extraction, Remote Sens.-Basel, 14, 710, https://doi.org/10.3390/rs14030710, 2022. a
Deo, M. and Naidu, C. S.: Real time wave forecasting using neural networks, Ocean Eng., 26, 191–203, 1998. a
Deser, C., Alexander, M. A., Xie, S.-P., and Phillips, A. S.: Sea surface temperature variability: Patterns and mechanisms, Annu. Rev. Mar. Sci., 2, 115–143, 2010. a
Dong, C., Liu, L., Nencioli, F., Bethel, B. J., Liu, Y., Xu, G., Ma, J., Ji, J., Sun, W., Shan, H., Lin, X., and Zou, B.: The near-global ocean mesoscale eddy atmospheric-oceanic-biological interaction observational dataset, Scientific Data, 9, 436, https://doi.org/10.1038/s41597-022-01550-9, 2022a. 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, 2022b. a
Ducournau, A. and Fablet, R.: Deep learning for ocean remote sensing: an application of convolutional neural networks for super-resolution on satellite-derived SST data, in: 2016 9th IAPR Workshop on Pattern Recogniton in Remote Sensing (PRRS), 4 December 2016, Cancun, Mexico, IEEE, 1–6, https://doi.org/10.1109/PRRS.2016.7867019, 2016. a
Duo, Z., Wang, W., and Wang, H.: Oceanic mesoscale eddy detection method based on deep learning, Remote Sens.-Basel, 11, 1921, https://doi.org/10.3390/rs11161921, 2019. a
European Union-Copernicus Marine Service: Mediterranean Sea High Resolution and Ultra High Resolution Sea Surface Temperature Analysis, Mercator Ocean International [data set], https://doi.org/10.48670/moi-00172, 2008. a
Fablet, R., Amar, 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, 3, 295–302, 2021. a
Fablet, R., Febvre, Q., and Chapron, B.: Multimodal 4DVarNets for the reconstruction of sea surface dynamics from SST-SSH synergies, IEEE T. Geosci. Remote, IEEE Transactions on Geoscience and Remote Sensing, 61, 1–14, 2023. a
Ghiasi, G., Lin, T.-Y., and Le, Q. V.: Dropblock: A regularization method for convolutional networks, Adv. Neur. In., 31, https://doi.org/10.48550/arXiv.1810.12890, 2018. a
González-Haro, C. and Isern-Fontanet, J.: Global ocean current reconstruction from altimetric and microwave SST measurements, J. Geophys. Res.-Oceans, 119, 3378–3391, 2014. a
Goodfellow, I., Bengio, Y., and Courville, A.: Deep learning, MIT Press, ISBN: 9780262035613, 2016. a
Ham, Y.-G., Kim, J.-H., and Luo, J.-J.: Deep learning for multi-year ENSO forecasts, Nature, 573, 568–572, 2019. a
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 27–30 June 2016, Las Vegas, NV, USA, IEEE, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016. a
Hu, J., Shen, L., and Sun, G.: Squeeze-and-excitation networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 18–23 June 2018, Salt Lake City, UT, USA, IEEE, 7132–7141, https://doi.org/10.1109/CVPR.2018.00745, 2018. a
Isern-Fontanet, J., Chapron, B., Lapeyre, G., and Klein, P.: Potential use of microwave sea surface temperatures for the estimation of ocean currents, Geophys. Res. Lett., 33, L24608, 2006. a
Jha, B., Hu, Z.-Z., and Kumar, A.: SST and ENSO variability and change simulated in historical experiments of CMIP5 models, Clim. Dynam., 42, 2113–2124, 2014. a
Kim, J., Lee, J. K., and Lee, K. M.: Accurate image super-resolution using very deep convolutional networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1646–1654, 2016a. a
Kim, J., Lee, J. K., and Lee, K. M.: Deeply-recursive convolutional network for image super-resolution, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 27–30 June 2016, Las Vegas, NV, USA, IEEE, 1637–1645, https://doi.org/10.1109/CVPR.2016.181, 2016b. a
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, arXiv [preprint], arXiv:1412.6980, 2014. a
Krasnopolsky, V. M., Fox-Rabinovitz, M. S., and Belochitski, A. A.: Using ensemble of neural networks to learn stochastic convection parameterizations for climate and numerical weather prediction models from data simulated by a cloud resolving model, Advances in Artificial Neural Systems, 2013, 5–5, 2013. a
Kurkin, A., Kurkina, O., Rybin, A., and Talipova, T.: Comparative analysis of the first baroclinic Rossby radius in the Baltic, Black, Okhotsk, and Mediterranean seas, Russ. J. Earth Sci., 20, ES4008-4008, https://doi.org/10.2205/2020ES000737, 2020. a, b
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, 22–27 July 2018, Valencia, Spain, IEEE, 1764–1767, https://doi.org/10.1109/IGARSS.2018.8518411, 2018. a
Liberti, G. L., Sabatini, M., Wethey, D. S., and Ciani, D.: A Multi-Pixel Split-Window Approach to Sea Surface Temperature Retrieval from Thermal Imagers with Relatively High Radiometric Noise: Preliminary Studies, Remote Sens.-Basel, 15, 2453, https://doi.org/10.3390/rs15092453, 2023. a
Lim, B., Son, S., Kim, H., Nah, S., and Mu Lee, K.: Enhanced deep residual networks for single image super-resolution, in: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 21–26 July 2017, Honolulu, HI, USA, IEEE, 136–144, https://doi.org/10.1109/CVPRW.2017.151, 2017. a, b, c, d
Lloyd, D. T., Abela, A., Farrugia, R. A., Galea, A., and Valentino, G.: Optically enhanced super-resolution of sea surface temperature using deep learning, IEEE T. Geosci. Remote, 60, 1–14, 2021. a
MacKenzie, B. R. and Schiedek, D.: Long-term sea surface temperature baselines—time series, spatial covariation and implications for biological processes, J. Marine Syst., 68, 405–420, 2007. a
Maloney, E. D. and Chelton, D. B.: An assessment of the sea surface temperature influence on surface wind stress in numerical weather prediction and climate models, J. Climate, 19, 2743–2762, 2006. a
Meng, Y., Rigall, E., Chen, X., Gao, F., Dong, J., and Chen, S.: Physics-guided generative adversarial networks for sea subsurface temperature prediction, IEEE T. Neur. Net. Lear., 34, 3357–3370, https://doi.org/10.1109/TNNLS.2021.3123968, 2021. a
Minnett, P., Alvera-Azcárate, A., Chin, T., Corlett, G., Gentemann, C., Karagali, I., Li, X., Marsouin, A., Marullo, S., Maturi, E., Santoleri, R., Saux Picart, S., Steele, M., and Vazquez-Cuervo, J.: Half a century of satellite remote sensing of sea-surface temperature, Remote Sens. Environ., 233, 111366, 2019. a
Mohan, A. T., Lubbers, N., Livescu, D., and Chertkov, M.: Embedding hard physical constraints in neural network coarse-graining of 3D turbulence, arXiv [preprint], arXiv:2002.00021, 2020. a
Pearson, K., Good, S., Merchant, C. J., Prigent, C., Embury, O., and Donlon, C.: Sea surface temperature in global analyses: Gains from the Copernicus Imaging Microwave Radiometer, Remote Sens.-Basel, 11, 2362, https://doi.org/10.3390/rs11202362, 2019. a
Pisano, A., Marullo, S., Artale, V., Falcini, F., Yang, C., Leonelli, F. E., Santoleri, R., and Buongiorno Nardelli, B.: New evidence of Mediterranean climate change and variability from sea surface temperature observations, Remote Sens.-Basel, 12, 132, https://doi.org/10.3390/rs12010132, 2020. a
Rio, M.-H., Santoleri, R., Bourdalle-Badie, R., Griffa, A., Piterbarg, L., and Taburet, G.: Improving the altimeter-derived surface currents using high-resolution sea surface temperature data: a feasability study based on model outputs, J. Atmos. Ocean. Tech., 33, 2769–2784, 2016. a
Singha, S., Bellerby, T. J., and Trieschmann, O.: Satellite oil spill detection using artificial neural networks, IEEE J. Sel. Top. Appl., 6, 2355–2363, 2013. a
Wang, Z., Bovik, A. C., Sheikh, H. R., and Simoncelli, E. P.: Image quality assessment: from error visibility to structural similarity, IEEE T. Image Process., 13, 600–612, 2004. a
Warner, T. T., Lakhtakia, M. N., Doyle, J. D., and Pearson, R. A.: Marine atmospheric boundary layer circulations forced by Gulf Stream sea surface temperature gradients, Mon. Weather Rev., 118, 309–323, 1990. a
Woollings, T., Hoskins, B., Blackburn, M., Hassell, D., and Hodges, K.: Storm track sensitivity to sea surface temperature resolution in a regional atmosphere model, Clim. Dynam., 35, 341–353, 2010. a
Yang, C., Leonelli, F. E., Marullo, S., Artale, V., Beggs, H., Buongiorno Nardelli, B., Chin, T. M., De Toma, V., Good, S., Huang, B., Merchant, C. J., Sakurai, T., Santoleri, R., Vazquez-Cuervo, J., Zhang, H.-M., and Pisano, A.: Sea surface temperature intercomparison in the framework of the Copernicus Climate Change Service (C3S), J. Climate, 34, 5257–5283, 2021. a
Zanna, L. and Bolton, T.: Data-driven equation discovery of ocean mesoscale closures, Geophys. Res. Lett., 47, e2020GL088376, https://doi.org/10.1029/2020GL088376, 2020. a
Zanna, L., Brankart, J., Huber, M., Leroux, S., Penduff, T., and Williams, P.: Uncertainty and scale interactions in ocean ensembles: From seasonal forecasts to multidecadal climate predictions, Q. J. Roy. Meteor. Soc., 145, 160–175, 2019. a
Short summary
Sea surface temperature (SST) is an essential variable to understanding the Earth's climate system, and its accurate monitoring from space is essential. Since satellite measurements are hindered by cloudy/rainy conditions, data gaps are present even in merged multi-sensor products. Since optimal interpolation techniques tend to smooth out small-scale features, we developed a deep learning model to enhance the effective resolution of gap-free SST images over the Mediterranean Sea to address this.
Sea surface temperature (SST) is an essential variable to understanding the Earth's climate...