Articles | Volume 20, issue 2
https://doi.org/10.5194/os-20-417-2024
© 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-20-417-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
22 Mar 2024
Research article |
| 22 Mar 2024
| 22 Mar 2024
Machine learning methods to predict sea surface temperature and marine heatwave occurrence: a case study of the Mediterranean Sea
CMCC Foundation – Euro-Mediterranean Center on Climate Change, Bologna, Italy
Giuliano Galimberti
Department of Statistical Sciences, University of Bologna, Bologna, Italy
Simona Masina
CMCC Foundation – Euro-Mediterranean Center on Climate Change, Bologna, Italy
Ronan McAdam
CMCC Foundation – Euro-Mediterranean Center on Climate Change, Bologna, Italy
Emanuela Clementi
CMCC Foundation – Euro-Mediterranean Center on Climate Change, Bologna, Italy
Related authors
Ronan McAdam, Giulia Bonino, Emanuela Clementi, and Simona Masina
State Planet Discuss., https://doi.org/10.5194/sp-2023-22, https://doi.org/10.5194/sp-2023-22, 2023
Revised manuscript accepted for SP
Short summary
Short summary
In the summer of 2022, a regional short-term forecasting system was able to predict the onset, spread, peaks and decay of a record-breaking marine heatwave in the Mediterranean Sea, up to 10 days in advance. Satellite data shows that the event was record-breaking in terms of basin-wide intensity and duration. This study demonstrates the potential of state-of-the-art forecasting systems to provide early-warning of marine heatwaves to marine activities (e.g. conservation and aquaculture).
Dimitra Denaxa, Gerasimos Korres, Giulia Bonino, Simona Masina, and Maria Hatzaki
State Planet Discuss., https://doi.org/10.5194/sp-2023-24, https://doi.org/10.5194/sp-2023-24, 2023
Preprint under review for SP
Short summary
Short summary
This study investigates air-sea heat fluxes during marine heatwaves (MHWs) in the Mediterranean Sea. Surface fluxes drive 44 % of the onset and only 17 % of the decline phases of MHWs, suggesting a key role of oceanic processes. Heat fluxes are more important in warmer months and onset phases, with the latent heat dominating. Shorter events show weaker heat flux contribution. In most cases, mixed layer shoaling occurs over the entire MHW duration, followed by vertical mixing after the MHW end day.
Giulia Bonino, Simona Masina, Giuliano Galimberti, and Matteo Moretti
Earth Syst. Sci. Data, 15, 1269–1285, https://doi.org/10.5194/essd-15-1269-2023, https://doi.org/10.5194/essd-15-1269-2023, 2023
Short summary
Short summary
We present a unique observational dataset of marine heat wave (MHW) macroevents and their characteristics over southern Europe and western Asian (SEWA) basins in the SEWA-MHW dataset. This dataset is the first effort in the literature to archive extremely hot sea surface temperature macroevents. The advantages of the availability of SEWA-MHWs are avoiding the waste of computational resources to detect MHWs and building a consistent framework which would increase comparability among MHW studies.
Giulia Bonino, Doroteaciro Iovino, Laurent Brodeau, and Simona Masina
Geosci. Model Dev., 15, 6873–6889, https://doi.org/10.5194/gmd-15-6873-2022, https://doi.org/10.5194/gmd-15-6873-2022, 2022
Short summary
Short summary
The sea surface temperature (SST) is highly influenced by the transfer of energy driven by turbulent air–sea fluxes (TASFs). In the NEMO ocean general circulation model, TASFs are computed by means of bulk formulas. Bulk formulas require the choice of a given bulk parameterization, which influences the magnitudes of the TASFs. Our results show that parameterization-related SST differences are primarily sensitive to the wind stress differences across parameterizations.
Giulia Bonino, Elisa Lovecchio, Nicolas Gruber, Matthias Münnich, Simona Masina, and Doroteaciro Iovino
Biogeosciences, 18, 2429–2448, https://doi.org/10.5194/bg-18-2429-2021, https://doi.org/10.5194/bg-18-2429-2021, 2021
Short summary
Short summary
Seasonal variations of processes such as upwelling and biological production that happen along the northwestern African coast can modulate the temporal variability of the biological activity of the adjacent open North Atlantic hundreds of kilometers away from the coast thanks to the lateral transport of coastal organic carbon. This happens with a temporal delay, which is smaller than a season up to roughly 500 km from the coast due to the intense transport by small-scale filaments.
Siren Rühs, Ton van den Bremer, Emanuela Clementi, Michael C. Denes, Aimie Moulin, and Erik van Sebille
EGUsphere, https://doi.org/10.5194/egusphere-2024-1002, https://doi.org/10.5194/egusphere-2024-1002, 2024
Short summary
Short summary
Simulating the transport of floating particles on the ocean surface is crucial for solving many societal issues. Here, we investigate how the representation of wind-generated surface waves impacts particle transport simulations. We find that different wave-driven processes can alter the transport patterns, and that commonly adopted approximations are not always adequate. This implies that ideally coupled ocean-wave models should be used for surface particle transport simulations.
Doroteaciro Iovino, Pier Giuseppe Fogli, and Simona Masina
Geosci. Model Dev., 16, 6127–6159, https://doi.org/10.5194/gmd-16-6127-2023, https://doi.org/10.5194/gmd-16-6127-2023, 2023
Short summary
Short summary
This paper describes the model performance of three global ocean–sea ice configurations, from non-eddying (1°) to eddy-rich (1/16°) resolutions. Model simulations are obtained following the Ocean Model Intercomparison Project phase 2 (OMIP2) protocol. We compare key global climate variables across the three models and against observations, emphasizing the relative advantages and disadvantages of running forced ocean–sea ice models at higher resolution.
Giovanni Coppini, Emanuela Clementi, Gianpiero Cossarini, Stefano Salon, Gerasimos Korres, Michalis Ravdas, Rita Lecci, Jenny Pistoia, Anna Chiara Goglio, Massimiliano Drudi, Alessandro Grandi, Ali Aydogdu, Romain Escudier, Andrea Cipollone, Vladyslav Lyubartsev, Antonio Mariani, Sergio Cretì, Francesco Palermo, Matteo Scuro, Simona Masina, Nadia Pinardi, Antonio Navarra, Damiano Delrosso, Anna Teruzzi, Valeria Di Biagio, Giorgio Bolzon, Laura Feudale, Gianluca Coidessa, Carolina Amadio, Alberto Brosich, Arnau Miró, Eva Alvarez, Paolo Lazzari, Cosimo Solidoro, Charikleia Oikonomou, and Anna Zacharioudaki
Ocean Sci., 19, 1483–1516, https://doi.org/10.5194/os-19-1483-2023, https://doi.org/10.5194/os-19-1483-2023, 2023
Short summary
Short summary
The paper presents the Mediterranean Forecasting System evolution and performance developed in the framework of the Copernicus Marine Service.
Bethany McDonagh, Emanuela Clementi, Anna Chiara Goglio, and Nadia Pinardi
EGUsphere, https://doi.org/10.5194/egusphere-2023-2251, https://doi.org/10.5194/egusphere-2023-2251, 2023
Short summary
Short summary
Tides in the Mediterranean Sea are typically of low amplitude, but twin experiments using numerical models with and without tides demonstrates that tides affect the circulation on temporal and spatial scales away from those of the tides directly. Tides enhance existing oscillations, and increase the upper layer salinity. Tides are also found to increase the mixed layer depth and enhance dense water formation in key regions. Internal tides are found to be widespread in the Mediterranean Sea.
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 Discuss., https://doi.org/10.5194/sp-2023-30, https://doi.org/10.5194/sp-2023-30, 2023
Revised manuscript under review for SP
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 associated transport of nutrient to the surface. Southeast of Crete the availability of both light and nutrient 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 fish catches.
Ali Aydogdu, Pietro Miraglio, Romain Escudier, Emanuela Clementi, and Simona Masina
State Planet, 1-osr7, 6, https://doi.org/10.5194/sp-1-osr7-6-2023, https://doi.org/10.5194/sp-1-osr7-6-2023, 2023
Short summary
Short summary
This paper investigates the salt content, salinity anomaly and trend in the Mediterranean Sea using observational and reanalysis products. The salt content increases overall, while negative salinity anomalies appear in the western basin, especially around the upwelling regions. There is a large spread in the salinity estimates that is reduced with the emergence of the Argo profilers.
Stefania A. Ciliberti, Enrique Alvarez Fanjul, Jay Pearlman, Kirsten Wilmer-Becker, Pierre Bahurel, Fabrice Ardhuin, Alain Arnaud, Mike Bell, Segolene Berthou, Laurent Bertino, Arthur Capet, Eric Chassignet, Stefano Ciavatta, Mauro Cirano, Emanuela Clementi, Gianpiero Cossarini, Gianpaolo Coro, Stuart Corney, Fraser Davidson, Marie Drevillon, Yann Drillet, Renaud Dussurget, Ghada El Serafy, Katja Fennel, Marcos Garcia Sotillo, Patrick Heimbach, Fabrice Hernandez, Patrick Hogan, Ibrahim Hoteit, Sudheer Joseph, Simon Josey, Pierre-Yves Le Traon, Simone Libralato, Marco Mancini, Pascal Matte, Angelique Melet, Yasumasa Miyazawa, Andrew M. Moore, Antonio Novellino, Andrew Porter, Heather Regan, Laia Romero, Andreas Schiller, John Siddorn, Joanna Staneva, Cecile Thomas-Courcoux, Marina Tonani, Jose Maria Garcia-Valdecasas, Jennifer Veitch, Karina von Schuckmann, Liying Wan, John Wilkin, and Romane Zufic
State Planet, 1-osr7, 2, https://doi.org/10.5194/sp-1-osr7-2-2023, https://doi.org/10.5194/sp-1-osr7-2-2023, 2023
Andrea Cipollone, Deep Sankar Banerjee, Doroteaciro Iovino, Ali Aydogdu, and Simona Masina
Ocean Sci., 19, 1375–1392, https://doi.org/10.5194/os-19-1375-2023, https://doi.org/10.5194/os-19-1375-2023, 2023
Short summary
Short summary
Sea-ice volume is characterized by low predictability compared to the sea ice area or the extent. A joint initialization of the thickness and concentration using satellite data could improve the predictive power, although it is still absent in the present global analysis–reanalysis systems. This study shows a scheme to correct the two features together that can be easily extended to include ocean variables. The impact of such a joint initialization is shown and compared among different set-ups.
Elena Bianco, Doroteaciro Iovino, Simona Masina, Stefano Materia, and Paolo Ruggieri
EGUsphere, https://doi.org/10.5194/egusphere-2023-1406, https://doi.org/10.5194/egusphere-2023-1406, 2023
Short summary
Short summary
Changes in ocean heat transport and surface heat fluxes in recent decades have altered the Arctic Ocean heat budget and caused warming of the upper ocean. Using two eddy-permitting ocean reanalyses, we show that this has important implications for sea ice variability. In the Arctic regional seas, upper ocean heat content acts as an important precursor for sea ice anomalies on sub-seasonal time scales and this link has strengthened since the 2000s.
Ronan McAdam, Giulia Bonino, Emanuela Clementi, and Simona Masina
State Planet Discuss., https://doi.org/10.5194/sp-2023-22, https://doi.org/10.5194/sp-2023-22, 2023
Revised manuscript accepted for SP
Short summary
Short summary
In the summer of 2022, a regional short-term forecasting system was able to predict the onset, spread, peaks and decay of a record-breaking marine heatwave in the Mediterranean Sea, up to 10 days in advance. Satellite data shows that the event was record-breaking in terms of basin-wide intensity and duration. This study demonstrates the potential of state-of-the-art forecasting systems to provide early-warning of marine heatwaves to marine activities (e.g. conservation and aquaculture).
Dimitra Denaxa, Gerasimos Korres, Giulia Bonino, Simona Masina, and Maria Hatzaki
State Planet Discuss., https://doi.org/10.5194/sp-2023-24, https://doi.org/10.5194/sp-2023-24, 2023
Preprint under review for SP
Short summary
Short summary
This study investigates air-sea heat fluxes during marine heatwaves (MHWs) in the Mediterranean Sea. Surface fluxes drive 44 % of the onset and only 17 % of the decline phases of MHWs, suggesting a key role of oceanic processes. Heat fluxes are more important in warmer months and onset phases, with the latent heat dominating. Shorter events show weaker heat flux contribution. In most cases, mixed layer shoaling occurs over the entire MHW duration, followed by vertical mixing after the MHW end day.
Leonardo Lima, Salvatore Causio, Mehmet Ilicak, Ronan McAdam, and Eric Jansen
State Planet Discuss., https://doi.org/10.5194/sp-2023-19, https://doi.org/10.5194/sp-2023-19, 2023
Revised manuscript not accepted
Short summary
Short summary
Recent studies have revealed an increase in the ocean temperature and heat content in the Black Sea, where the research on marine heat waves (MHWs) is still incipient. Our study reveals long-lasting MHWs and interesting connections between surface and subsurface MHWs in the Black Sea. Our analysis is a starting point to create a monitoring system of MHWs for the Black Sea.
Giulia Bonino, Simona Masina, Giuliano Galimberti, and Matteo Moretti
Earth Syst. Sci. Data, 15, 1269–1285, https://doi.org/10.5194/essd-15-1269-2023, https://doi.org/10.5194/essd-15-1269-2023, 2023
Short summary
Short summary
We present a unique observational dataset of marine heat wave (MHW) macroevents and their characteristics over southern Europe and western Asian (SEWA) basins in the SEWA-MHW dataset. This dataset is the first effort in the literature to archive extremely hot sea surface temperature macroevents. The advantages of the availability of SEWA-MHWs are avoiding the waste of computational resources to detect MHWs and building a consistent framework which would increase comparability among MHW studies.
Giulia Bonino, Doroteaciro Iovino, Laurent Brodeau, and Simona Masina
Geosci. Model Dev., 15, 6873–6889, https://doi.org/10.5194/gmd-15-6873-2022, https://doi.org/10.5194/gmd-15-6873-2022, 2022
Short summary
Short summary
The sea surface temperature (SST) is highly influenced by the transfer of energy driven by turbulent air–sea fluxes (TASFs). In the NEMO ocean general circulation model, TASFs are computed by means of bulk formulas. Bulk formulas require the choice of a given bulk parameterization, which influences the magnitudes of the TASFs. Our results show that parameterization-related SST differences are primarily sensitive to the wind stress differences across parameterizations.
Marco Reale, Gianpiero Cossarini, Paolo Lazzari, Tomas Lovato, Giorgio Bolzon, Simona Masina, Cosimo Solidoro, and Stefano Salon
Biogeosciences, 19, 4035–4065, https://doi.org/10.5194/bg-19-4035-2022, https://doi.org/10.5194/bg-19-4035-2022, 2022
Short summary
Short summary
Future projections under the RCP8.5 and RCP4.5 emission scenarios of the Mediterranean Sea biogeochemistry at the end of the 21st century show different levels of decline in nutrients, oxygen and biomasses and an acidification of the water column. The signal intensity is stronger under RCP8.5 and in the eastern Mediterranean. Under RCP4.5, after the second half of the 21st century, biogeochemical variables show a recovery of the values observed at the beginning of the investigated period.
Amy Solomon, Céline Heuzé, Benjamin Rabe, Sheldon Bacon, Laurent Bertino, Patrick Heimbach, Jun Inoue, Doroteaciro Iovino, Ruth Mottram, Xiangdong Zhang, Yevgeny Aksenov, Ronan McAdam, An Nguyen, Roshin P. Raj, and Han Tang
Ocean Sci., 17, 1081–1102, https://doi.org/10.5194/os-17-1081-2021, https://doi.org/10.5194/os-17-1081-2021, 2021
Short summary
Short summary
Freshwater in the Arctic Ocean plays a critical role in the global climate system by impacting ocean circulations, stratification, mixing, and emergent regimes. In this review paper we assess how Arctic Ocean freshwater changed in the 2010s relative to the 2000s. Estimates from observations and reanalyses show a qualitative stabilization in the 2010s due to a compensation between a freshening of the Beaufort Gyre and a reduction in freshwater in the Amerasian and Eurasian basins.
Giulia Bonino, Elisa Lovecchio, Nicolas Gruber, Matthias Münnich, Simona Masina, and Doroteaciro Iovino
Biogeosciences, 18, 2429–2448, https://doi.org/10.5194/bg-18-2429-2021, https://doi.org/10.5194/bg-18-2429-2021, 2021
Short summary
Short summary
Seasonal variations of processes such as upwelling and biological production that happen along the northwestern African coast can modulate the temporal variability of the biological activity of the adjacent open North Atlantic hundreds of kilometers away from the coast thanks to the lateral transport of coastal organic carbon. This happens with a temporal delay, which is smaller than a season up to roughly 500 km from the coast due to the intense transport by small-scale filaments.
Hiroyuki Tsujino, L. Shogo Urakawa, Stephen M. Griffies, Gokhan Danabasoglu, Alistair J. Adcroft, Arthur E. Amaral, Thomas Arsouze, Mats Bentsen, Raffaele Bernardello, Claus W. Böning, Alexandra Bozec, Eric P. Chassignet, Sergey Danilov, Raphael Dussin, Eleftheria Exarchou, Pier Giuseppe Fogli, Baylor Fox-Kemper, Chuncheng Guo, Mehmet Ilicak, Doroteaciro Iovino, Who M. Kim, Nikolay Koldunov, Vladimir Lapin, Yiwen Li, Pengfei Lin, Keith Lindsay, Hailong Liu, Matthew C. Long, Yoshiki Komuro, Simon J. Marsland, Simona Masina, Aleksi Nummelin, Jan Klaus Rieck, Yohan Ruprich-Robert, Markus Scheinert, Valentina Sicardi, Dmitry Sidorenko, Tatsuo Suzuki, Hiroaki Tatebe, Qiang Wang, Stephen G. Yeager, and Zipeng Yu
Geosci. Model Dev., 13, 3643–3708, https://doi.org/10.5194/gmd-13-3643-2020, https://doi.org/10.5194/gmd-13-3643-2020, 2020
Short summary
Short summary
The OMIP-2 framework for global ocean–sea-ice model simulations is assessed by comparing multi-model means from 11 CMIP6-class global ocean–sea-ice models calculated separately for the OMIP-1 and OMIP-2 simulations. Many features are very similar between OMIP-1 and OMIP-2 simulations, and yet key improvements in transitioning from OMIP-1 to OMIP-2 are also identified. Thus, the present assessment justifies that future ocean–sea-ice model development and analysis studies use the OMIP-2 framework.
Verena Haid, Doroteaciro Iovino, and Simona Masina
The Cryosphere, 11, 1387–1402, https://doi.org/10.5194/tc-11-1387-2017, https://doi.org/10.5194/tc-11-1387-2017, 2017
Short summary
Short summary
Since the Antarctic sea ice extent shows a recent increase, we investigate the sea ice response to changed amount and distribution of surface freshwater addition in the Southern Ocean with the ocean–sea ice model NEMO/LIM2. We find that freshwater addition within the range of current estimates increases the ice extent, but higher amounts could have an opposing effect. The freshwater distribution is of great influence on the ice dynamics and the ice thickness is strongly influenced by it.
Vasco M. N. C. S. Vieira, Pavel Jurus, Emanuela Clementi, Heidi Pettersson, and Marcos Mateus
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2016-273, https://doi.org/10.5194/gmd-2016-273, 2016
Revised manuscript has not been submitted
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.
Italo Epicoco, Silvia Mocavero, Francesca Macchia, Marcello Vichi, Tomas Lovato, Simona Masina, and Giovanni Aloisio
Geosci. Model Dev., 9, 2115–2128, https://doi.org/10.5194/gmd-9-2115-2016, https://doi.org/10.5194/gmd-9-2115-2016, 2016
Short summary
Short summary
The present work aims at evaluating the scalability performance of a high-resolution global ocean biogeochemistry model (PELAGOS025) on massive parallel architectures and the benefits in terms of the time-to-solution reduction. The outcome of the analysis demonstrated that the lack of scalability is due to several factors such as the I/O operations, the memory contention, and the load unbalancing due to the memory structure of the biogeochemistry model component.
V. M. N. C. S. Vieira, E. Sahlée, P. Jurus, E. Clementi, H. Pettersson, and M. Mateus
Biogeosciences Discuss., https://doi.org/10.5194/bgd-12-15901-2015, https://doi.org/10.5194/bgd-12-15901-2015, 2015
Manuscript not accepted for further review
V. M. N. C. S. Vieira, E. Sahlée, P. Jurus, E. Clementi, H. Pettersson, and M. Mateus
Biogeosciences Discuss., https://doi.org/10.5194/bgd-12-15925-2015, https://doi.org/10.5194/bgd-12-15925-2015, 2015
Manuscript not accepted for further review
Cited articles
Alvarez Fanjul, E., Ciliberti, S. A., and Bahurel, P.: Implementing Operational Ocean Monitoring and Forecasting Systems, IOC-UNESCO, 376 pp., https://doi.org/10.48670/ETOOFS, 2022. a
Anding, D. and Kauth, R.: Estimation of sea surface temperature from space, Remote Sens. Environ., 1, 217–220, 1970. a
Bonino, G., Galimberti, G., Masina, S., McAdam, R., and Clementi, E.: Machine learning methods to predict Sea Surface Temperature and Marine Heatwave occurrence: a case study of the Mediterranean Sea, Zenodo [code], https://doi.org/10.5281/zenodo.8335345, 2023a. a
Bonino, G., Masina, S., Galimberti, G., and Moretti, M.: Southern Europe and western Asian marine heatwaves (SEWA-MHWs): a dataset based on macroevents, Earth Syst. Sci. Data, 15, 1269–1285, https://doi.org/10.5194/essd-15-1269-2023, 2023b. a
Buizza, C., Casas, C. Q., Nadler, P., Mack, J., Marrone, S., Titus, Z., Le Cornec, C., Heylen, E., Dur, T., Ruiz, L. B., and Heaney, C.: Data learning: Integrating data assimilation and machine learning, J. Comput. Sci., 58, 101525, https://doi.org/10.1016/j.jocs.2021.101525, 2022. a
Carvalho, N. and Guillen, J.: Aquaculture in the Mediterranean, IEMed Mediterr. Yearb, 2021. a
Cavole, L. M., Demko, A. M., Diner, R. E., Giddings, A., Koester, I., Pagniello, C. M., Paulsen, M. L., Ramirez-Valdez, A., Schwenck, S. M., Yen, N. K., and Zill, M. E.: Biological impacts of the 2013–2015 warm-water anomaly in the Northeast Pacific: winners, losers, and the future, Oceanography, 29, 273–285, 2016. a
Chandrapavan, A., Caputi, N., and Kangas, M. I.: The decline and recovery of a crab population from an extreme marine heatwave and a changing climate, Front. Mar. Sci., 6, 510, https://doi.org/10.3389/fmars.2019.00510, 2019. a
Chattopadhyay, A., Nabizadeh, E., and Hassanzadeh, P.: Analog forecasting of extreme-causing weather patterns using deep learning, J. Adv. Model. Earth Sy., 12, e2019MS001958, https://doi.org/10.1029/2019MS001958, 2020. a
Ciappa, A. C.: Effects of Marine Heatwaves (MHW) and Cold Spells (MCS) on the surface warming of the Mediterranean Sea from 1989 to 2018, Prog. Oceanogr., 205, 102828, https://doi.org/10.1016/j.pocean.2022.102828, 2022. a
Clementi, E., Aydogdu, A., Goglio, A.C., Pistoia, J., Escudier, R., Drudi, M., Grandi, A., Mariani, A., Lyubartsev, V., Lecci, R., and Cretí, S.: Mediterranean Sea Physical Analysis and Forecast (CMEMS MED-Currents, EAS6 system) (Version 1), Copernicus Monitoring Environment Marine Service (CMEMS) [data set], 10, https://doi.org/10.25423/CMCC/MEDSEA_ANALYSISFORECAST_PHY_006_013_EAS6, 2021. a, b
Copernicus Climate Change Service (C3S): Sea surface temperature daily data from 1981 to present derived from satellite observations, Copernicus Climate Change Service (C3S) Climate Data Store (CDS) [data set], https://doi.org/10.24381/cds.cf608234, 2019 a
Corchado, J.: Hybrid cbr system for real-time temperature forecasting in the ocean, in: IEEE colloquium on knowledge discovery, London, UK, 1995. a
Cramer, W., Guiot, J., Fader, M., Garrabou, J., Gattuso, J.-P., Iglesias, A., Lange, M. A., Lionello, P., Llasat, M. C., Paz, S., Anukwonke, C. C., Tambe, E. B., Nwafor, D. C., and Malik, K. T.: Climate change and interconnected risks to sustainable development in the Mediterranean, Nat. Clim. Change, 8, 972–980, 2018. a, b
Darmaraki, S., Waldman, R., Sevault, F., and Somot, S.: Dominant drivers of Past Mediterranean Marine Heatwaves, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-13986, https://doi.org/10.5194/egusphere-egu23-13986, 2023. a
Dueben, P. D. and Bauer, P.: Challenges and design choices for global weather and climate models based on machine learning, Geoscientific Model Development, 11, 3999–4009, 2018. a
Garrabou, J., Coma, R., Bensoussan, N., Bally, M., Chevaldonné, P., Cigliano, M., Díaz, D., Harmelin, J. G., Gambi, M. C., Kersting, D. K., and Ledoux, J. B.: Mass mortality in Northwestern Mediterranean rocky benthic communities: effects of the 2003 heat wave, Glob. Change Biol., 15, 1090–1103, 2009. a
Giamalaki, K., Beaulieu, C., and Prochaska, J.: Assessing predictability of marine heatwaves with random forests, Geophys. Res. Lett., 49, e2022GL099069, https://doi.org/10.1029/2022GL099069, 2022. a, b, c
Giorgi, F.: Climate change hot-spots, Geophys. Res. Lett., 33, L08707, https://doi.org/10.1029/2006GL025734, 2006. 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 [data set], https://doi.org/10.5285/62c0f97b1eac4e0197a674870afe1ee6, 2019. a
Guinaldo, T., Voldoire, A., Waldman, R., Saux Picart, S., and Roquet, H.: Response of the sea surface temperature to heatwaves during the France 2022 meteorological summer, Ocean Sci., 19, 629–647, https://doi.org/10.5194/os-19-629-2023, 2023. a
Guo, Y., Zhang, S., Yang, J., Yu, G., and Wang, Y.: Dual memory scale network for multi-step time series forecasting in thermal environment of aquaculture facility: A case study of recirculating aquaculture water temperature, Expert Syst. Appl., 208, 118218, https://doi.org/10.1016/j.eswa.2022.118218, 2022. a
Han, M., Feng, Y., Zhao, X., Sun, C., Hong, F., and Liu, C.: A convolutional neural network using surface data to predict subsurface temperatures in the Pacific Ocean, IEEE Access, 7, 172816–172829, 2019. a
Hersbach, H., Bell, B., Berrisford, P., Biavati, G., Horányi, A., Muñoz Sabater, J., Nicolas, J., Peubey, C., Radu, R., Rozum, I., Schepers, D., Simmons, A., Soci, C., Dee, D., and Thépaut, J.-N.: ERA5 hourly data on single levels from 1940 to present, Copernicus Climate Change Service (C3S) Climate Data Store (CDS) [data set], https://doi.org/10.24381/cds.adbb2d47, 2023. a
Hornik, K.: Approximation capabilities of multilayer feedforward networks, Neural Networks, 4, 251–257, 1991. a
JJacox, M. G., Alexander, M. A., Siedlecki, S., Chen, K., Kwon, Y .O., Brodie, S., Ortiz, I., Tommasi, D., Widlansky, M. J., Barrie, D., and Capotondi, A.: Seasonal-to-interannual prediction of North American coastal marine ecosystems: forecast methods, mechanisms of predictability, and priority developments, Prog. Oceanogr., 183, 102307, https://doi.org/10.1016/j.pocean.2020.102307, 2020. a
Jacques-Dumas, V., Ragone, F., Borgnat, P., Abry, P., and Bouchet, F.: Deep learning-based extreme heatwave forecast, Front. Climate, 4, https://doi.org/10.3389/fclim.2022.789641, 2022. a
Juza, M., Fernández-Mora, À., and Tintoré, J.: Sub-Regional Marine Heat Waves in the Mediterranean Sea From Observations: Long-Term Surface Changes, Sub-Surface and Coastal Responses, Front. Mar. Sci., 9, https://doi.org/10.3389/fmars.2022.785771, 2022. a
Lee, D., Won, K., Park, M., Choi, H., and Jung, S.: An analysis of mass mortalities in aquaculture fish farms on the southern coast in Korea, Ocean Policy Research, 33, 1–16, 2018. a
Leroux, S., Brankart, J.-M., Albert, A., Brodeau, L., Molines, J.-M., Jamet, Q., Le Sommer, J., Penduff, T., and Brasseur, P.: Ensemble quantification of short-term predictability of the ocean dynamics at a kilometric-scale resolution: a Western Mediterranean test case, Ocean Sci., 18, 1619–1644, https://doi.org/10.5194/os-18-1619-2022, 2022. a
Li, X., Liu, B., Zheng, G., Ren, Y., Zhang, S., Liu, Y., Gao, L., Liu, Y., Zhang, B., and Wang, F.: Deep-learning-based information mining from ocean remote-sensing imagery, Natl. Sci. Rev., 7, 1584–1605, 2020. a
Liu, J., Zhang, T., Han, G., and Gou, Y.: TD-LSTM: Temporal dependence-based LSTM networks for marine temperature prediction, Sensors, 18, 3797, https://doi.org/10.3390/s18113797, 2018. a
Madec, G., Delecluse, P., Crepon, M., and Chartier, M.: A three-dimensional numerical study of deep-water formation in the northwestern Mediterranean Sea, J. Phys. Oceanogr., 21, 1349–1371, 1991. a
Marbà, N., Jordà, G., Agusti, S., Girard, C., and Duarte, C. M.: Footprints of climate change on Mediterranean Sea biota, Front. Mar. Sci., 2, https://doi.org/10.3389/fmars.2015.00056, 2015. a
McMillin, L. M.: Estimation of sea surface temperatures from two infrared window measurements with different absorption, J. Geophys. Res., 80, 5113–5117, 1975. a
Oidtmann, B., Thrush, M., Denham, K., and Peeler, E.: International and national biosecurity strategies in aquatic animal health, Aquaculture, 320, 22–33, 2011. a
Pastor, F. and Khodayar, S.: Marine heat waves: Characterizing a major climate impact in the Mediterranean, Sci. Total Environ., 25, 160621, https://doi.org/10.1016/j.scitotenv.2022.160621, 2022. a
Pastor, F., Valiente, J. A., and Khodayar, S.: A warming Mediterranean: 38 years of increasing sea surface temperature, Remote Sens., 12, 2687, https://doi.org/10.3390/rs12172687, 2020. a
Rivetti, I., Fraschetti, S., Lionello, P., Zambianchi, E., and Boero, F.: Global warming and mass mortalities of benthic invertebrates in the Mediterranean Sea, PloS one, 9, e115655, https://doi.org/10.1371/journal.pone.0115655, 2014. a
Rodrigues, R. R., Taschetto, A. S., Sen Gupta, A., and Foltz, G. R.: Common cause for severe droughts in South America and marine heatwaves in the South Atlantic, Nat. Geosci., 12, 620–626, 2019. a
Schlegel, R. W., Oliver, E. C., and Chen, K.: Drivers of marine heatwaves in the Northwest Atlantic: The role of air–sea interaction during onset and decline, Front. Mar. Sci., 8, 627970, https://doi.org/10.3389/fmars.2021.627970, 2021. a, b
Taylor, J. and Feng, M.: A deep learning model for forecasting global monthly mean sea surface temperature anomalies, Front. Climate, 4, https://doi.org/10.3389/fclim.2022.932932, 2022. a
Tran, T. T. K., Bateni, S. M., Ki, S. J., and Vosoughifar, H.: A review of neural networks for air temperature forecasting, Water, 13, 1294, https://doi.org/10.3390/w13091294, 2021. a
Vogt, L., Burger, F. A., Griffies, S. M., and Frölicher, T. L.: Local drivers of marine heatwaves: a global analysis with an earth system model, Front. Climate, 4, https://doi.org/10.3389/fclim.2022.847995, 2022. a
Wei, L. and Guan, L.: Seven-day Sea Surface Temperature Prediction using a 3DConv-LSTM model, Front. Mar. Sci., 9, https://doi.org/10.3389/fmars.2022.905848, 2022. a
Wolff, S., O'Donncha, F., and Chen, B.: Statistical and machine learning ensemble modelling to forecast sea surface temperature, J. Marine Syst., 208, 103347, https://doi.org/10.1016/j.jmarsys.2020.103347, 2020. a
Xiao, C., Chen, N., Hu, C., Wang, K., Gong, J., and Chen, Z.: Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach, Remote Sens. Environ., 233, 111358, https://doi.org/10.1016/j.rse.2019.111358, 2019. a
Xie, J., Zhang, J., Yu, J., and Xu, L.: An adaptive scale sea surface temperature predicting method based on deep learning with attention mechanism, IEEE Geosci. Remote S., 17, 740–744, 2019. a
Zanetta, F., Nerini, D., Beucler, T., and Liniger, M. A.: Physics-constrained deep learning postprocessing of temperature and humidity, Artif. Intell. Earth Syst., 2, e220089, https://doi.org/10.1175/AIES-D-22-0089.1, 2023. a
Short summary
This study employs machine learning to predict marine heatwaves (MHWs) in the Mediterranean Sea. MHWs have far-reaching impacts on society and ecosystems. Using data from ESA and ECMWF, the research develops accurate prediction models for sea surface temperature (SST) and MHWs across the region. Notably, machine learning methods outperform existing forecasting systems, showing promise in early MHW predictions. The study also highlights the importance of solar radiation as a predictor of SST.
This study employs machine learning to predict marine heatwaves (MHWs) in the Mediterranean Sea....
