Articles | Volume 21, issue 3
https://doi.org/10.5194/os-21-897-2025
© Author(s) 2025. 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-21-897-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Marine heatwaves in the Mediterranean Sea: a convolutional neural network study for extreme event prediction
Antonios Parasyris
CORRESPONDING AUTHOR
Foundation for Research and Technology – Hellas, Institute of Applied and Computational Mathematics, 70013 Heraklion, Greece
Vassiliki Metheniti
Foundation for Research and Technology – Hellas, Institute of Applied and Computational Mathematics, 70013 Heraklion, Greece
Nikolaos Kampanis
Foundation for Research and Technology – Hellas, Institute of Applied and Computational Mathematics, 70013 Heraklion, Greece
Sofia Darmaraki
Foundation for Research and Technology – Hellas, Institute of Applied and Computational Mathematics, 70013 Heraklion, Greece
Related authors
No articles found.
Dimitra Denaxa, Gerasimos Korres, Sophia Darmaraki, and Maria Hatzaki
State Planet Discuss., https://doi.org/10.5194/sp-2024-4, https://doi.org/10.5194/sp-2024-4, 2024
Revised manuscript under review for SP
Short summary
Short summary
The Mediterranean Sea experiences a basin-wide increase in sea surface temperature (SST) and extreme SST occurrences. Stronger warming trends are found in the eastern basin where a decrease in SST variability is also observed. Our findings on the origin of marine heatwave (MHW) trends in the basin suggest that the mean SST warming drives the long-term trends for most MHW properties across the basin except for mean MHW intensity, where interannual variability emerges as the dominant driver.
Riccardo Martellucci, Francesco Tiralongo, Sofia F. Darmaraki, Michela D'Alessandro, Giorgio Mancinelli, Emanuele Mancini, Roberto Simonini, Milena Menna, Annunziata Pirro, Diego Borme, Rocco Auriemma, Marco Graziano, and Elena Mauri
State Planet Discuss., https://doi.org/10.5194/sp-2024-16, https://doi.org/10.5194/sp-2024-16, 2024
Revised manuscript under review for SP
Short summary
Short summary
In 2023, global mean air temperatures reached unprecedented highs and the Mediterranean was hit by the longest marine heatwave in four decades. These conditions favored the spread of invasive species affecting fisheries in the central Mediterranean. This study provides new insights into the cascading impacts of climate-driven extreme events on marine ecosystems and fisheries and suggests actionable strategies for dealing with invasive species in a changing climate.
Related subject area
Approach: Numerical Models | Properties and processes: Climate and modes of variability
Ocean wave spectrum bias correction through energy conservation for climate change impacts
A new vision of the Adriatic Dense Water future under extreme warming
Seafloor marine heatwaves outpace surface events in future on the northwest European shelf
Dynamically downscaled seasonal ocean forecasts for North American east coast ecosystems
On the response of the Equatorial Atmosphere and Ocean to changes in Sea Surface Temperature along the Path of the North Equatorial Counter Current
Exploring variability in climate change projections on the Nemunas River and Curonian Lagoon: coupled SWAT and SHYFEM modeling approach
An assessment of equatorial Atlantic interannual variability in Ocean Model Intercomparison Project (OMIP) simulations
Twenty-first century marine climate projections for the NW European shelf seas based on a perturbed parameter ensemble
AdriE: a high-resolution ocean model ensemble for the Adriatic Sea under severe climate change conditions
Predictability of marine heatwaves: assessment based on the ECMWF seasonal forecast system
The Mediterranean Forecasting System – Part 1: Evolution and performance
Andrea Lira Loarca and Giovanni Besio
Ocean Sci., 21, 767–785, https://doi.org/10.5194/os-21-767-2025, https://doi.org/10.5194/os-21-767-2025, 2025
Short summary
Short summary
A new method improves the accuracy of climate models by adjusting wave spectrum simulations in the Mediterranean Sea. It corrects biases and accounts for changes in wave patterns due to climate change, such as shifts in direction and frequency. This technique was applied to multiple climate models, assessing future wave conditions for mid-century and end-of-century scenarios. The results underline the importance of precise corrections for better predicting how waves may evolve as the climate changes.
Cléa Denamiel, Iva Tojčić, and Petra Pranić
Ocean Sci., 21, 37–62, https://doi.org/10.5194/os-21-37-2025, https://doi.org/10.5194/os-21-37-2025, 2025
Short summary
Short summary
We use a high-resolution atmosphere–ocean model to project Adriatic Dense Water dynamics under extreme warming. We find that a 15 % increase in sea surface evaporation will offset a 25 % decrease in extreme windstorms. As a result, future dense water will form at the same rate as today but will be too light to reach the Adriatic's deepest parts, making deep-water presence reliant on exchanges with the Ionian Sea.
Robert J. Wilson, Yuri Artioli, Giovanni Galli, James Harle, Jason Holt, Ana M. Queiros, and Sarah Wakelin
EGUsphere, https://doi.org/10.5194/egusphere-2024-3810, https://doi.org/10.5194/egusphere-2024-3810, 2024
Short summary
Short summary
Marine heatwaves are of growing concern around the world. We use a state of the art ensemble of downscaled climate models to project how often heatwaves will occur in future across northwest Europe under a high-emissions scenario. The projections show that without emissions reductions, heatwaves will occur more than half of the time in future. We show that the seafloor is expected to experience much more frequent heatwaves than the sea surface in future.
Andrew C. Ross, Charles A. Stock, Vimal Koul, Thomas L. Delworth, Feiyu Lu, Andrew Wittenberg, and Michael A. Alexander
Ocean Sci., 20, 1631–1656, https://doi.org/10.5194/os-20-1631-2024, https://doi.org/10.5194/os-20-1631-2024, 2024
Short summary
Short summary
In this paper, we use a high-resolution regional ocean model to downscale seasonal ocean forecasts from the Seamless System for Prediction and EArth System Research (SPEAR) model of the Geophysical Fluid Dynamics Laboratory (GFDL). We find that the downscaled model has significantly higher prediction skill in many cases.
David John Webb
EGUsphere, https://doi.org/10.5194/egusphere-2024-3560, https://doi.org/10.5194/egusphere-2024-3560, 2024
Preprint withdrawn
Short summary
Short summary
A modern climate model is used to test the hypothesis that changes observed during El Niños are, in part, forced by changes in the temperature of the North Equatorial Counter Current. This is a warm current that flows eastwards across the Pacific, a few degrees north of the Equator, close to the Inter-Tropical Convection Zone, a major region of deep atmospheric convection. The tests generate a significant El Niño type response in the ocean, giving confidence that the hypothesis is correct.
Natalja Čerkasova, Jovita Mėžinė, Rasa Idzelytė, Jūratė Lesutienė, Ali Ertürk, and Georg Umgiesser
Ocean Sci., 20, 1123–1147, https://doi.org/10.5194/os-20-1123-2024, https://doi.org/10.5194/os-20-1123-2024, 2024
Short summary
Short summary
This study advances the understanding of climate projection variability in the Nemunas River, Curonian Lagoon, and southeastern Baltic Sea continuum by analyzing a subset of climate models with a focus on a coupled ocean and drainage basin model. This study investigates the variability and trends in environmental parameters, such as water fluxes, timing, nutrient load, water temperature, ice cover, and saltwater intrusions in Representative Concentration Pathway 4.5 and 8.5 scenarios.
Arthur Prigent and Riccardo Farneti
Ocean Sci., 20, 1067–1086, https://doi.org/10.5194/os-20-1067-2024, https://doi.org/10.5194/os-20-1067-2024, 2024
Short summary
Short summary
We evaluate the eastern equatorial Atlantic's (EEA's) seasonal cycle and interannual variability in the Ocean Model Intercomparison Project Phases 1 and 2 (OMIP1 and OMIP2) for 1985–2004. While both simulate EEA patterns, biases like a diffusive thermocline and insufficient cooling exist during the development of the Atlantic cold tongue. OMIP1 exhibits 51% (33%) larger interannual sea surface temperature (sea surface height) variability than OMIP2, attributed to differences in wind forcing.
Jonathan Tinker, Matthew D. Palmer, Benjamin J. Harrison, Enda O'Dea, David M. H. Sexton, Kuniko Yamazaki, and John W. Rostron
Ocean Sci., 20, 835–885, https://doi.org/10.5194/os-20-835-2024, https://doi.org/10.5194/os-20-835-2024, 2024
Short summary
Short summary
The northwest European shelf (NWS) seas are economically and environmentally important but poorly represented in global climate models (GCMs). We combine use of a shelf sea model with GCM output to provide improved 21st century projections of the NWS. We project a NWS warming of 3.11 °C and freshening of −1.01, and we provide uncertainty estimates. We calculate the climate signal emergence and consider warming levels. We have released our data for the UK's Climate Change Risk Assessment.
Davide Bonaldo, Sandro Carniel, Renato R. Colucci, Cléa Denamiel, Petra Pranic, Fabio Raicich, Antonio Ricchi, Lorenzo Sangelantoni, Ivica Vilibic, and Maria Letizia Vitelletti
EGUsphere, https://doi.org/10.5194/egusphere-2024-1468, https://doi.org/10.5194/egusphere-2024-1468, 2024
Short summary
Short summary
We present a high-resolution modelling effort to investigate the possible end-of-century evolution of the main physical processes in the Adriatic Sea in a severe climate change scenario, with an ensemble approach (viz., use a of multiple simulations) allowing to control the uncertainty of the predictions. Our model exhibits a satisfactory capability to reproduce the recent past and provides a ground for a set of multidisciplinary studies in this area over a multi-decadal horizon.
Eric de Boisséson and Magdalena Alonso Balmaseda
Ocean Sci., 20, 265–278, https://doi.org/10.5194/os-20-265-2024, https://doi.org/10.5194/os-20-265-2024, 2024
Short summary
Short summary
Marine heatwaves are long periods of extremely warm ocean surface temperatures. Predicting such events a few months in advance would help decision-making to mitigate their impacts on marine ecosystems. This work investigates how well operational seasonal forecasts can predict marine heatwaves. Results show that such events can be predicted a few months in advance in the tropics but that extending the predictability skill to other regions will require additional work on the forecast models.
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.
Cited articles
Abdelmajeed, A. Y. and Juszczak, R.: Challenges and Limitations of Remote Sensing Applications in Northern Peatlands: Present and Future Prospects, https://doi.org/10.3390/rs16030591, 2024.
Anding, D. and Kauth, R.: Estimation of sea surface temperature from space, Remote Sens. Environ., 1, 217–220, https://doi.org/10.1016/S0034-4257(70)80002-5, 1970.
Balaji, V.: Climbing down Charney's ladder: machine learning and the post-Dennard era of computational climate science, Philos. T. Roy. Soc. A, 379, 20200085, https://doi.org/10.1098/rsta.2020.0085, 2021.
Benincasa, R., Liguori, G., Pinardi, N., and von Storch, H.: Internal and forced ocean variability in the Mediterranean Sea, Ocean Sci., 20, 1003–1012, https://doi.org/10.5194/os-20-1003-2024, 2024.
Berrisford, P., Dee, D., Fielding, K., Fuentes, M., Kallberg, P., Kobayashi, S., and Uppala, S. S.: The ERA-interim archive, ERA Report Series, https://www.ecmwf.int/en/elibrary/73681-era-interim-archive (last access: May 2025), 2009.
Berthou, S., Renshaw, R., Smyth, T., Tinker, J., Grist, J. P., Wihsgott, J. U., Jones, S., Inall, M., Nolan, G., Berx, B., Arnold, A., Blunn, L. P., Castillo, J. M., Cotterill, D., Daly, E., Dow, G., Gómez, B., Fraser-Leonhardt, V., Hirschi, J. J. M., Lewis, H. W., Mahmood, S., and Worsfold, M.: Exceptional atmospheric conditions in June 2023 generated a northwest European marine heatwave which contributed to breaking land temperature records, Commun. Earth Environ., 5, 287, https://doi.org/10.1038/s43247-024-01413-8, 2024.
Bertsimas, D. and Boussioux, L.: Ensemble modeling for time series forecasting: an adaptive robust optimization approach, arXiv [preprint], https://doi.org/10.48550/arXiv.2304.04308, 2023.
Bethoux, J. P., Gentili, B., Morin, P., Nicolas, E., Pierre, C., and Ruiz-Pino, D.: The Mediterranean Sea: a miniature ocean for climatic and environmental studies and a key for the climatic functioning of the North Atlantic, Prog. Oceanogr., 44, 131–146, https://doi.org/10.1016/S0079-6611(99)00023-3, 1999.
Beuvier, J., Béranger, K., Lebeaupin Brossier, C., Somot, S., Sevault, F., Drillet, Y., Bourdallé-Badie, R., Ferry, N., and Lyard, F.: Spreading of the Western Mediterranean Deep Water after winter 2005: Time scales and deep cyclone transport, J. Geophys. Res.-Oceans, 117, C07022, https://doi.org/10.1029/2011JC007679, 2012.
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, 2023.
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, Ocean Sci., 20, 417–432, https://doi.org/10.5194/os-20-417-2024, 2024.
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.
Chen, L., Han, B., Wang, X., Zhao, J., Yang, W., and Yang, Z.: Machine Learning Methods in Weather and Climate Applications: A Survey, Appl. Sci. 13, 12019, https://doi.org/10.3390/app132112019, 2023.
Coppini, G., Clementi, E., Cossarini, G., Salon, S., Korres, G., Ravdas, M., Lecci, R., Pistoia, J., Goglio, A. C., Drudi, M., Grandi, A., Aydogdu, A., Escudier, R., Cipollone, A., Lyubartsev, V., Mariani, A., Cretì, S., Palermo, F., Scuro, M., Masina, S., Pinardi, N., Navarra, A., Delrosso, D., Teruzzi, A., Di Biagio, V., Bolzon, G., Feudale, L., Coidessa, G., Amadio, C., Brosich, A., Miró, A., Alvarez, E., Lazzari, P., Solidoro, C., Oikonomou, C., and Zacharioudaki, A.: The Mediterranean Forecasting System – Part 1: Evolution and performance, Ocean Sci., 19, 1483–1516, https://doi.org/10.5194/os-19-1483-2023, 2023.
Darmaraki, S., Somot, S., Sevault, F., and Nabat, P.: Past Variability of Mediterranean Sea Marine Heatwaves, Geophys. Res. Lett., 46, 9813–9823, https://doi.org/10.1029/2019GL082933, 2019a.
Darmaraki, S., Somot, S., Sevault, F., Nabat, P., Cabos Narvaez, W. D., Cavicchia, L., Djurdjevic, V., Li, L., Sannino, G., and Sein, D. V.: Future evolution of Marine Heatwaves in the Mediterranean Sea, Clim. Dynam., 53, 1371–1392, https://doi.org/10.1007/s00382-019-04661-z, 2019b.
Darmaraki, S., Denaxa, D., Theodorou, I., Livanou, E., Rigatou, D., Raitsos E, D., Stavrakidis-Zachou, O., Dimarchopoulou, D., Bonino, G., McAdam, R., Organelli, E., Pitsouni, A., and Parasyris, A.: Marine Heatwaves in the Mediterranean Sea: A Literature Review, Mediterr. Mar. Sci., 25, 586–620, https://doi.org/10.12681/mms.38392, 2024.
Desai, S. and Strachan, A.: Parsimonious neural networks learn interpretable physical laws, Sci. Rep., 11, 12761, https://doi.org/10.1038/s41598-021-92278-w, 2021.
Doury, A., Somot, S., Gadat, S., Ribes, A., and Corre, L.: Regional climate model emulator based on deep learning: concept and first evaluation of a novel hybrid downscaling approach, Clim. Dynam., 60, 1751–1779, https://doi.org/10.1007/s00382-022-06343-9, 2023.
Fawcett, T.: An introduction to ROC analysis, Pattern Recogn. Lett., 27, 861–874, https://doi.org/10.1016/j.patrec.2005.10.010, 2006.
Fdez-Riverola, F., Corchado, J. M., and Torres, J. M.: An Automated Hybrid CBR System for Forecasting, Advances in Case-Based Reasoning, Berlin, Heidelberg, 519–533, https://doi.org/10.1007/3-540-46119-1_38, 2002.
Garcia-Gorriz, E. and Garcia-Sanchez, J.: Prediction of sea surface temperatures in the western Mediterranean Sea by neural networks using satellite observations, Geophys. Res. Lett., 34, L11603, https://doi.org/10.1029/2007GL029888, 2007.
Garrabou, J., Gómez-Gras, D., Medrano, A., Cerrano, C., Ponti, M., Schlegel, R., Bensoussan, N., Turicchia, E., Sini, M., Gerovasileiou, V., Teixido, N., Mirasole, A., Tamburello, L., Cebrian, E., Rilov, G., Ledoux, J. B., Souissi, J. B., Khamassi, F., Ghanem, R., Benabdi, M., Grimes, S., Ocaña, O., Bazairi, H., Hereu, B., Linares, C., Kersting, D. K., la Rovira, G., Ortega, J., Casals, D., Pagès-Escolà, M., Margarit, N., Capdevila, P., Verdura, J., Ramos, A., Izquierdo, A., Barbera, C., Rubio-Portillo, E., Anton, I., López-Sendino, P., Díaz, D., Vázquez-Luis, M., Duarte, C., Marbà, N., Aspillaga, E., Espinosa, F., Grech, D., Guala, I., Azzurro, E., Farina, S., Cristina Gambi, M., Chimienti, G., Montefalcone, M., Azzola, A., Mantas, T. P., Fraschetti, S., Ceccherelli, G., Kipson, S., Bakran-Petricioli, T., Petricioli, D., Jimenez, C., Katsanevakis, S., Kizilkaya, I. T., Kizilkaya, Z., Sartoretto, S., Elodie, R., Ruitton, S., Comeau, S., Gattuso, J. P., and Harmelin, J. G.: Marine heatwaves drive recurrent mass mortalities in the Mediterranean Sea, Glob. Change Biol., 28, 5708–5725, https://doi.org/10.1111/gcb.16301, 2022.
Giamalaki, K., Beaulieu, C., and Prochaska, J. X.: Assessing Predictability of Marine Heatwaves With Random Forests, Geophys. Res. Lett., 49, e2022GL099069, https://doi.org/10.1029/2022GL099069, 2022.
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, https://doi.org/10.1109/ACCESS.2019.2955957, 2019.
Hobday, A. J., Alexander, L. V., Perkins, S. E., Smale, D. A., Straub, S. C., Oliver, E. C. J., Benthuysen, J. A., Burrows, M. T., Donat, M. G., Feng, M., Holbrook, N. J., Moore, P. J., Scannell, H. A., Sen Gupta, A., and Wernberg, T.: A hierarchical approach to defining marine heatwaves, Prog. Oceanogr., 141, 227–238, https://doi.org/10.1016/j.pocean.2015.12.014, 2016.
Hornik, K.: Approximation capabilities of multilayer feedforward networks, Neural Networks, 4, 251–257, https://doi.org/10.1016/0893-6080(91)90009-T, 1991.
Ibtehaz, N. and Rahman, M. S.: MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation, Neural Networks, 121, 74–87, https://doi.org/10.1016/j.neunet.2019.08.025, 2020.
Jacox, M. G., Alexander, M. A., Amaya, D., Becker, E., Bograd, S. J., Brodie, S., Hazen, E. L., Pozo Buil, M., and Tommasi, D.: Global seasonal forecasts of marine heatwaves, Nature, 604, 486–490, https://doi.org/10.1038/s41586-022-04573-9, 2022.
Jacques-Dumas, V., Ragone, F., Borgnat, P., Abry, P., and Bouchet, F.: Deep Learning-Based Extreme Heatwave Forecast, Front. Clim., 4, https://doi.org/10.3389/fclim.2022.789641, 2022.
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, arXiv [preprint], https://doi.org/10.48550/arXiv.1412.6980, 2014.
Konsta, K., Doxa, A., Katsanevakis, S., and Mazaris, A.: Projected intensification of subsurface marine heatwaves under climate change, Research Square [preprint], https://doi.org/10.21203/rs.3.rs-3091828/v1, 2023.
Lacoue-Labarthe, T., Nunes, P. A. L. D., Ziveri, P., Cinar, M., Gazeau, F., Hall-Spencer, J. M., Hilmi, N., Moschella, P., Safa, A., Sauzade, D., and Turley, C.: Impacts of ocean acidification in a warming Mediterranean Sea: An overview, Reg. Stud. Mar. Sci., 5, 1–11, https://doi.org/10.1016/j.rsma.2015.12.005, 2016.
Lam, R., Sanchez-Gonzalez, A., Willson, M., Wirnsberger, P., Fortunato, M., Alet, F., Ravuri, S., Ewalds, T., Eaton-Rosen, Z., Hu, W., Merose, A., Hoyer, S., Holland, G., Vinyals, O., Stott, J., Pritzel, A., Mohamed, S., and Battaglia, P.: Learning skillful medium-range global weather forecasting, Science, 382, 1416–1421, https://doi.org/10.1126/science.adi2336, 2023.
Lin, T. Y., Goyal, P., Girshick, R., He, K., and Dollár, P.: Focal Loss for Dense Object Detection, IEEE T. Pattern Anal., 42, 318–327, https://doi.org/10.1109/TPAMI.2018.2858826, 2020.
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.
Liu, Y., Weisberg, R. H., Sorinas, L., Law, J. A., and Nickerson, A. K.: Rapid Intensification of Hurricane Ian in Relation to Anomalously Warm Subsurface Water on the Wide Continental Shelf, Geophys. Res. Lett., 52, e2024GL113192, https://doi.org/10.1029/2024GL113192, 2025.
Maas, A. L., Hannun, A. Y., and Ng, A. Y.: Rectifier Nonlinearities Improve Neural Network Acoustic Models, Proceedings of the 30th International Conference on Machine Learning, 28, 3, https://ai.stanford.edu/~amaas/papers/relu_hybrid_icml2013_final.pdf (last access: May 2025), 2013.
Mavropoulou, A.-M., Mantziafou, A., Jarosz, E., and Sofianos, S.: The influence of Black Sea Water inflow and its synoptic time-scale variability in the North Aegean Sea hydrodynamics, Ocean Dynam., 66, 195–206, https://doi.org/10.1007/s10236-016-0923-5, 2016.
McAdam, R., Masina, S., and Gualdi, S.: Seasonal forecasting of subsurface marine heatwaves, Commun. Earth Environ., 4, 225, https://doi.org/10.1038/s43247-023-00892-5, 2023.
McMillin, L. M.: Estimation of sea surface temperatures from two infrared window measurements with different absorption, J. Geophys. Res., 80, 5113–5117, https://doi.org/10.1029/JC080i036p05113, 1975.
Menna, M., Gačić, M., Martellucci, R., Notarstefano, G., Fedele, G., Mauri, E., Gerin, R., and Poulain, P.-M.: Climatic, Decadal, and Interannual Variability in the Upper Layer of the Mediterranean Sea Using Remotely Sensed and In-Situ Data, Remote Sens., 14, 1322, https://doi.org/10.3390/rs14061322, 2022.
Nguyen, Q. D. and Thai, H.-T.: Crack segmentation of imbalanced data: The role of loss functions, Eng. Struct., 297, 116988, https://doi.org/10.1016/j.engstruct.2023.116988, 2023.
Oktay, O., Schlemper, J., Folgoc, L. L., Lee, M. J., Heinrich, M. P., Misawa, K., Mori, K., McDonagh, S. G., Hammerla, N. Y., Kainz, B., Glocker, B., and Rueckert, D. J. A.: Attention U-Net: Learning Where to Look for the Pancreas, arXiv [preprint], https://doi.org/10.48550/arXiv.1804.03999, 2018.
Oliver, E. C. J., Donat, M. G., Burrows, M. T., Moore, P. J., Smale, D. A., Alexander, L. V., Benthuysen, J. A., Feng, M., Sen Gupta, A., Hobday, A. J., Holbrook, N. J., Perkins-Kirkpatrick, S. E., Scannell, H. A., Straub, S. C., and Wernberg, T.: Longer and more frequent marine heatwaves over the past century, Nat. Commun., 9, 1324, https://doi.org/10.1038/s41467-018-03732-9, 2018.
Parasyris, A., Alexandrakis, G., Kozyrakis, G. V., Spanoudaki, K., and Kampanis, N. A.: Predicting Meteorological Variables on Local Level with SARIMA, LSTM and Hybrid Techniques, Atmosphere, 13, 878, https://doi.org/10.3390/atmos13060878, 2022.
Petrelli, P.: XMHW: Xarray based code to identify Marine HeatWave events and their characteristics, Zenodo [code], https://doi.org/10.5281/zenodo.6270280, 2022.
Pisano, A., Ciani, D., Marullo, S., Santoleri, R., and Buongiorno Nardelli, B.: A new operational Mediterranean diurnal optimally interpolated sea surface temperature product within the Copernicus Marine Service, Earth Syst. Sci. Data, 14, 4111–4128, https://doi.org/10.5194/essd-14-4111-2022, 2022.
Ronneberger, O., Fischer, P., and Brox, T.: U-net: Convolutional networks for biomedical image segmentation, Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, 5–9 October 2015, Proceedings, Part III 18, 234–241, https://doi.org/10.1007/978-3-319-24574-4_28, 2015.
Schultz, M. G., Betancourt, C., Gong, B., Kleinert, F., Langguth, M., Leufen, L. H., Mozaffari, A., and Stadtler, S.: Can deep learning beat numerical weather prediction?, Philos. T. Roy. Soc. A, 379, 20200097, https://doi.org/10.1098/rsta.2020.0097, 2021.
Sevault, F.: Atlas of the 1980–2018 ERA-interim simulation with the coupled regional climate system model CNRM-RCSM6 (version v2), Zenodo, https://doi.org/10.5281/zenodo.11066601, 2024.
Sharma, S., Sharma, S., and Athaiya, A.: Activation Functions in Neural Networks, Int. J. Eng. Appl. Sci. Tech., 4, 310–316, https://doi.org/10.33564/IJEAST.2020.v04i12.054, 2020.
Smith, K. E., Burrows, M. T., Hobday, A. J., Sen Gupta, A., Moore, P. J., Thomsen, M., Wernberg, T., and Smale, D. A.: Socioeconomic impacts of marine heatwaves: Global issues and opportunities, Science, 374, eabj3593, https://doi.org/10.1126/science.abj3593, 2021.
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.
Sun, W., Zhou, S., Yang, J., Gao, X., Ji, J., and Dong, C.: Artificial Intelligence Forecasting of Marine Heatwaves in the South China Sea Using a Combined U-Net and ConvLSTM System, Remote Sens., 15, 4068, https://doi.org/10.3390/rs15164068, 2023.
Taylor, J. and Feng, M.: A deep learning model for forecasting global monthly mean sea surface temperature anomalies, Front. Clim., 4, https://doi.org/10.3389/fclim.2022.932932, 2022.
Velaoras, D., Zervakis, V., and Theocharis, A.: The Physical Characteristics and Dynamics of the Aegean Water Masses, in: The Aegean Sea Environment: The Geodiversity of the Natural System, edited by: Anagnostou, C. L., Kostianoy, A. G., Mariolakos, I. D., Panayotidis, P., Soilemezidou, M., and Tsaltas, G., Springer International Publishing, Cham, 231–259, https://doi.org/10.1007/698_2020_730, 2024.
Waldman, R., Somot, S., Herrmann, M., Bosse, A., Caniaux, G., Estournel, C., Houpert, L., Prieur, L., Sevault, F., and Testor, P.: Modeling the intense 2012–2013 dense water formation event in the northwestern Mediterranean Sea: Evaluation with an ensemble simulation approach, J. Geophys. Res.-Oceans, 122, 1297–1324, https://doi.org/10.1002/2016JC012437, 2017.
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.
Xu, Z., Xiao, Z., Zhao, X., Ma, Z., Zhang, Q., Zeng, P., and Zhang, X.: Derivation of Landslide Rainfall Thresholds by Geostatistical Methods in Southwest China, Sustainability, 16, 4044, https://doi.org/10.3390/su16104044, 2024.
Zanetta, F., Nerini, D., Beucler, T., and Liniger, M. A.: Physics-Constrained Deep Learning Postprocessing of Temperature and Humidity, Artificial Intelligence for the Earth Systems, 2, e220089, https://doi.org/10.1175/AIES-D-22-0089.1, 2023.
Short summary
The Mediterranean faces more frequent and intense marine heat waves, harming ecosystems and fisheries. Using machine learning, we developed a model to forecast these events up to 7 d in the future, outperforming traditional methods. This approach enables faster, accurate forecasts, helping authorities mitigate impacts and protect marine resources.
The Mediterranean faces more frequent and intense marine heat waves, harming ecosystems and...