Abstract
Sea surface temperature (SST) is a key indicator of the global climate system and is directly related to marine and coastal ecosystems, weather conditions, and atmospheric events. Marine heat waves (MHWs), characterized by prolonged periods of high SST, affect significantly the oceanic water quality and thus, the local ecosystem, and marine and coastal activities. Given the anticipated increase of MHWs occurrences due to climate change, develo** targeted strategies is needed to mitigate their impact. Accurate SST forecasting can significantly contribute to this cause and thus it comprises a crucial, yet challenging, task for the scientific community. Despite the wide variety of existing methods in the literature, the majority of them focus either on providing near-future SST forecasts (a few days until 1 month) or long-term predictions (decades to century) in climate scales based on hypothetical scenarios that need to be proven. In this work, we introduce a robust deep learning-based method for efficient SST forecasting of the interim future (1 year ahead) using high-resolution satellite-derived SST data. Our approach processes daily SST sequences lasting 1 year, along with five other relevant atmospheric variables, to predict the corresponding daily SST timeseries for the subsequent year. The novel method was deployed to accurately forecast SST over the northeastern Mediterranean Seas (Aegean, Ionian, Cretan Seas: AICS). Utilizing the effectiveness of well-established deep learning architectures, our method can provide accurate spatiotemporal predictions for multiple areas at once, without the need to be deployed separately at each sub-region. The modular design of the framework allows customization for different spatial and temporal resolutions according to use case requirements. The proposed model was trained and evaluated using available data from the AICS region over a 15-year time period (2008–2022). The results demonstrate the efficiency of our method in predicting SST variability, even for previously unseen data that are over 2 years in advance, in respect to the training set. The proposed methodology is a valuable tool that also can contribute to MHWs prediction.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10236-023-01595-3/MediaObjects/10236_2023_1595_Fig11_HTML.png)
Similar content being viewed by others
Data Availability
The data that support the findings of this study are openly available. The sea surface temperatures (SSTs) are available in: https://doi.org/10.48670/moi-00172. The ERA-5 meteorological data are available in: https://doi.org/10.24381/cds.adbb2d47
Notes
SST_MED_SST_L4_NRT_OBSERVATIONS_010_004_c.
References
Androulidakis Y, Kourafalou V (2011) Evolution of a buoyant outflow in the presence of complex topography: the Dardanelles plume (North Aegean Sea). J Geophys Res (Oceans) 116:4019
Androulidakis YS, Kourafalou V (2022) Marine heat waves over natural and urban coastal environments of South Florida. Water 14(23):3840
Androulidakis YS, Krestenitis YN (2022) Sea surface temperature variability and marine heat waves over the Aegean, Ionian, and Cretan seas from 2008–2021. J Mar Sci Eng 10(1):42
Bell MJ, Lefebvre M, Le Traon P-Y, Smith N, Wilmer-Becker K (2009) GODAE: the global ocean data assimilation experiment. Oceanography 22(3):14–21
Birkeland C (1997) Life and death of coral reefs. Springer Science & Business Media
Cho K, Van Merriënboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. ar**v:1406.1078
Cleveland RB, Cleveland WS, McRae JE, Terpenning I (1990) STL: a seasonal-trend decomposition. J Off Stat 6(1):3–73
Darmaraki S, Somot S, Sevault F, Nabat P (2019) Past variability of Mediterranean Sea marine heatwaves. Geophys Res Lett 46(16):9813–9823
de Almeida Pereira GH, Fusioka AM, Nassu BT, Minetto R (2021) Active fire detection in Landsat-8 imagery: a large-scale dataset and a deep-learning study. ISPRS Journal of Photogrammetry and Remote Sensing 178:171–186
Di Lorenzo E, Mantua N (2016) Multi-year persistence of the 2014/15 north pacific marine heatwave. Nature Climate Change 6(11):1042–1047
Drévillon M, Bourdallé-Badie R, Derval C, Lellouche J, Rémy E, Tranchant B, Benkiran M, Greiner E, Guinehut S, Verbrugge N et al (2008) The GODAE/Mercator-Ocean global ocean forecasting system: results, applications and prospects. J Oper Oceanogr 1(1):51–57
Freund Y, Schapire RE et al (1996) Experiments with a new boosting algorithm. In: icml, vol 96, pages 148–156. Citeseer
Frölicher TL, Fischer EM, Gruber N (2018) Marine heatwaves under global warming. Nature 560(7718):360–364
Garrabou J, Coma R, Bensoussan N, Bally M, Chevaldonné P, Cigliano M, Díaz D, Harmelin J-G, Gambi MC, Kersting D et al (2009) Mass mortality in Northwestern Mediterranean rocky benthic communities: effects of the 2003 heat wave. Glob Chang Biol 15(5):1090–1103
Garrabou J, Gómez-Gras D, Medrano A, Cerrano C, Ponti M, Schlegel R, Bensoussan N, Turicchia E, Sini M, Gerovasileiou V et al (2022) Marine heatwaves drive recurrent mass mortalities in the Mediterranean Sea. Glob Chang Biol 28(19):5708–5725
Good S, Fiedler E, Mao C, Martin MJ, Maycock A, Reid R, Roberts-Jones J, Searle T, Waters J, While J et al (2020) The current configuration of the ostia system for operational production of foundation sea surface temperature and ice concentration analyses. Remote Sens 12(4):720
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Hobday AJ, Alexander LV, Perkins SE, Smale DA, Straub SC, Oliver EC, Benthuysen JA, Burrows MT, Donat MG, Feng M et al (2016) A hierarchical approach to defining marine heatwaves. Prog Oceanogr 141:227–238
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Holbrook NJ, Scannell HA, Sen Gupta A, Benthuysen JA, Feng M, Oliver EC, Alexander LV, Burrows MT, Donat MG, Hobday AJ et al (2019) A global assessment of marine heatwaves and their drivers. Nat Commun 10(1):2624
Houpert L, Testor P, Durrieu de Madron X, Somot S, D’Ortenzio F, Estournel C, Lavigne H (2014) Seasonal cycle of the mixed layer, the seasonal thermocline and the upper-ocean heat storage rate in the Mediterranean Sea derived from observations. Progress in Oceanography, pages –
Jahanbakht M, **ang W, Azghadi MR (2021) Sea surface temperature forecasting with ensemble of stacked deep neural networks. IEEE Geosci Remote Sens Lett 19:1–5
Kara AB, Helber RW, Boyer TP, Elsner JB (2009) Mixed layer depth in the Aegean, Marmara, Black and Azov Seas: Part I: general features. Journal of Marine Systems 78:S169–S180. Coastal Processes: Challenges for Monitoring and Prediction
Kazemi SM, Goel R, Eghbali S, Ramanan J, Sahota J, Thakur S, Wu S, Smyth C, Poupart P, Brubaker M (2019) Time2vec: learning a vector representation of time. ar**v:1907.05321
Kendall M (1975) Rank correlation methods. Charles Griffin, London, UK
Kent, E.C., Taylor, P.K. (2006). Toward estimating climatic trends in SST. Part I: methods of measurement. Journal of Atmospheric and Oceanic Technology 23(3):464–475
Krestenitis M, Orfanidis G, Ioannidis K, Avgerinakis K, Vrochidis S, Kompatsiaris I (2019) Oil spill identification from satellite images using deep neural networks. Remote Sens 11(15):1762
Lattos A, Papadopoulos DK, Feidantsis K, Karagiannis D, Giantsis IA, Michaelidis B (2022) Are marine heatwaves responsible for mortalities of farmed mytilus galloprovincialis? a pathophysiological analysis of marteilia infected mussels from thermaikos gulf, greece. Animals 12(20):2805
Lattos A, Papadopoulos DK, Feidantsis K, Karagiannis D, Giantsis IA, Michaelidis B (2022) Are marine heatwaves responsible for mortalities of farmed Mytilus galloprovincialis? A pathophysiological analysis of Marteilia infected mussels from Thermaikos Gulf, Greece. Animals 12(20):2805
Mohamed B, Skliris N (2022) Steric and atmospheric contributions to interannual sea level variability in the Eastern Mediterranean Sea over 1993–2019. Oceanologia 64(1):50–62
Moss RH, Edmonds JA, Hibbard KA, Manning MR, Rose SK, Van Vuuren DP, Carter TR, Emori S, Kainuma M, Kram T et al (2010) The next generation of scenarios for climate change research and assessment. Nature 463(7282):747–756
Nardelli BB, Tronconi C, Pisano A, Santoleri R (2013) High and ultra-high resolution processing of satellite sea surface temperature data over Southern European Seas in the framework of MyOcean project. Remote Sens Environ 129:1–16
Nardelli C, Pisano A, Tronconi BB (2019) Mediterranean sea and black sea surface temperature NRT data, quality information document. Luxembourg, Copernicus Marine Environment Monitoring Service
Nazarenko L, Schmidt G, Miller R, Tausnev N, Kelley M, Ruedy R, Russell G, Aleinov I, Bauer M, Bauer S et al (2015) Future climate change under RCP emission scenarios with GISS M odelE2. J Adv Model Earth Syst 7(1):244–267
Oliver EC, Benthuysen JA, Bindoff NL, Hobday AJ, Holbrook NJ, Mundy CN, Perkins-Kirkpatrick SE (2017) The unprecedented 2015/16 Tasman Sea marine heatwave. Nat Commun 8(1):16101
Oliver EC, Donat MG, Burrows MT, Moore PJ, Smale DA, Alexander LV, Benthuysen JA, Feng M, Sen Gupta A, Hobday AJ et al (2018) Longer and more frequent marine heatwaves over the past century. Nat Commun 9(1):1–12
Olson DB, Kourafalou VH, Johns WE, Samuels G, Veneziani M (2007) Aegean surface circulation from a satellite-tracked drifter array. J Phys Oceanogr 37(7):1898–1917
Patil KR, Iiyama M (2022) Deep learning models to predict sea surface temperature in Tohoku region. IEEE Access 10:40410–40418
Pearce AF, Feng M (2013) The rise and fall of the “marine heat wave’’ off Western Australia during the summer of 2010/2011. J Mar Syst 111:139–156
Pinardi N, Allen I, Demirov E, De Mey P, Korres G, Lascaratos A, Le Traon P-Y, Maillard C, Manzella G, Tziavos C (2003) The Mediterranean ocean forecasting system: first phase of implementation (1998–2001). Annales Geophysicae, vol 21. Copernicus Publications Göttingen, Germany, pp 3–20
Rilov G (2016) Multi-species collapses at the warm edge of a warming sea. Sci Rep 6(1):36897
Tabernik D, Šela S, Skvarč J, Skočaj D (2020) Segmentation-based deep-learning approach for surface-defect detection. J Intell Manuf 31(3):759–776
Wang W, Lee J, Harrou F, Sun Y (2020) Early detection of Parkinson’s disease using deep learning and machine learning. IEEE Access 8:147635–147646
Wang Y, Zhang J, Zhu H, Long M, Wang J, Yu PS (2019) Memory in memory: a predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 9154–9162
Wernberg T, Smale DA, Tuya F, Thomsen MS, Langlois TJ, De Bettignies T, Bennett S, Rousseaux CS (2013) An extreme climatic event alters marine ecosystem structure in a global biodiversity hotspot. Nat Clim Chang 3(1):78–82
Willmott CJ, Robeson SM, Matsuura K (2012) A refined index of model performance. Int J Climatol 32(13):2088–2094
**ao C, Chen N, Hu C, Wang K, Gong J, Chen Z (2019) Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach. Remote Sens Environ 233
**ao C, Chen N, Hu C, Wang K, Xu Z, Cai Y, Xu L, Chen Z, Gong J (2019) A spatiotemporal deep learning model for sea surface temperature field prediction using time-series satellite data. Environ Model Softw 120:104502
**e J, Zhang J, Yu J, Xu L (2019) An adaptive scale sea surface temperature predicting method based on deep learning with attention mechanism. IEEE Geosci Remote Sens Lett 17(5):740-744
Xu S, Dai D, Cui X, Yin X, Jiang S, Pan H, Wang G (2023) A deep learning approach to predict sea surface temperature based on multiple modes. Ocean Model 181:102158
Yang Y, Dong J, Sun X, Lima E, Mu Q, Wang X (2017) A CFCC-LSTM model for sea surface temperature prediction. IEEE Geosci Remote Sens Lett 15(2):207–211
Yu X, Shi S, Xu L, Liu Y, Miao Q, Sun M (2020) A novel method for sea surface temperature prediction based on deep learning. Mathematical Problems in Engineering 2020:1–9
Zhang K, Geng X, Yan X-H (2020) Prediction of 3-D ocean temperature by multilayer convolutional LSTM. IEEE Geosci Remote Sens Lett 17(8):1303–1307
Zhang Q, Wang H, Dong J, Zhong G, Sun X (2017) Prediction of sea surface temperature using long short-term memory. IEEE Geosci Remote Sens Lett 14(10):1745–1749
Acknowledgements
The sea surface temperatures (SSTs) and the ERA-5 meteorological data were provided by the E.U. Copernicus Marine Service (https://www.copernicus.eu/, accessed on 24/04/23).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Responsible Editor: Tomasz Dabrowski.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the Topical Collection on the Coastal Ocean and Shelf Seas Task Team (COSS-TT) meeting, Montreal, Canada, May 2-4, 2023
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Krestenitis, M., Androulidakis, Y. & Krestenitis, Y. Deep learning-based forecasting of sea surface temperature in the interim future: application over the Aegean, Ionian, and Cretan Seas (NE Mediterranean Sea). Ocean Dynamics 74, 149–168 (2024). https://doi.org/10.1007/s10236-023-01595-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10236-023-01595-3