A deep learning-based hybrid model for improved SST prediction in the tropical Pacific Ocean

Yuanzhe MA; Bowen XIE; Zhongkun FENG; Guimin SUN; Cong ZHANG; Shuguo YANG

doi:10.1007/s00343-025-4333-8

Your Location：

Home >

Browse articles >

A deep learning-based hybrid model for improved SST prediction in the tropical Pacific Ocean

Physics | Updated：2025-12-16

- A deep learning-based hybrid model for improved SST prediction in the tropical Pacific Ocean
- Journal of Oceanology and Limnology Vol. 43, Issue 6, Pages: 1709-1725(2025)
- Affiliations：
  
  1.School of Mathematics and Physics, Qingdao University of Science and Technology, Qingdao 266061, China
  2.CAS Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, China
  3.University of Chinese Academy of Sciences, Beijing 100049, China
  4.Marine Sciences Research Institute of Shandong Province, Qingdao 266104, China
- Author bio：
  
  xiebw@mails.qust.edu.cn
- Funds：
- DOI：10.1007/s00343-025-4333-8
  CLC：
- Received：09 December 2024，
  
  Published：01 November 2025
- Accepted：
Scan QR Code
MA Yuanzhe,XIE Bowen,FENG Zhongkun,et al.A deep learning-based hybrid model for improved SST prediction in the tropical Pacific Ocean[J].Journal of Oceanology and Limnology,2025,43(06):1709-1725.
DOI：

MA Yuanzhe,XIE Bowen,FENG Zhongkun,et al.A deep learning-based hybrid model for improved SST prediction in the tropical Pacific Ocean[J].Journal of Oceanology and Limnology,2025,43(06):1709-1725. DOI： 10.1007/s00343-025-4333-8.

摘要

Abstract

Sea surface temperature (SST) is an important ocean variable affecting climate change. It plays an important role in the interactions between the ocean and the atmosphere

and it also has an effect on the transport of heat

freshwater

and carbon. Therefore

accurate SST prediction is necessary for understanding climate change and protecting ocean ecosystems. In this study

we proposed a hybrid model to predict SST in the tropical Pacific Ocean based on two single deep-learning models. Results indicate that the proposed hybrid model shows superior prediction accuracy at all lead times compared to the single model. Specifically

during El Niño periods

the root mean square error

mean absolute error

and Pearson correlation coefficient of the hybrid model forecasts were approximately 0.54 °C

0.40 °C

and 0.98

respectively

while during La Niña periods

these metrics were 0.55 °C

0.39 °C

and 0.98

respectively. Notably

the hybrid model was able to capture the spatial distribution of SSTs during the El Niño-Southern Oscillation (ENSO) events more accurately relative to a single model. Moreover

the prediction results of the hybrid model in different ocean regions exhibited lower prediction errors and higher correlations. The ablation experiments showed that sea surface wind (SSW) had different effects on SST at different times. By combining SST and SSW data

the model can make more-accurate predictions under different climatic conditions. The proposed hybrid model is able to predict SSTs quickly and accurately with better robustness during ENSO.

关键词

Keywords

references

Aparna S , D'Souza S , Arjun N . 2018 . Prediction of daily sea surface temperature using artificial neural networks . International Journal of Remote Sensing , 39 ( 12 ): 4214 - 4231 , https://doi.org/10.1080/01431161.2018.1454623 https://doi.org/10.1080/01431161.2018.1454623 .

Atlas R , Hoffman R N , Ardizzone J et al . 2011 . A cross-calibrated, multiplatform ocean surface wind velocity product for meteorological and oceanographic applications . Bulletin of the American Meteorological Society , 92 ( 2 ): 157 - 174 , https://doi.org/10.1175/2010bams2946.1 https://doi.org/10.1175/2010bams2946.1 .

Barnett T P , Graham N , Pazan S et al . 1993 . ENSO and ENSO-related predictability. Part I: prediction of equatorial Pacific sea surface temperature with a hybrid coupled ocean-atmosphere model . Journal of Climate , 6 ( 8 ): 1545 - 1566 , https://doi.org/10.1175/1520-0442(1993)006<1545:EAERPP>2.0.CO;2. https://doi.org/10.1175/1520-0442(1993)006<1545:EAERPP>2.0.CO;2.

Collins D C , Reason C J C , Tangang F . 2004 . Predictability of Indian Ocean sea surface temperature using canonical correlation analysis . Climate Dynamics , 22 ( 5 ): 481 - 497 , https://doi.org/10.1007/s00382-004-0390-4 https://doi.org/10.1007/s00382-004-0390-4 .

Costa P , Gómez B , Venâncio A et al . 2012 . Using the Regional Ocean Modelling System (ROMS) to improve the sea surface temperature predictions of the MERCATOR Ocean System . Scientia Marina , 76 ( S1 ): 165 - 175 , https://doi.org/10.3989/scimar.03614.19E https://doi.org/10.3989/scimar.03614.19E .

de A . Araújo R, de Mattos Neto P S G, Nedjah N et al. 2023 . An error correction system for sea surface temperature prediction. Neural Computing and Applications , 35 ( 16 ): 11681 - 11699 , https://doi.org/10.1007/s00521-023-08311-8 https://doi.org/10.1007/s00521-023-08311-8 .

de Mattos Neto P S G , Cavalcanti G D C , de O . Santos Júnior D S et al. 2022 . Hybrid systems using residual modeling for sea surface temperature forecasting. Scientific Reports , 12 ( 1 ): 487 , https://doi.org/10.1038/s41598-021-04238-z https://doi.org/10.1038/s41598-021-04238-z .

Emanuel K . 2005 . Increasing destructiveness of tropical cyclones over the past 30 years . Nature , 436 ( 7051 ): 686 - 688 , https://doi.org/10.1038/nature03906 https://doi.org/10.1038/nature03906 .

Fairall C W , Bradley E F , Godfrey J S et al . 1996 . Cool-skin and warm-layer effects on sea surface temperature . Journal of Geophysical Research: Oceans , 101 ( C1 ): 1295 - 1308 , https://doi.org/10.1029/95JC03190 https://doi.org/10.1029/95JC03190 .

Fernández J G , Abdellaoui I A , Mehrkanoon S . 2022 . Deep coastal sea elements forecasting using UNet-based models. Knowledge - Based Systems , 252 : 109445 , https://doi.org/10.1016/j.knosys.2022.109445 https://doi.org/10.1016/j.knosys.2022.109445 .

Fölicher T L , Fischer E M , Gruber N . 2018 . Marine heatwaves under global warming . Nature , 560 ( 7718 ): 360 - 364 , https://doi.org/10.1038/s41586-018-0383-9 https://doi.org/10.1038/s41586-018-0383-9 .

Ganachaud A , Sen Gupta A , Brown J N et al . 2013 . Projected changes in the tropical Pacific Ocean of importance to tuna fisheries . Climatic Change , 119 ( 1 ): 163 - 179 , https://doi.org/10.1007/s10584-012-0631-1 https://doi.org/10.1007/s10584-012-0631-1 .

Garabato A C N , Polzin K L , King B A et al . 2004 . Widespread intense turbulent mixing in the southern Ocean . Science , 303 ( 5655 ): 210 - 213 , https://doi.org/10.1126/science.1090929 https://doi.org/10.1126/science.1090929 .

Graham N E , Michaelsen J , Barnett T P . 1987 . An investigation of the El Niño-southern Oscillation cycle with statistical models: 1. Predictor field characteristics . Journal of Geophysical Research: Oceans , 92 ( C13 ): 14251 - 14270 , https://doi.org/10.1029/JC092iC13p14251 https://doi.org/10.1029/JC092iC13p14251 .

Han M X , Feng Y , Zhao X L et al . 2019 . 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 https://doi.org/10.1109/access.2019.2955957 .

Hittawe M M , Langodan S , Beya O et al . 2022 . Efficient SST prediction in the Red Sea using hybrid deep learning-based approach . In: Proceedings of 2022 IEEE 20th International Conference on Industrial Informatics (INDIN) . Perth, Australia . p. 107 - 117 , https://doi.org/10.1109/INDIN51773.2022.9976090 https://doi.org/10.1109/INDIN51773.2022.9976090 .

Huang B Y , Liu C Y , Banzon V et al . 2021 . Improvements of the Daily Optimum Interpolation Sea Surface Temperature (DOISST) version 2.1 . Journal of Climate , 34 ( 8 ): 2923 - 2939 , https://doi.org/10.1175/jcli-d-20-0166.1 https://doi.org/10.1175/jcli-d-20-0166.1 .

Huang C J , Qiao F L , Chen S Y et al . 2019 . Observation and parameterization of broadband sea surface albedo . Journal of Geophysical Research: Oceans , 124 ( 7 ): 4480 - 4491 . https://doi.org/10.1029/2018jc014444 https://doi.org/10.1029/2018jc014444 .

Hughes T P , Kerry J T , Álvarez-Noriega M et al . 2017 . Global warming and recurrent mass bleaching of corals . Nature , 543 ( 7645 ): 373 - 377 , https://doi.org/10.1038/nature21707 https://doi.org/10.1038/nature21707 .

Kara A B , Wallcraft A J , Martin P J et al . 2008 . Performance of mixed layer models in simulating SST in the equatorial Pacific Ocean . Journal of Geophysical Research: Oceans , 113 ( C2 ): https://doi.org/10.1029/2007jc004250.

Karim M R . 2013 . Seasonal ARIMA for forecasting sea surface temperature of the north zone of the Bay of Bengal . Research & Reviews : Journal of Statistics , 2 ( 2 ): 23 - 31 .

Kumar P , Sardana D , Rajni N . 2021 . Regional sea level changes in the Indian shelf sea and its association with SST anomalies. Regional Studies in Marine Science , 47 : 101992 , https://doi.org/10.1016/j.rsma.2021.101992 https://doi.org/10.1016/j.rsma.2021.101992 .

Lins I D , Araujo M , das Chagas Moura M et al . 2013 . Prediction of sea surface temperature in the tropical Atlantic by support vector machines . Computational Statistics & Data Analysis , 61 : 187 - 198 , https://doi.org/10.1016/j.csda.2012.12.003 https://doi.org/10.1016/j.csda.2012.12.003 .

Liu G , Rauenzahn J L , Heron S F et al . 2013 . NOAA coral reef watch 50 km satellite sea surface temperature-based decision support system for coral bleaching management. NOAA Technical Report NESDIS 143, NOAA/NESDIS, College Park, MD .

Liu H , Tian H Q , Li Y F et al . 2015 . Comparison of four Adaboost algorithm based artificial neural networks in wind speed predictions . Energy Conversion and Management , 92 : 67 - 81 , https://doi.org/10.1016/j.enconman.2014.12.053 https://doi.org/10.1016/j.enconman.2014.12.053 .

Liu J , Tang Y M , Wu Y L et al . 2021 . Forecasting the Indian Ocean dipole with deep learning techniques . Geophysical Research Letters , 48 ( 20 ): e2021 GL 094407 , https://doi.org/10.1029/2021gl094407 https://doi.org/10.1029/2021gl094407 .

McPhaden M J , Zebiak S E , Glantz M H . 2006 . ENSO as an integrating concept in earth science . Science , 314 ( 5806 ): 1740 - 1745 , https://doi.org/10.1126/science.1132588 https://doi.org/10.1126/science.1132588 .

Messias V R , Estrella J C , Ehlers R et al . 2016 . Combining time series prediction models using genetic algorithm to autoscaling Web applications hosted in the cloud infrastructure . Neural Computing and Applications , 27 ( 8 ): 2383 - 2406 , https://doi.org/10.1007/s00521-015-2133-3 https://doi.org/10.1007/s00521-015-2133-3 .

Oliver E C J , Benthuysen J A , Darmaraki S et al . 2021 . Marine heatwaves . Annual Review of Marine Science , 13 : 313 - 342 , https://doi.org/10.1146/annurev-marine-032720-095144 https://doi.org/10.1146/annurev-marine-032720-095144 .

Ouyang L , Ling F H , Li Y et al . 2023 . Wave forecast in the Atlantic Ocean using a double-stage ConvLSTM network . Atmospheric and Oceanic Science Letters , 16 ( 4 ): 100347 , https://doi.org/10.1016/j.aosl.2023.100347 https://doi.org/10.1016/j.aosl.2023.100347 .

Power S , Lengaigne M , Capotondi A et al . 2021 . Decadal climate variability in the tropical Pacific: characteristics, causes, predictability, and prospects . Science , 374 ( 6563 ): eaay 9165 , https://doi.org/10.1126/science.aay9165 https://doi.org/10.1126/science.aay9165 .

Qi J F , Liu C Y , Chi J Y et al . 2022 . An ensemble-based machine learning model for estimation of subsurface thermal structure in the South China Sea . Remote Sensing , 14 ( 13 ): 3207 , https://doi.org/10.3390/rs14133207 https://doi.org/10.3390/rs14133207 .

Qi J F , Qu T D , Yin B S . 2023a . Meta-learning-based estimation of the barrier layer thickness in the tropical Indian Ocean . Environmental Research Communications , 5 ( 9 ): 091005 , https://doi.org/10.1088/2515-7620/acf9e1 https://doi.org/10.1088/2515-7620/acf9e1 .

Qi J F , Sun G M , Xie B W et al . 2024a . Deep learning to estimate ocean subsurface salinity structure in the Indian Ocean using satellite observations . Journal of Oceanology and Limnology , 42 ( 2 ): 377 - 389 , https://doi.org/10.1007/s00343-023-3063-z https://doi.org/10.1007/s00343-023-3063-z .

Qi J F , Xie B W , Li D L et al . 2023b . Estimating thermohaline structures in the tropical Indian Ocean from surface parameters using an improved CNN model. Frontiers in Marine Science , 10 : 1181182 , https://doi.org/10.3389/fmars.2023.1181182 https://doi.org/10.3389/fmars.2023.1181182 .

Qi J F , Xie B W , Yang D Z et al . 2024b . Deep learning-driven forecasting of daily sea surface temperatures in the South China Sea . In: Proceedings of 2024 Photonics & Electromagnetics Research Symposium (PIERS) . IEEE, Chengdu . p. 1 - 6 , https://doi.org/10.1109/PIERS62282.2024.10617964 https://doi.org/10.1109/PIERS62282.2024.10617964 .

Qi J F , Zhang L L , Yin B S et al . 2023c . Advancing ocean subsurface thermal structure estimation in the Pacific Ocean: a multi-model ensemble machine learning approach. Dynamics of Atmospheres and Oceans , 104 : 101403 , https://doi.org/10.1016/j.dynatmoce.2023.101403 https://doi.org/10.1016/j.dynatmoce.2023.101403 .

Qiao F L , Yuan Y L , Yang Y Z et al . 2004 . Wave-induced mixing in the upper ocean: distribution and application to a global ocean circulation model . Geophysical Research Letters , 31 ( 11 ), https://doi.org/10.1029/2004gl019824.

Ren Y B , Li X F . 2023 . Predicting the daily sea ice concentration on a subseasonal scale of the pan-Arctic during the melting season by a deep learning model . IEEE Transactions on Geoscience and Remote Sensing , 61 : 1 - 15 , https://doi.org/10.1109/tgrs.2023.3279089 https://doi.org/10.1109/tgrs.2023.3279089 .

Saji N H , Goswami B N , Vinayachandran P N et al . 1999 . A dipole mode in the tropical Indian Ocean . Nature , 401 ( 6751 ): 360 - 363 , https://doi.org/10.1038/43854 https://doi.org/10.1038/43854 .

Shao Q , Li W , Han G J et al . 2021 . A deep learning model for forecasting sea surface height anomalies and temperatures in the South China Sea . Journal of Geophysical Research: Oceans , 126 ( 7 ): e2021 JC 017515 , https://doi.org/10.1029/2021jc017515 https://doi.org/10.1029/2021jc017515 .

Shi X J , Chen Z R , Wang H et al . 2015 . Convolutional LSTM network: a machine learning approach for precipitation nowcasting . In: Proceedings of the 29th International Conference on Neural Information Processing Systems . MIT Press , Montreal . p. 802 - 810 .

Sunder S , Ramsankaran R , Ramakrishnan B . 2020 . Machine learning techniques for regional scale estimation of high-resolution cloud-free daily sea surface temperatures from MODIS data . ISPRS Journal of Photogrammetry and Remote Sensing , 166 : 228 - 240 , https://doi.org/10.1016/j.isprsjprs.2020.06.008 https://doi.org/10.1016/j.isprsjprs.2020.06.008 .

Talley L D , Pickard G L , Emery W J et al . 2011 . Introduction to descriptive physical oceanography . In: Talley L D, Pickard G L, Emery W J et al. eds . Descriptive Physical Oceanography. 6th edn. Academic Press, London , p. 1 - 6 , https://doi.org/10.1016/b978-0-7506-4552-2.10001-0 https://doi.org/10.1016/b978-0-7506-4552-2.10001-0 .

Wang G J , Cai W J , Gan B L et al . 2017 . Continued increase of extreme ElNiño frequency long after 1.5 °C warming stabilization . Nature Climate Change , 7 ( 8 ): 568 - 572 , https://doi.org/10.1038/nclimate3351 https://doi.org/10.1038/nclimate3351 .

Webster P J , Holland G J , Curry J A et al . 2005 . Changes in tropical cyclone number, duration, and intensity in a warming environment . Science , 309 ( 5742 ): 1844 - 1846 , https://doi.org/10.1126/science.1116448 https://doi.org/10.1126/science.1116448 .

Wolff S , O’Donncha F , Chen B . 2020 . Statistical and machine learning ensemble modelling to forecast sea surface temperature. Journal of Marine Systems , 208 : 103347 , https://doi.org/10.1016/j.jmarsys.2020.103347 https://doi.org/10.1016/j.jmarsys.2020.103347 .

Wu Z Y , Jiang C B , Conde M et al . 2019 . Hybrid improved empirical mode decomposition and BP neural network model for the prediction of sea surface temperature . Ocean Science , 15 ( 2 ): 349 - 360 , https://doi.org/10.5194/os-15-349-2019 https://doi.org/10.5194/os-15-349-2019 .

Xiao C J , Chen N C , Hu C L et al . 2019 . Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach. Remote Sensing of Environment , 233 : 111358 , https://doi.org/10.1016/j.rse.2019.111358 https://doi.org/10.1016/j.rse.2019.111358 .

Xiao L , Yang P H , Wang Y X et al . 2024 . Attention adaptive temporal graph convolutional network for long-term seasonal sea surface temperature forecasting . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 17 : 19003 - 19015 , https://doi.org/10.1109/jstars.2024.3471826 https://doi.org/10.1109/jstars.2024.3471826 .

Xie B W , Qi J F , Yang S G et al . 2024 . Sea surface temperature and marine heat wave predictions in the South China Sea: a 3D U-Net deep learning model integrating multi-source data . Atmosphere , 15 ( 1 ): 86 , https://doi.org/10.3390/atmos15010086 https://doi.org/10.3390/atmos15010086 .

Xu S , Dai D J , Cui X R et al . 2023 . A deep learning approach to predict sea surface temperature based on multiple modes. Ocean Modelling , 181 : 102158 , https://doi.org/10.1016/j.ocemod.2022.102158 https://doi.org/10.1016/j.ocemod.2022.102158 .

Yan J N , Mu L , Wang L Z et al . 2020 . Temporal convolutional networks for the advance prediction of ENSO . Scientific Reports , 10 ( 1 ): 8055 , https://doi.org/10.1038/s41598-020-65070-5 https://doi.org/10.1038/s41598-020-65070-5 .

Zhang K , Geng X P , Yan X H . 2020 . Prediction of 3-D ocean temperature by multilayer convolutional LSTM . IEEE Geoscience and Remote Sensing Letters , 17 ( 8 ): 1303 - 1307 , https://doi.org/10.1109/lgrs.2019.2947170 https://doi.org/10.1109/lgrs.2019.2947170 .

Zhang Q , Wang H , Dong J Y et al . 2017 . Prediction of Sea surface temperature using long short-term memory . IEEE Geoscience and Remote Sensing Letters , 14 ( 10 ): 1745 - 1749 , https://doi.org/10.1109/lgrs.2017.2733548 https://doi.org/10.1109/lgrs.2017.2733548 .

Zou H , Yang Y H . 2004 . Combining time series models for forecasting . International Journal of Forecasting , 20 ( 1 ): 69 - 84 , https://doi.org/10.1016/s0169-2070(03)00004-9 https://doi.org/10.1016/s0169-2070(03)00004-9 .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

A physics-enhanced deep-learning model for estimating turbid shallow water depth from SAR images

Prediction of sea surface pCO₂ in the South China Sea using Spatiotemporal Convolutional LSTM model

Deep neural network based on adversarial training for short-term high-resolution precipitation nowcasting from radar echo images

Characteristics and possible influential factors of marine heat wave in the Bohai Sea

Numerical Studies on Effects of V-Shaped Leading Edge on Incident Shock Wave Boundary Layer Interaction

Related Author

Bowen XIE

Tian MA

Qing XU

Xiaobin YIN

Yan LI

Letian LÜ

Kaiguo FAN

Shuang LI

Related Institution

College of Marine Technology/Sanya Oceanographic Institution, Ocean University of China

Laboratory for Regional Oceanography and Numerical Modeling, Qingdao Marine Science and Technology Center

National Key Laboratory of Intelligent Spatial Information

Ocean College, Zhejiang University

Marine Science and Technology College, Zhejiang Ocean University

Address：Editorial Office of JOL, 88 Haijun Rd. Qingdao, 266000, China
Tel：+86-532-82898754 Email：jol@qdio.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰