{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T08:58:16Z","timestamp":1775725096613,"version":"3.50.1"},"reference-count":35,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T00:00:00Z","timestamp":1710374400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"publisher","award":["2023YFC3107800"],"award-info":[{"award-number":["2023YFC3107800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"publisher","award":["42376190"],"award-info":[{"award-number":["42376190"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"publisher","award":["41876014"],"award-info":[{"award-number":["41876014"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation","doi-asserted-by":"publisher","award":["2023YFC3107800"],"award-info":[{"award-number":["2023YFC3107800"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation","doi-asserted-by":"publisher","award":["42376190"],"award-info":[{"award-number":["42376190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation","doi-asserted-by":"publisher","award":["41876014"],"award-info":[{"award-number":["41876014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>We explore to what extent data-driven prediction models have skills in forecasting daily sea-surface temperature (SST), which are comparable to or perform better than current physics-based operational systems over long-range forecast horizons. Three hybrid deep learning-based models are developed within the South China Sea (SCS) basin by integrating deep neural networks (back propagation, long short-term memory, and gated recurrent unit) with traditional empirical orthogonal function analysis and empirical mode decomposition. Utilizing a 40-year (1982\u20132021) satellite-based daily SST time series on a 0.25\u00b0 grid, we train these models on the first 32 years (1982\u20132013) of detrended SST anomaly (SSTA) data. Their predictive accuracies are then validated using data from 2014 and tested over the subsequent seven years (2015\u20132021). The models\u2019 forecast skills are assessed using spatial anomaly correlation coefficient (ACC) and root-mean-square error (RMSE), with ACC proving to be a stricter metric. A forecast skill horizon, defined as the lead time before ACC drops below 0.6, is determined to be 50 days. The models are equally capable of achieving a basin-wide average ACC of ~0.62 and an RMSE of ~0.48 \u00b0C at this horizon, indicating a 36% improvement in RMSE over climatology. This implies that on average the forecast skill horizon for these models is beyond the available forecast length. Analysis of one model, the BP neural network, reveals a variable forecast skill horizon (5 to 50 days) for each individual day, showing that it can adapt to different time scales. This adaptability seems to be influenced by a number of mechanisms arising from the evident regional and global atmosphere\u2013ocean coupling variations on time scales ranging from intraseasonal to decadal in the SSTA of the SCS basin.<\/jats:p>","DOI":"10.3390\/rs16061034","type":"journal-article","created":{"date-parts":[[2024,3,15]],"date-time":"2024-03-15T04:47:05Z","timestamp":1710478025000},"page":"1034","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["SST Forecast Skills Based on Hybrid Deep Learning Models: With Applications to the South China Sea"],"prefix":"10.3390","volume":"16","author":[{"given":"Mengmeng","family":"Zhang","sequence":"first","affiliation":[{"name":"Tianjin Key Laboratory for Marine Environmental Research and Service, School of Marine Science and Technology, Tianjin University, Tianjin 300072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8442-7148","authenticated-orcid":false,"given":"Guijun","family":"Han","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory for Marine Environmental Research and Service, School of Marine Science and Technology, Tianjin University, Tianjin 300072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Wu","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory for Marine Environmental Research and Service, School of Marine Science and Technology, Tianjin University, Tianjin 300072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoliang","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory for Marine Environmental Research and Service, School of Marine Science and Technology, Tianjin University, Tianjin 300072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8059-5010","authenticated-orcid":false,"given":"Qi","family":"Shao","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory for Marine Environmental Research and Service, School of Marine Science and Technology, Tianjin University, Tianjin 300072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6116-7718","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory for Marine Environmental Research and Service, School of Marine Science and Technology, Tianjin University, Tianjin 300072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lige","family":"Cao","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory for Marine Environmental Research and Service, School of Marine Science and Technology, Tianjin University, Tianjin 300072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory for Marine Environmental Research and Service, School of Marine Science and Technology, Tianjin University, Tianjin 300072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanqiu","family":"Dong","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory for Marine Environmental Research and Service, School of Marine Science and Technology, Tianjin University, Tianjin 300072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zenghua","family":"Ji","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory for Marine Environmental Research and Service, School of Marine Science and Technology, Tianjin University, Tianjin 300072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1038\/s41586-019-0912-1","article-title":"Deep learning and process understanding for data-driven Earth system science","volume":"566","author":"Reichstein","year":"2019","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"eaba1482","DOI":"10.1126\/sciadv.aba1482","article-title":"Purely satellite data-driven deep learning forecast of complicated tropical instability waves","volume":"6","author":"Zheng","year":"2020","journal-title":"Sci. Adv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4214","DOI":"10.1080\/01431161.2018.1454623","article-title":"Prediction of daily sea surface temperature using artificial neural networks","volume":"39","author":"Aparna","year":"2018","journal-title":"Int. J. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"111358","DOI":"10.1016\/j.rse.2019.111358","article-title":"Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach","volume":"233","author":"Xiao","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e2020EA001558","DOI":"10.1029\/2020EA001558","article-title":"Ocean reanalysis data-driven deep learning forecast for sea surface multivariate in the South China Sea","volume":"8","author":"Shao","year":"2021","journal-title":"Earth Space Sci."},{"key":"ref_6","first-page":"1","article-title":"Mid-term simultaneous spatiotemporal prediction of sea surface height anomaly and sea surface temperature using satellite data in the South China Sea","volume":"19","author":"Shao","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e2020EA001199","DOI":"10.1029\/2020EA001199","article-title":"The Navy\u2019s Earth System Prediction Capability: A new global coupled atmosphere-ocean-sea ice prediction system designed for daily to subseasonal forecasting","volume":"8","author":"Barton","year":"2021","journal-title":"Earth Space Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1873","DOI":"10.1007\/s00382-016-3178-4","article-title":"Regime shift of the South China Sea SST in the Late 1990s","volume":"48","author":"Thompson","year":"2017","journal-title":"Clim. Dyn."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"5473","DOI":"10.1175\/2007JCLI1824.1","article-title":"Daily high-resolution-blended analyses for sea surface temperature","volume":"20","author":"Reynolds","year":"2007","journal-title":"J. Clim."},{"key":"ref_10","unstructured":"Thomson, R.E., and Emery, W.J. (2014). Data Analysis Methods in Physical Oceanography, Elsevier. [3rd. ed.]."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"C11","DOI":"10.1029\/2005JC003276","article-title":"Trends and interannual variability of the South China Sea Surface winds, surface height, and surface temperature in the recent decade","volume":"111","author":"Fang","year":"2006","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1007\/s13131-019-1416-4","article-title":"Trends of sea surface temperature and sea surface temperature fronts in the South China Sea during 2003\u20132017","volume":"38","author":"Yu","year":"2019","journal-title":"Acta Oceanol. Sin."},{"key":"ref_13","first-page":"1","article-title":"Empirical orthogonal functions and statistical weather prediction","volume":"Volume 1","author":"Lorenz","year":"1956","journal-title":"Statistical Forecasting Project Report"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Torres, M.E., Colominas, M.A., Schlotthauer, G., and Flandrin, P. (2011, January 22\u201327). A Complete Ensemble Empirical Mode Decomposition with Adaptive Noise. Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic.","DOI":"10.1109\/ICASSP.2011.5947265"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1126\/science.ade8450","article-title":"Experimentally realized in situ backpropagation for deep learning in photonic neural networks","volume":"380","author":"Pai","year":"2023","journal-title":"Science"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"105675","DOI":"10.1016\/j.engappai.2022.105675","article-title":"Assessment of the spatiotemporal prediction capabilities of machine learning algorithms on sea surface temperature data: A comprehensive study","volume":"118","author":"Kartal","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e2021JC017515","DOI":"10.1029\/2021JC017515","article-title":"A deep learning model for forecasting sea surface height anomalies and temperatures in the South China Sea","volume":"126","author":"Shao","year":"2021","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1175\/1520-0493(2003)131<0335:NWPMPO>2.0.CO;2","article-title":"Numerical weather prediction model performance over high southern latitudes","volume":"131","author":"Pendlebury","year":"2003","journal-title":"Mon. Weather. Rev."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1038\/s43247-021-00151-5","article-title":"Ensemble forecasting greatly expands the prediction horizon for ocean mesoscale variability","volume":"2","author":"Thoppil","year":"2021","journal-title":"Commun. Earth Environ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"118601","DOI":"10.1016\/j.apenergy.2022.118601","article-title":"Carbon Price Forecasting Based on CEEMDAN and LSTM","volume":"311","author":"Zhou","year":"2022","journal-title":"Appl. Energy"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"19751","DOI":"10.1038\/s41598-019-56452-5","article-title":"Short-Term Rainfall Forecast Model Based on the Improved BP\u2013NN Algorithm","volume":"9","author":"Liu","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zor, K., and Bulu\u015f, K. (2021, January 29\u201330). A Benchmark of GRU and LSTM Networks for Short-Term Electric Load Forecasting. Proceedings of the 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), Online.","DOI":"10.1109\/3ICT53449.2021.9581373"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"102906","DOI":"10.1016\/j.resourpol.2022.102906","article-title":"Medium- to Long-Term Nickel Price Forecasting Using LSTM and GRU Networks","volume":"78","author":"Ozdemir","year":"2022","journal-title":"Resour. Policy"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1175\/1520-0477(1998)079<0061:APGTWA>2.0.CO;2","article-title":"A practical guide to wavelet analysis","volume":"79","author":"Torrence","year":"1998","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"7986","DOI":"10.1038\/s41598-020-64785-9","article-title":"Tendencies, variability and persistence of sea surface temperature anomalies","volume":"10","author":"Bulgin","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"D01105","DOI":"10.1029\/2008JD010723","article-title":"Decadal and seasonal dependence of North Pacific sea surface temperature persistence","volume":"114","author":"Ding","year":"2009","journal-title":"J. Geophys. Res. (Atmos.)"},{"key":"ref_28","first-page":"226","article-title":"Harmonic analysis of sea surface temperature and wind stress in the vicinity of the maritime continent","volume":"17","author":"Du","year":"2003","journal-title":"J. Meteorol. Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5797","DOI":"10.1029\/2017JC013657","article-title":"Annual and semiannual cycles of diurnal warming of sea surface temperature in the South China Sea","volume":"123","author":"Yan","year":"2018","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"12486","DOI":"10.1002\/2015JD024199","article-title":"Covariations of SST and surface heat flux on 10\u201320 day and 30\u201360 day time scales over the South China Sea and western North Pacific","volume":"120","author":"Wu","year":"2015","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"GL037174","DOI":"10.1029\/2009GL037174","article-title":"Decadal change in intraseasonal variability over the South China Sea","volume":"36","author":"Kajikawa","year":"2009","journal-title":"Geophys. Res. Lett."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1007\/s00376-020-0211-7","article-title":"Western North Pacific tropical cyclone database created by the China Meteorological Administration","volume":"38","author":"Lu","year":"2021","journal-title":"Adv. Atmos. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3798","DOI":"10.1175\/MWR-D-10-05019.1","article-title":"Sea surface temperature response to tropical cyclones","volume":"139","author":"Dare","year":"2011","journal-title":"Mon. Weather. Rev."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"5952","DOI":"10.1175\/JCLI-D-14-00651.1","article-title":"Tropical cyclone\u2013induced ocean response: A comparative study of the South China Sea and tropical Northwest Pacific","volume":"28","author":"Mei","year":"2015","journal-title":"J. Clim."},{"key":"ref_35","unstructured":"Klie, H. (2024, March 09). A Tale of Two Approaches: Physics-Based vs. Data-Driven Models. Available online: https:\/\/jpt.spe.org\/twa\/a-tale-of-two-approaches-physics-based-vs-data-driven-models."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/6\/1034\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:13:44Z","timestamp":1760105624000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/6\/1034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,14]]},"references-count":35,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["rs16061034"],"URL":"https:\/\/doi.org\/10.3390\/rs16061034","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,14]]}}}