{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T02:33:27Z","timestamp":1783132407383,"version":"3.54.6"},"reference-count":46,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T00:00:00Z","timestamp":1597881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Program on Global Change and Air\u2013Sea Interaction","award":["GASI-02-PACINDYGST2-03"],"award-info":[{"award-number":["GASI-02-PACINDYGST2-03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Sea surface temperature (SST) in the China Seas has shown an enhanced response in the accelerated global warming period and the hiatus period, causing local climate changes and affecting the health of coastal marine ecological systems. Therefore, SST distribution prediction in this area, especially seasonal and yearly predictions, could provide information to help understand and assess the future consequences of SST changes. The past few years have witnessed the applications and achievements of neural network technology in SST prediction. Due to the diversity of SST features in the China Seas, long-term and high-spatial-resolution prediction remains a crucial challenge. In this study, we adopted long short-term memory (LSTM)-based deep neural networks for 12-month lead time SST prediction from 2015 to 2018 at a 0.05\u00b0 spatial resolution. Considering the sub-regional differences in the SST features of the study area, we applied self-organizing feature maps (SOM) to classify the SST data first, and then used the classification results as additional inputs for model training and validation. We selected nine models differing in structure and initial parameters for ensemble to overcome the high variance in the output. The statistics of four years\u2019 SST difference between the predicted SST and Operational SST and Ice Analysis (OSTIA) data shows the average root mean square error (RMSE) is 0.5 \u00b0C for a one-month lead time and is 0.66 \u00b0C for a 12-month lead time. The southeast of the study area shows the highest predictable accuracy, with an RMSE less than 0.4 \u00b0C for a 12-month prediction lead time. The results indicate that our model is feasible and provides accurate long-term and high-spatial-resolution SST prediction. The experiments prove that introducing appropriate class labels as auxiliary information can improve the prediction accuracy, and integrating models with different structures and parameters can increase the stability of the prediction results.<\/jats:p>","DOI":"10.3390\/rs12172697","type":"journal-article","created":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T09:35:31Z","timestamp":1597916131000},"page":"2697","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["Prediction of Sea Surface Temperature in the China Seas Based on Long Short-Term Memory Neural Networks"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9131-5929","authenticated-orcid":false,"given":"Li","family":"Wei","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering\/Institute for Advanced Ocean Study, Ocean University of China, Qingdao 266100, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9902-8035","authenticated-orcid":false,"given":"Lei","family":"Guan","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering\/Institute for Advanced Ocean Study, Ocean University of China, Qingdao 266100, China"},{"name":"Sanya Oceanographic Institution, Ocean University of China, Sanya 572024, China"},{"name":"Laboratory for Regional Oceanography and Numerical Modeling, Qingdao National Laboratory for Marine Science and Technology, Qingdao 266237, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqin","family":"Qu","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering\/Institute for Advanced Ocean Study, Ocean University of China, Qingdao 266100, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering\/Institute for Advanced Ocean Study, Ocean University of China, Qingdao 266100, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,8,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Deser, C., Phillips, A.S., and Alexander, M.A. (2010). Twentieth century tropical sea surface temperature trends revisited. Geophys. Res. Lett., 37.","DOI":"10.1029\/2010GL043321"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1525\/elementa.191","article-title":"Projected sea surface temperatures over the 21st century: Changes in the mean, variability and extremes for large marine ecosystem regions of Northern Oceans","volume":"6","author":"Alexander","year":"2018","journal-title":"Elem. Sci. Anth."},{"key":"ref_3","first-page":"500","article-title":"Enhanced Responses of Sea Surface Temperature over Offshore China to Global Warming and Hiatus","volume":"12","author":"Tan","year":"2016","journal-title":"Clim. Chang. Res."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, Q., Li, Y., Li, Q., Liu, Y., and Wang, Y.-N. (2019). Changes in Means and Extreme Events of Sea Surface Temperature in the East China Seas Based on Satellite Data from 1982 to 2017. Atmosphere, 10.","DOI":"10.3390\/atmos10030140"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"8987","DOI":"10.1175\/JCLI-D-16-0016.1","article-title":"Robust Surface Warming in Offshore China Seas and Its Relationship to the East Asian Monsoon Wind Field and Ocean Forcing on Interdecadal Time Scales","volume":"30","author":"Cai","year":"2017","journal-title":"J. Clim."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"5","DOI":"10.3389\/fmars.2018.00026","article-title":"Impacts of Ocean Warming on China\u2019s Fisheries Catches: An Application of \u201cMean Temperature of the Catch\u201d Concept","volume":"5","author":"Liang","year":"2018","journal-title":"Front. Mar. Sci."},{"key":"ref_7","first-page":"174","article-title":"Relationship between the Variation of the Sea Surface Temperature over the South China Sea and the Rainfalls over the Middle and Lower Reaches of the Yangtze River in Jun","volume":"10","author":"Xu","year":"1990","journal-title":"Sci. Meteorol. Sin."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1929","DOI":"10.1175\/BAMS-D-13-00254.1","article-title":"Revisiting the 26.5 \u00b0C sea surface temperature threshold for tropical cyclone development","volume":"96","author":"Davies","year":"2015","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"5522","DOI":"10.1002\/joc.6169","article-title":"Relationship between interannual changes of summer rainfall over Yangtze River Valley and South China Sea\u2013Philippine Sea: Possible impact of tropical zonal sea surface temperature gradient","volume":"39","author":"Ha","year":"2019","journal-title":"Int. J. Clim."},{"key":"ref_10","first-page":"992","article-title":"The relationship between the flood and drought over the lower reach of the Yangtze River valley and the SST over the Indian ocean and the South China Sea","volume":"27","author":"Qiong","year":"2003","journal-title":"Chin. J. Atmos. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Liu, J.Y. (2013). Status of Marine Biodiversity of the China Seas. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0050719"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5","DOI":"10.3389\/fmars.2018.00121","article-title":"Comparison of Remotely-Sensed Sea Surface Temperature and Salinity Products With in Situ Measurements From British Columbia, Canada","volume":"5","author":"Thakur","year":"2018","journal-title":"Front. Mar. Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1109\/TCI.2017.2749184","article-title":"Data-Driven Models for the Spatio-Temporal Interpolation of Satellite-Derived SST Fields","volume":"3","author":"Fablet","year":"2017","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/s003820050156","article-title":"Forecasting the equatorial Pacific sea surface temperatures by neural network models","volume":"13","author":"Tangang","year":"1997","journal-title":"Clim. Dyn."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"7511","DOI":"10.1029\/97JC03414","article-title":"Forecasting regional sea surface temperatures in the tropical Pacific by neural network models, with wind stress and sea level pressure as predictors","volume":"103","author":"Tangang","year":"1998","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1175\/1520-0442(1998)011<0029:FEEANN>2.0.CO;2","article-title":"Forecasting ENSO Events: A Neural Network\u2013Extended EOF Approach","volume":"11","author":"Tangang","year":"1998","journal-title":"J. Clim."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.neunet.2006.01.004","article-title":"Neural network forecasts of the tropical Pacific sea surface temperatures","volume":"19","author":"Wu","year":"2006","journal-title":"Neural Netw."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ali, M.M., Weller, R.A., and Swain, D. (2004). Estimation of ocean subsurface thermal structure from surface parameters: A neural network approach. Geophys. Res. Lett., 31.","DOI":"10.1029\/2004GL021192"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1016\/j.quascirev.2004.07.020","article-title":"Sea-surface temperatures around the Australian margin and Indian Ocean during the Last Glacial Maximum","volume":"24","author":"Barrows","year":"2005","journal-title":"Quat. Sci. Rev."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1016\/j.quascirev.2004.02.018","article-title":"Glacial Mediterranean sea surface temperatures based on planktonic foraminiferal assemblages","volume":"24","author":"Hayes","year":"2005","journal-title":"Quat. Sci. Rev."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Garcia-Gorriz, E., and Garcia-Sanchez, J. (2007). Prediction of sea surface temperatures in the western Mediterranean Sea by neural networks using satellite observations. Geophys. Res. Lett., 34.","DOI":"10.1029\/2007GL029888"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1007\/s10236-017-1032-9","article-title":"Prediction of daily sea surface temperature using efficient neural networks","volume":"67","author":"Patil","year":"2017","journal-title":"Ocean Dyn."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1260\/1759-3131.4.2.133","article-title":"Using Artificial Neural Networks to Forecast Monthly and Seasonal Sea Surface Temperature Anomalies in the Western Indian Ocean","volume":"4","author":"Mahongo","year":"2013","journal-title":"Int. J. Ocean Clim. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.1175\/JTECH-D-15-0213.1","article-title":"Prediction of Sea Surface Temperature by Combining Numerical and Neural Techniques","volume":"33","author":"Patil","year":"2016","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1109\/LGRS.2019.2926992","article-title":"Prediction of Sea Surface Temperature in the South China Sea by Artificial Neural Networks","volume":"17","author":"Wei","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1109\/LGRS.2017.2733548","article-title":"Prediction of Sea Surface Temperature Using Long Short-Term Memory","volume":"14","author":"Zhang","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1109\/LGRS.2017.2780843","article-title":"A CFCC-LSTM Model for Sea Surface Temperature Prediction","volume":"15","author":"Yang","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1441","DOI":"10.1175\/JTECH-D-17-0217.1","article-title":"Basin-Scale Prediction of Sea Surface Temperature with Artificial Neural Networks","volume":"35","author":"Patil","year":"2018","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Gong, S., and Wong, K. (2018). Spatio-Temporal Analysis of Sea Surface Temperature in the East China Sea Using TERRA\/MODIS Products Data. Sea Level Rise and Coastal Infrastructure, IntechOpen.","DOI":"10.5772\/intechopen.73217"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1080\/17538947.2017.1365957","article-title":"The spatiotemporal patterns of sea ice in the Bohai Sea during the winter seasons of 2000\u20132016","volume":"12","author":"Ouyang","year":"2019","journal-title":"Int. J. Digit. Earth"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.dsr.2017.08.003","article-title":"Sea-ice production in the northern Japan Sea","volume":"127","author":"Nihashi","year":"2017","journal-title":"Deep. Sea Res. Part I Oceanogr. Res. Pap."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"6215","DOI":"10.1175\/JCLI-D-11-00648.1","article-title":"Daily, Global, High-Resolution SST and Sea Ice Reanalysis for 1985-2007 Using the Ostia System","volume":"25","author":"Fiedler","year":"2012","journal-title":"J. Clim."},{"key":"ref_33","unstructured":"McLaren, A., Fiedler, E., Roberts-Jones, J., Martin, M., Mao, C., and Good, S. (2020, August 20). Quality Information Document: Global Ocean OSTIA Near Real Time Level 4 Sea Surface Temperature Product, Available online: https:\/\/resources.marine.copernicus.eu\/documents\/QUID\/CMEMS-OSI-QUID-010-001.pdf."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1088\/0031-8949\/39\/1\/027","article-title":"The self-organizing feature maps","volume":"39","author":"Kohonen","year":"1989","journal-title":"Phys. Scr."},{"key":"ref_35","unstructured":"Haykin, S. (2009). Neural Networks and Learning Machines, Pearson Education. 3rd ed."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Oyana, T.J., Achenie, L.E., Cuadros-Vargas, E., Rivers, P.A., and Scott, K.E. (2006). A Mathematical Improvement of the Self-Organizing Map Algorithm. Proceedings from the International Conference on Advances in Engineering and Technology, Elsevier BV.","DOI":"10.1016\/B978-008045312-5\/50057-1"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1002\/2015RG000505","article-title":"Progress on upwelling studies in the China seas","volume":"54","author":"Hu","year":"2016","journal-title":"Rev. Geophys."},{"key":"ref_38","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_39","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1016\/j.ejor.2017.11.054","article-title":"Deep learning with long short-term memory networks for financial market predictions","volume":"270","author":"Fischer","year":"2018","journal-title":"Eur. J. Oper. Res."},{"key":"ref_40","unstructured":"Olah, C. (2020, March 08). Understanding LSTM Networks. Available online: http:\/\/colah.github.io\/posts\/2015-08-Understanding-LSTMs\/."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Bengio, Y. (2012). Practical Recommendations for Gradient-Based Training of Neural Networks: Tricks of the Trade, Springer.","DOI":"10.1007\/978-3-642-35289-8_26"},{"key":"ref_42","first-page":"281","article-title":"Random Search for Hyper-Parameter Optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn Res."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Bishop, C.M. (1995). Neural Networks for Pattern Recognition, Oxford University Press.","DOI":"10.1093\/oso\/9780198538493.001.0001"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_45","unstructured":"(2020, July 01). China Offshore Ocean Climate Monitoring Bulletin. Available online: http:\/\/www.nmefc.cn\/chanpin\/hyqh\/qhjc\/bulletin_201608.pdf."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"e853","DOI":"10.1002\/asl.853","article-title":"What caused the record-breaking warming in East China Seas during August 2016?","volume":"19","author":"Tan","year":"2018","journal-title":"Atmos. Sci. Lett."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/17\/2697\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:04:05Z","timestamp":1760177045000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/17\/2697"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,20]]},"references-count":46,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["rs12172697"],"URL":"https:\/\/doi.org\/10.3390\/rs12172697","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,20]]}}}