Application of deep learning technique to the sea surface height prediction in the South China Sea

• Published in: Acta oceanologica Sinica Vol. 40; no. 7; pp. 68 - 76
• Main Authors: Song, Tao, Han, Ningsheng, Zhu, Yuhang, Li, Zhongwei, Li, Yineng, Li, Shaotian, Peng, Shiqiu
• Format: Journal Article
• Language: English
• Published: Beijing The Chinese Society of Oceanography 01.07.2021; Springer Nature B.V; College of Computer and Communication Engineering,China University of Petroleum(East China),Qingdao 266580,China; Guangxi Key Laboratory of Marine Disaster in the Beibu Gulf,Bubei Gulf University,Qinzhou 535011,China%State Key Laboratory of Tropical Oceanography,South China Sea Institute of Oceanology,Chinese Academy of Sciences,Guangzhou 510301,China; Key Laboratory of Science and Technology on Operational Oceanography,Chinese Academy of Sciences,Guangzhou 511458,China; Key Laboratory of Science and Technology on Operational Oceanography,Chinese Academy of Sciences,Guangzhou 511458,China%State Key Laboratory of Tropical Oceanography,South China Sea Institute of Oceanology,Chinese Academy of Sciences,Guangzhou 510301,China; Guangxi Key Laboratory of Marine Disaster in the Beibu Gulf,Bubei Gulf University,Qinzhou 535011,China; Southern Marine Science and Engineering Guangdong Laboratory(Guangzhou),Guangzhou 511458,China; Department of Artificial Intelligence,Faculty of Computer Science,Polytechnical University of Madrid,Boadilla del Monte 28660,Madrid,Spain%College of Computer and Communication Engineering,China University of Petroleum(East China),Qingdao 266580,China%State Key Laboratory of Tropical Oceanography,South China Sea Institute of Oceanology,Chinese Academy of Sciences,Guangzhou 510301,China; Southern Marine Science and Engineering Guangdong Laboratory(Guangzhou),Guangzhou 511458,China%State Key Laboratory of Tropical Oceanography,South China Sea Institute of Oceanology,Chinese Academy of Sciences,Guangzhou 510301,China
• Subjects: Climatology; Computation; Deep learning; Earth and Environmental Science; Earth Sciences; Ecology; Eddies; Engineering Fluid Dynamics; Environmental Chemistry; Feature extraction; Learning; Long short-term memory; Marine & Freshwater Sciences; Marine environment; Mesoscale eddies; Ocean models; Oceanography; Oceans; Offshore; Performance prediction; Predictions; Sea surface; Temporal variations; South China Sea; sea surface height prediction; deep learning; convolutional operation; long short term memory
• DOI: 10.1007/s13131-021-1735-0
• ISSN: 0253-505X

A deep-learning-based method, called ConvLSTMP3, is developed to predict the sea surface heights (SSHs). ConvLSTMP3 is data-driven by treating the SSH prediction problem as the one of extracting the spatial-temporal features of SSHs, in which the spatial features are “learned” by convolutional operations while the temporal features are tracked by long short term memory (LSTM). Trained by a reanalysis dataset of the South China Sea (SCS), ConvLSTMP3 is applied to the SSH prediction in a region of the SCS east off Vietnam coast featured with eddied and offshore currents in summer. Experimental results show that ConvLSTMP3 achieves a good prediction skill with a mean RMSE of 0.057 m and accuracy of 93.4% averaged over a 15-d prediction period. In particular, ConvLSTMP3 shows a better performance in predicting the temporal evolution of mesoscale eddies in the region than a full-dynamics ocean model. Given the much less computation in the prediction required by ConvLSTMP3, our study suggests that the deep learning technique is very useful and effective in the SSH prediction, and could be an alternative way in the operational prediction for ocean environments in the future.