A Prediction Model of Significant Wave Height in the South China Sea Based on Attention Mechanism

被引:12
|
作者
Hao, Peng [1 ]
Li, Shuang [1 ]
Yu, Chengcheng [1 ]
Wu, Gengkun [2 ]
机构
[1] Zhejiang Univ, Inst Phys Oceanog & Remote Sensing, Ocean Coll, Zhoushan, Peoples R China
[2] Shandong Univ Sci & Technol, Coll Comp Sci & Engn, Qingdao, Peoples R China
基金
中国国家自然科学基金;
关键词
CBA-Net; significant wave height (SWH); deep learning; South China Sea; attention mechanism; STATISTICAL-MODELS; TERM PREDICTION; NEURAL-NETWORKS; SIMULATION; FORECASTS;
D O I
10.3389/fmars.2022.895212
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Significant wave height (SWH) prediction plays an important role in marine engineering fields such as fishery, exploration, power generation, and ocean transportation. Traditional SWH prediction methods based on numerical models cannot achieve high accuracy. In addition, the current SWH prediction methods are largely limited to single-point SWH prediction, without considering regional SWH prediction. In order to explore a new SWH prediction method, this paper proposes a deep neural network model for regional SWH prediction based on the attention mechanism, namely CBA-Net. In this study, the wind and wave height of the ERA5 data set in the South China Sea from 2011 to 2018 were used as input features to train the model to evaluate the SWH prediction performance at 1 h, 12 h, and 24 h. The results show that the single use of a convolutional neural network cannot accurately predict SWH. After adding the Bi-LSTM layer and attention mechanism, the prediction of SWH is greatly improved. In the 1 h SWH prediction using CBA-Net, SARMSE, SAMAPE, SACC are 0.299, 0.136, 0.971 respectively. Compared with the CNN + Bi-LSTM method that does not use the attention mechanism, SARMSE and SAMAPE are reduced by 43.4% and 48.7%, respectively, while SACC is increased by 5%. In the 12 h SWH prediction, SARMSE, SAMAPE, and SACC of CBA-Net are 0.379, 0.177, 0.954 respectively. In the 24 h SWH prediction, SARMSE, SAMAPE, and SACC of CBA-Net are 0.500, 0.236, 0.912 respectively. Although with the increase of prediction time, the performance is slightly lower than that of 12 h, the prediction error is still maintained at a small level, which is still better than other methods.
引用
收藏
页数:12
相关论文
共 50 条
  • [41] Revisiting the seasonal wave height variability in the South China Sea with merged satellite altimetry observations
    SU Hui
    WEI Chunlei
    JIANG Shaocai
    LI Peiliang
    ZHAI Fangguo
    Acta Oceanologica Sinica, 2017, 36 (11) : 38 - 50
  • [42] Revisiting the seasonal wave height variability in the South China Sea with merged satellite altimetry observations
    Hui Su
    Chunlei Wei
    Shaocai Jiang
    Peiliang Li
    Fangguo Zhai
    Acta Oceanologica Sinica, 2017, 36 : 38 - 50
  • [43] An attention mechanism model based on positional encoding for the prediction of ship maneuvering motion in real sea state
    Lei Dong
    Hongdong Wang
    Jiankun Lou
    Journal of Marine Science and Technology, 2024, 29 : 136 - 152
  • [44] Landslide Displacement Prediction Based on a Deep Learning Model Considering the Attention Mechanism
    Guo Z.
    Yang Y.
    He J.
    Huang D.
    Diqiu Kexue - Zhongguo Dizhi Daxue Xuebao/Earth Science - Journal of China University of Geosciences, 2024, 49 (05): : 1665 - 1678
  • [45] On the Annual Cycle Characteristics of the Sea Surface Height in South China Sea
    Liu Q.
    Jia Y.
    Wang X.
    Yang H.
    Advances in Atmospheric Sciences, 2001, 18 (4) : 613 - 621
  • [46] On the annual cycle characteristics of the sea surface height in South China Sea
    Liu, QY
    Jia, YL
    Wang, XH
    Yang, HJ
    ADVANCES IN ATMOSPHERIC SCIENCES, 2001, 18 (04) : 613 - 622
  • [47] A Hybrid Model of Conformer and LSTM for Ocean Wave Height Prediction
    Xiao, Jiawei
    Lu, Peng
    APPLIED SCIENCES-BASEL, 2024, 14 (14):
  • [48] Shear wave velocity prediction based on 1DCNN-BiLSTM network with attention mechanism
    Feng, Gang
    Liu, Wen-Qing
    Yang, Zhe
    Yang, Wei
    FRONTIERS IN EARTH SCIENCE, 2024, 12
  • [49] Deep Learning on the Sphere for Multi-model Ensembling of Significant Wave Height
    Littardi, Andrea
    Hildeman, Anders
    Nicolaou, Mihalis A.
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 3828 - 3832
  • [50] Research on berth occupancy prediction model based on attention mechanism
    Wang Z.
    Xue W.
    Niu Y.
    Cui Y.
    Sun Q.
    Hei X.
    Tongxin Xuebao/Journal on Communications, 2020, 41 (12): : 182 - 192