AUTHOR=Hou Boyang , Fu Hanjiao , Li Xin , Song Tao , Zhang Zhiyuan 

TITLE=Predicting significant wave height in the South China Sea using the SAC-ConvLSTM model

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 11 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2024.1424714

DOI=10.3389/fmars.2024.1424714

ISSN=2296-7745

ABSTRACT=The precise forecasting of Significant wave height(SWH) is vital to ensure the safety and efficiency of aquatic activities such as ocean engineering, shipping, and fishing. This paper proposes a deep learning model named SAC-ConvLSTM to perform 24-hour prediction with the significant wave height in the South China Sea. The long-term prediction capability of the model is enhanced by using the attention mechanism and context vectors. The experimental results show that the SAC-ConvLSTM model has the best prediction performance compared with other models, with RMSE, MAE, and PCC of 0.2117m, 0.1083m, and 0.9630, respectively, at the 24-hour prediction. In addition, the introduction of wind can improve the accuracy of wave prediction.The SAC-ConvLSTM model also has good prediction performance compared to the ConvLSTM model during extreme weather, especially in coastal areas.