A Prediction Model of Significant Wave Height in the South China Sea Based on Attention Mechanism
A Prediction Model of Significant Wave Height in the South China Sea Based on Attention Mechanism
复制标题
基于注意力机制的南海有效波高预测模型
DOI：
10.3389/fmars.2022.895212
复制
发表时间：
2022-06
影响因子：
3.7
通讯作者：
Gengkun Wu
中科院分区：
文献类型：
--
作者：
Peng Hao;Shuang Li;Chengcheng Yu;Gengkun Wu
有效波高预报在渔业、勘探、发电、海洋运输等海洋工程领域具有重要意义。传统的基于数值模型的SWH预测方法不能达到很高的精度。另外，目前的SWH预测方法大都局限于单点SWH预测，没有考虑区域SWH预测。为了探索一种新的SWH预测方法，提出了一种基于注意机制的区域SWH深度神经网络预测模型，即CBA-Net。在这项研究中，ERA 5数据集的风和波高在南海2011年至2018年被用作输入特征来训练模型，以评估SWH预测性能在1小时，12小时，和24小时。结果表明，单一使用卷积神经网络不能准确预测SWH。在加入Bi-LSTM层和注意力机制后，SWH的预测得到了很大的改善。在CBA-Net的1h SWH预测中，SARMSE、SAMAPE、SACC分别为0.299、0.136、0.971。与未使用注意力机制的CNN + Bi-LSTM方法相比，SARMSE和SAMAPE分别降低了43.4%和48.7%，而SACC增加了5%。CBA-Net的12 h SWH预测SARMSE、SAMAPE和SACC分别为0.379、0.177、0.954。在24 h SWH预测中，CBA-Net的SARMSE、SAMAPE和SACC分别为0.500、0.236、0.912。虽然随着预测时间的增加，性能略低于12 h，但预测误差仍维持在较小的水平，仍优于其他方法。
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.
登录
查看更多内容
DOI：
--
发表时间：
2014-09
期刊：
ArXiv
影响因子：
--
作者：
Wojciech Zaremba;I. Sutskever;O. Vinyals
通讯作者：
Wojciech Zaremba;I. Sutskever;O. Vinyals
DOI：
10.1186/1757-1626-3-38
发表时间：
2010-01-28
期刊：
Cases journal
影响因子：
--
作者：
Tuli N
通讯作者：
Tuli N
通过分解确定性和随机分量改进有效波高的短期预测
影响因子：
8.7
作者：
Huang Weinan;Dong Sheng
通讯作者：
Dong Sheng
影响因子：
5
作者：
Raj, Nawin;Brown, Jason
通讯作者：
Brown, Jason
DOI：
10.23919/saiee.2019.8643022
发表时间：
2019-03
期刊：
JDDG: Journal der Deutschen Dermatologischen Gesellschaft
影响因子：
--
作者：
通讯作者：
--