Short- to Medium-Term Sea Surface Height Prediction in the Bohai Sea Using an Optimized Simple Recurrent Unit Deep Network
Short- to Medium-Term Sea Surface Height Prediction in the Bohai Sea Using an Optimized Simple Recurrent Unit Deep Network
复制标题
利用优化的简单循环单元深度网络进行渤海中短期海面高度预测
DOI：
10.3389/fmars.2021.672280
复制
发表时间：
2021-09
影响因子：
3.7
通讯作者：
Xiaoyi Jiang
中科院分区：
文献类型：
--
作者：
Pengfei Ning;Cuicui Zhang;Xuefeng Zhang;Xiaoyi Jiang
全球变暖加剧了海平面的上升，并在中国所在的渤海东北部等浅海海域造成了严重的生态灾难。海面高度异常(SSHA)的预报在海平面变化监测中具有重要意义。然而，由于动态物理现象的发生，SSHA的非线性对目前旨在提供SSHA准确预测的方法(如ROMS，MITgCM)提出了挑战。在这项研究中，我们开发了一个优化的简单递归单元(SRU)深层网络，用于利用存档验证和国际卫星海洋学(AVISO)数据进行SSHA的中短期预报。由于SRU的并行结构，深度网络的计算复杂度可以在很大程度上得到降低，这使得中短期预测更加有效。为了避免过拟合和梯度的消失，采用跳跃连接策略对模型进行优化，显著提高了预测精度。在渤海海域对该模型进行了详细的实验，结果表明：(I)该模型在1天、5天、20天和300天的预测中显著优于BP(BP)、RNN(递归神经网络)、LSTM(长短期记忆)和GRU(门控递归单元)算法等现有深度学习方法；(Ii)可以实时预测SSHA的短期趋势(次日或2天)；以及(Iii)在几秒钟内实现对未来5-20天的中期预测，并显示出需要中长期预测的应用的巨大潜力。据我们所知，这是第一篇研究SRU深度学习模型对短期和中期SSHA预测的有效性的论文。
Global warming has intensified the rise in sea levels and has caused severe ecological disasters in shallow coastal waters such as the Northeastern China's Bohai Sea. The prediction of the sea surface height anomaly (SSHA) has great significance in the context of monitoring changes in sea levels. However, the non-linearity of SSHA due to the occurrence of dynamic physical phenomena poses a challenge to current methods(e.g., ROMS, MITgcm) that aim to provide accurate predictions of SSHA. In this study, we have developed an optimized Simple Recurrent Unit (SRU) deep network for the short- to medium-term prediction of the SSHA using Archiving Validation and International of Satellites Oceanographic (AVISO) data. Thanks to the parallel structure of the SRU, the computational complexity of the deep network can be reduced to a considerable extent and this makes the short- to medium-term prediction more efficient. To avoid over-fitting and a vanishing gradient, a skip-connection strategy has been utilized for model optimization, and this improves significantly the accuracy of prediction. Detailed experiments were carried out in the Bohai Sea to evaluate the proposed model and it was demonstrated that the proposed framework (i) outperformed significantly the current deep learning methods such as the BP (Backpropagation), the RNN (Recurrent Neural Network), the LSTM (Long Short-term Memory), and the GRU (Gated Recurrent Unit) algorithms for 1, 5, 20, and 300-day prediction; (ii) can predict the short-term trend in the SSHA (for the next day or 2 days) in real time; and (iii) achieves medium-term prediction in seconds for the next 5–20 days and shows great potential for applications requiring medium- to long-term predictions. To the best of our knowledge, this is the first paper that investigates the effectiveness of the SRU deep learning model for short- to medium-term SSHA predictions.
登录
查看更多内容
影响因子：
5.3
作者：
Xingxing Wang;Yingmin Wang;M. Tan;F. Cai
通讯作者：
Xingxing Wang;Yingmin Wang;M. Tan;F. Cai
DOI：
10.1109/sc.2016.4
发表时间：
2016-11
期刊：
SC16: International Conference for High Performance Computing, Networking, Storage and Analysis
影响因子：
--
作者：
F. Qiao;Wei Zhao;Xunqiang Yin;Xiaomeng Huang;Xin Liu;Qi Shu;Guansuo Wang;Zhenya Song;Xinfang Li
通讯作者：
F. Qiao;Wei Zhao;Xunqiang Yin;Xiaomeng Huang;Xin Liu;Qi Shu;Guansuo Wang;Zhenya Song;Xinfang Li
DOI：
10.1109/jstars.2021.3054395
发表时间：
2021
影响因子：
5.5
作者：
Wei Tang;Wei Zhan;Bowen Jin;M. Motagh;Yubin Xu
通讯作者：
Wei Tang;Wei Zhan;Bowen Jin;M. Motagh;Yubin Xu
DOI：
10.1007/978-981-10-3945-4_3
发表时间：
2017
期刊：
--
影响因子：
--
作者：
Z. Wang;Jing Wu;Changxin Liu;Gaoxiang Gu
通讯作者：
Z. Wang;Jing Wu;Changxin Liu;Gaoxiang Gu
DOI：
10.18653/v1/d18-1477
发表时间：
2017-09
期刊：
--
影响因子：
--
作者：
Tao Lei;Yu Zhang;Sida I. Wang;Huijing Dai;Yoav Artzi
通讯作者：
Tao Lei;Yu Zhang;Sida I. Wang;Huijing Dai;Yoav Artzi