Abstract
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.
Highlights
To evaluate the effectiveness and efficiency of the proposed method, the performance of the proposed method based on the Simple Recurrent Unit (SRU) deep network was compared with that of several existing models, including BP (He et al, 2018), Long Short-Term Memory (LSTM) (Graves, 2012), Gated Recurrent Unit (GRU) (Li et al, 2021), and the original SRU (Lei et al, 2018) models without optimization and parallel computing
The performance of the original SRU network without parallel computing was considered mainly because in most scenarios parallel computing is supported in marine survey platforms and equipment
Especially for small survey vessels or on small islands, high performance equipment is not readily available and parallel computing is not supported. For these situations, it is necessary to ensure that the SRU framework can be applied for prediction of the sea surface height anomaly (SSHA)
Summary
Studies have shown that in recent decades the global sea-level has changed from a relatively low average rate (0.4 mm/a) of increase in the past two thousand years to a much higher rate (3.6 mm/a) (Kittel et al, 2021). The global average rate of rise in sealevel for the period 1993–2019 was 3.24 ± 0.3 mm/a; in the same period, the rate of rise of sea-level along China’s coast was 3.9 mm/a (Kappelle, 2020). In the last 10 years, the average sealevel of China’s coastal areas has been at a high level in the past 40 years, being about 100 mm higher than the average sea-level in 1980–1989. Due to the shallow water of the Bohai Sea (average 18 m), the rate of rise of the sea-level in this area for 1980– 2019 was 3.7 mm/a. In the 30 years, the sea-level of the Bohai Sea will rise by 55–180 mm (Tang et al, 2021)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
