Significant wave height (SWH) is a key parameter for monitoring the state of waves. Accurate and long-term SWH forecasting is significant to maritime shipping and coastal engineering. This study proposes a transformer model based on an attention mechanism to achieve the forecasting of SWHs. The transformer model can capture the contextual information and dependencies between sequences and achieves continuous time series forecasting. Wave scale classification is carried out according to the forecasting results, and the results are compared with gated recurrent unit (GRU) and long short-term memory (LSTM) machine-learning models and the key laboratory of MArine Science and NUmerical Modeling (MASNUM) numerical wave model. The results show that the machine-learning models outperform the MASNUM within 72 h, with the transformer being the best model. For continuous 12 h, 24 h, 36 h, 48 h, 72 h, and 96 h forecasting, the average mean absolute errors (MAEs) of the test sets were, respectively, 0.139 m, 0.186 m, 0.223 m, 0.254 m, 0.302 m, and 0.329 m, and the wave scale classification accuracies were, respectively, 91.1%, 99.4%, 86%, 83.3%, 78.9%, and 77.5%. The experimental results validate that the transformer model can achieve continuous and accurate SWH forecasting, as well as accurate wave scale classification and early warning of waves, providing technical support for wave monitoring.

The whitecap coverage at the sea surface is affected by the ratio of kinetic energy to potential energy, θ, the wave spectrum width parameter, ρ, and other factors. This paper validates an improved statistical theory for surface whitecap coverage. Based on the theoretical analysis, we find that the whitecap coverage is more sensitive to ρ than to θ, and the improved statistical theory for surface whitecap coverage is suitable in regions of rough winds and waves. The satellite-derived whitecap coverage data in the westerly wind zone is used to validate the improved theory. The comparison between the results from theory and observations displays a better performance from the improved theory relative to the other methods tested.

For improved prevention and reduction of marine disasters, China’s marine authorities and emergency response agencies require a solution that provides risk assessment, early warning, and decision-making support. This paper proposes a comprehensive approach to disaster assessment that involves automated long-term operation, a spatial information visualization method and systematic integration. The proposed approach provides functions for numerical ocean models with forecast results, automated processing of massive data, multiple disaster/element coupled assessment, and multidimensional display and expression. With regard to storm surge disasters, the approach proposed in this paper adopts a four-tier structure and the functions of each tier are described separately. The original data are comprised of a combination of statistical analysis data and real-time data obtained from the unstructured grid Finite Volume Community Ocean Model. Automated data processing methods and assessment theories incorporating an indicator system and weighted parameters are used for the assessment. By applying 2D/3D visualization technology, assessment results are displayed via several modes for ease of operation and comprehension. The validity of the approach was verified by applying it to Typhoon Hato (No. 1713). Compared with the results of the post-disaster investigation, the assessment results of the proposed approach proved the reliability of the system.

Marine dynamic disasters, such as storm surges and huge waves, can cause large economic and human losses. The assessment of marine dynamic disasters is, thus, important, but improvements to its reliability are needed. The current study improved and integrated the assessment from the perspective of multi-factor coupling. Using a weighted index system, a marine dynamic disaster assessment indicator system suitable for China’s coastal waters was established, and a method for calculating the weight of disaster indicators was proposed from the perspective of rapid assessment. To reduce the assessment deviation in coastal waters, a multi-factor coupling algorithm was proposed. This algorithm obtained amplitude variations of wave orbital motion in horizontal and vertical directions, which was used to evaluate the influence of background current and terrain slope on coastal ocean waves. Landsat 8 remote sensing images were used to carry out an object-oriented extraction of raft and cage aquaculture areas in China’s coastal waters. The aquaculture density was then used as the main basis for a vulnerability assessment. Finally, the whole assessment system was integrated and verified during a typical storm surge process in coastal waters around the Shandong Peninsula in China. The coupled variations were also added to the assessment process and increased the risk value by an average of 12% in the High Sea States of the case study.