Sea surface temperature (SST) is an important physical factor in the interaction between the ocean and the atmosphere. Accurate monitoring and prediction of the temporal and spatial distribution of SST are of great significance in dealing with climate change, disaster prevention, disaster reduction, and marine ecological protection. This study establishes a prediction model of sea surface temperature for the next five days in the East China Sea using long-term and short-term memory neural networks (LSTM). It investigates the influence of different parameters on prediction accuracy. The sensitivity experiment results show that, based on the same training data, the length of the input data of the LSTM model can improve the model’s prediction performance to a certain extent. However, no obvious positive correlation is observed between the increase in the input data length and the improvement of the model’s prediction accuracy. On the contrary, the LSTM model’s performance decreases with the prediction length increase. Furthermore, the single-point prediction results of the LSTM model for the estuary of the Yangtze River, Kuroshio, and the Pacific Ocean are accurate. In particular, the prediction results of the point in the Pacific Ocean are the most accurate at the selected four points, with an RMSE of 0.0698 °C and an $R^2$ of 99.95%. At the same time, the model in the Pacific region is migrated to the East China Sea. The model was found to have good mobility and can well represent the long-term and seasonal trends of SST in the East China Sea.

The ocean chlorophyll-a (Chl-a) concentration is an important variable in the marine environment, the abnormal distribution of which is closely related to the hazards of red tides. Thus, the accurate prediction of its concentration in the East China Sea (ECS) is greatly important for preventing water eutrophication and protecting the coastal ecological environment. Processed by two different pre-processing methods, 10-year (2011–2020) satellite-observed chlorophyll-a data and logarithmic data were used as the long short-term memory (LSTM) neural network training datasets in this study. The 2021 data were used for comparison to prediction results. The past 15 days’ data were used to predict the concentration of chlorophyll-a for the five following days. Results showed that the predictions obtained by both pre-processing methods could simulate the seasonal distribution of the Chl-a concentration in the ECS effectively. Moreover, the prediction performance of the model driven by the original values was better in the medium- and low-concentration regions. However, in the high-concentration region, the prediction of extreme concentrations by the two data-driven LSTM models showed underestimation, considering that the prediction performance of the model driven by the original values was better. Results of sensitivity experiments showed that the prediction accuracy of the model decreased considerably when the backward prediction time step increased. In this study, the neural network was driven only by chlorophyll-a, whose concentration in the ECS was forecasted, and the effect of other relevant marine elements on Chl-a was not considered, which is the current weakness of this study.

Deep learning methods have excellent prospects for application in wave forecasting research. This study employed the convolutional LSTM (ConvLSTM) algorithm to predict the South China Sea (SCS) significant wave height (SWH). Three prediction models were established to investigate the influences of setting different parameters and using multiple training data on the forecasting effects. Compared with the SWH data from the China–France Ocean Satellite (CFOSAT), the SWH of WAVEWATCH III (WWIII) from the pacific islands ocean observing system are accurate enough to be used as training data for the ConvLSTM-based SWH prediction model. Model A was preliminarily established by only using the SWH from WWIII as the training data, and 20 sensitivity experiments were carried out to investigate the influences of different parameter settings on the forecasting effect of Model A. The experimental results showed that Model A has the best forecasting effect when using three years of training data and three hourly input data. With the same parameter settings as the best prediction performance Model A, Model B and C were also established by using more different training data. Model B used the wind shear velocity and SWH as training and input data. When making a 24-h SWH forecast, compared with Model A, the root mean square error (RMSE) of Model B is decreased by 17.6%, the correlation coefficient (CC) is increased by 2.90%, and the mean absolute percentage error (MAPE) is reduced by 12.2%. Model C used the SWH, wind shear velocity, wind and wave direction as training and input data. When making a 24-h SWH forecast, compared with Model A, the RMSE of Model C decreased by 19.0%, the CC increased by 2.65%, and the MAPE decreased by 14.8%. As the performance of the ConvLSTM-based prediction model mainly rely on the SWH training data. All the ConvLSTM-based prediction models show a greater RMSE in the nearshore area than that in the deep area of SCS and also show a greater RMSE during the period of typhoon transit than that without typhoon. Considering the wind shear velocity, wind, and wave direction also used as training data will improve the performance of SWH prediction.

Oceanic mesoscale eddies typically span tens to hundreds of kilometers and last several weeks to months. They are a key dynamic process influencing the distribution of oceanic energy, affecting energy budgets, heat distributions, and material transport. Advances in satellite remote sensing and in situ observation over the past half-century have substantially enhanced our understanding of the statistical properties, energetics, and dynamic mechanisms of mesoscale eddies, establishing this field as a major focus in physical oceanography. This article presents a comprehensive review of recent advancements in 6 key areas of mesoscale eddy research: (a) eddy detection methods and data products (leading automated detection methods and the corresponding eddy datasets and data products currently available), (b) eddy generation and dissipation (eddy generation, development, and dissipation mechanisms), (c) energy cascades (energy cascades between eddies, large-scale circulation and submesoscale processes, the role of these processes in modulating the energy transfer of near-inertial internal and surface waves, and research progress in related parameterization), (d) air–sea interaction (eddy-induced interactions, especially the interaction between eddies and typhoons), (e) interdisciplinary studies (impacts of eddies on biogeochemistry, acoustics, and other related fields), and (f) observation studies (programs dedicated to studying mesoscale eddies through in situ observation). This article also discusses research prospects on mesoscale eddies.

Using multi-source observational data and GLORYS12V1 reanalysis data, we conduct a comparative analysis of different responses of two warm eddies, AE1 and AE2 in the northern South China Sea, to Typhoon Kalmaegi during September 2014. The findings of our research are as follows: (1) for horizontal distribution, the area and the sea surface temperature (SST) of AE1 and AE2 decrease by about 31 % (36 %) and 0.4 °C (0.6 °C). The amplitude, Rossby number (Ro = relative vorticity $/$ Coriolis parameter) and eddy kinetic energy (EKE) of AE1 increase by 1.3 cm (5.7 %), $\mathrm{1.4}\times {\mathrm{10}}^{-\mathrm{2}}$ (20.6 %) and 107.2 cm² s⁻² (49.2 %) after the typhoon, respectively, while AE2 weakens and the amplitude, Rossby number and EKE decrease by 3.1 cm (14.6 %), $\mathrm{1.6}\times {\mathrm{10}}^{-\mathrm{2}}$ (26.2 %) and 38.5 cm² s⁻² (20.2 %), respectively. (2) In the vertical direction, AE1 demonstrates enhanced convergence, leading to an increase in temperature and a decrease in salinity above 150 m. The response below the mixed-layer depth (MLD) is particularly prominent (1.3 °C). In contrast, AE2 experiences cooling and a decrease in salinity above the MLD. Below the MLD, it exhibits a subsurface temperature drop and salinity increase due to the upwelling of cold water induced by the suction effect of the typhoon. (3) The disparity in the responses of the two warm eddies can be attributed to their different positions relative to Typhoon Kalmaegi. Under the influence of negative wind stress curl outside the maximum wind radius (R_max) of the typhoon, triggering negative Ekman pumping velocity (EPV) and quasi-geostrophic adjustment of the eddy, the warm eddy AE1, with its center to the left of the typhoon's path, further enhances the converging sinking of the upper warm water, resulting in its intensification. On the other hand, the warm eddy AE2, situated closer to the center of the typhoon, weakens due to the cold suction caused by the strong positive wind stress curl within the typhoon's R_max. The same polarity eddies may have different response to typhoons. The distance between eddies and typhoons, eddy intensity, and the background field need to be considered.