Most download

Artificial intelligence in oceanography has demonstrated a great potential with the explosive growth of ocean observation data and numerical model products. This article first reviews the history of ocean big data development, and then introduces in detail the current status of artificial intelligence in oceanography applications including identifying ocean phenomenon, forecasting ocean variables and phenomenon, estimating dynamic parameters, correcting forecast errors, and solving dynamic equations. Specifically, this article elaborates the research on the intelligent identification of ocean eddies, internal waves and sea ice, the intelligent prediction of sea surface temperatures, El Ni?o-Southern Oscillation, storm surges, waves and currents, the intelligent estimation of ocean turbulence parameterization for numerical models, and the intelligent correction of waves and current forecast errors. In addition, it discusses the recent progress of applying physical mechanism fusion and Fourier neural operator for solving ocean dynamic equations. This article is based on the current status of artificial intelligence in oceanography and aims to provide a comprehensive demonstration of the advantages and potential of applying artificial intelligence methods in the field of oceanography. With the two emerging research hotspots: digital twin oceans and artificial intelligence large models, the future development direction of artificial intelligence provides enlightenment and reference for interested scientists and researchers.

The Indian Ocean Dipole (IOD) is a pivotal climate phenomenon in the Indian Ocean region, exerting a significant impact on the climate change of the surrounding areas and the global climate system. Accurate prediction of IOD is essential for comprehending the dynamics of the global climate, yet traditional forecasting methods are limited in capturing its complexity and nonlinearity, constraining predictive capabilities. This paper begins by outlining the relevant theories of IOD and evaluates the strengths and weaknesses of traditional forecasting methods. It then provides a comprehensive analysis of the application and development of deep learning in the field of IOD prediction, highlights the advantages of deep learning models over traditional methods in terms of automatic feature extraction, nonlinear relationship modeling, and large data processing capabilities. Additionally, the paper discusses the challenges faced by deep learning models in IOD forecasting: including data scarcity, overfitting, and model interpretability issues, and proposes future research directions to promote innovation and progress in the application of deep learning technology in the field of climate prediction.

Histopathological indexes can be used to assess health of organism, but their application faces challenges such as low efficiency, high cost and strong subjectivity. Introducing artificial intelligence (AI) technology into histopathological analysis of biological tissues can leverage its high-throughput image analysis capabilities, overcoming the limitations in assessing and monitoring marine organism health. Based on our review on health assessment indicators of marine organisms, the application of AI in image analysis, and the use of AI for histopathological image processing, a deep learning-based histopathological image analysis approach was proposed using gill tissues of marine mussels as representative. Through a series of processes such as training, validation, and prediction of histopathology images, it was determined that the Res-UNet deep learning model can efficiently and accurately quantify histopathological damage in mussels’ gills. An automated, high-throughput, and less subjective workflow based on deep learning was finally established, offering new ideas and techniques for marine organism health assessment and marine monitoring.

Abyssal peridotite is widely distributed in tectonic environments such as mid-ocean ridges, subduction zones, and continental margins, and typically undergoes subsequent alterations, among which serpentinization is the most significant type. Serpentinization refers to the chemical process wherein ferromagnesium-rich minerals in peridotite, such as olivine and pyroxene, are replaced by a series of secondary minerals like serpentine, magnetite, and brucite. The conditions of serpentinization are closely linked with hydrothermal circulation and the migration of mineral-forming substances, bearing significant implications for indicating hydrothermal mineralization. Traditional methods of petrology and geochemistry exhibit polysemic interpretations and uncertainties when reflecting serpentinization conditions, with different minerals or chemical indicators possibly suggesting different outcomes. Oxygen isotopes are ubiquitous in nature and the oxygen isotope tracing method, due to its wide applicability, ease of comparison, and support for in-situ micro-zone analysis, can clearly reflect the reaction conditions and processes of the mineral or rock-fluid system. This study primarily provides an overview of the principles of oxygen isotope thermometry, the process of abyssal peridotite serpentinization, application cases of oxygen isotope thermometry in the serpentinization of abyssal peridotite, factors influencing the oxygen isotope compositions of serpentinites, as well as the advantages and limitations of oxygen isotope thermometry. It aims to offer a reference for a more profound understanding of the serpentinization process of abyssal peridotite.

An accuracy analysis of wind speed data retrieved from Sentinel-1 synthetic aperture radar (SAR) was conducted based on buoy observations from the National Data Buoy Center (NDBC). A back propagation (BP) neural network was utilized to correct the deviation in the SAR-derived wind speeds. Sensitivity experiments were designed for environmental factors, the number of training samples for BP neural network input, and neural network structure parameters. Finally, the SAR wind field data were converted into u and v vector wind data, and the accuracy analysis and correction were performed separately for u and v wind components. The experiment finds that the SAR-derived wind speed is underestimated compared to the buoy data. After calibration using BP neural network, the accuracy of SAR-derived wind speed data is improved, and the absolute value of bias of wind speed decreases from 0.78 m/s to 0.04 m/s, the RMSE of wind speed decreases from 1.98 m/s to 1.77 m/s. The sensitivity experiments suggest that low quality environmental factors input data will decrease the calibration effect of BP neural network, and increasing the sample size of the training set can improve that. The calibration results of converted u and v vector wind field data also show that the BP neural network has good correction effect.

Waves are one of the most important phenomena in the ocean. The accurate and quick updated wave forecasting is of crucial significance for ensuring marine activities safety. The development of wave forecast is presented, including the traditional statistical wave forecasting methods, numerical wave prediction models, and the rapidly developing artificial intelligence (AI) wave forecasting methods. Currently, AI wave forecast models have been demonstrated unique advantages in terms of computational efficiency and adaptive forecasting accuracy, and they are gradually being applied in practical wave forecasting operations, transitioning from the research stage. However, they also have limitations, including limited forecasting elements, underestimation of extreme wave conditions, and weak forecasting generalization ability. Based on the characteristics of AI wave prediction, key scientific and technological issues that need to be addressed in current AI wave forecasting are proposed. These include efficient utilization of observational data, incorporation of prior physical knowledge, and enhancement of AI model safety and generalization ability.

Combined with the Holland wind fields and the ERA5 wind fields, the mixed wind fields was set up by introducing a weight coefficient varying with the radius of wind speed, and a typhoon wave model in Zhejiang sea area was established using MIKE21 SW. Then, the Holland, the ERA5 and the mixed wind fields were used as the input wind fields to simulate the wind speed and the significant wave height during No.1918 typhoon Mitag, respectively. The verification shows that the simulated results obtained using the Holland wind fields and the ERA5 wind fields cannot agree accurately with the observed data, while the mixed wind fields proposed in this study can improve the simulation accuracy. In order to study whether the above conclusion is universal in Zhejiang sea area, five typical typhoons that have the most serious impact on Zhejiang sea area in the recent 5 years were selected for typhoon wave numerical simulations and the error statistical analysis. The results indicate the wind speed around the typhoon center is relatively good using the Holland wind fields and the average relative errors of the maximum wind speed are 8.62%-10.19%, but the average relative errors of the wind speed below 10 m/s is relatively bigger, reaching 29.76%-44.29%. However, the wind speed around the typhoon center using the ERA5 wind fields is smaller than the observed data, and the average relative errors of the maximum wind speed are 17.64%-25.77%, but the average relative errors of wind speed below 10 m/s are smaller than that using the Holland wind fields, which are 19.64%-32.00%. During the five typhoon processes, the average values of the average relative errors of the significant wave height driven by Holland, the ERA5 and the mixed wind fields are 29.92%, 25.62% and 22.82%, respectively. Correspondingly, the average root mean square errors are 0.46 m, 0.42 m and 0.39 m and the consistency indexes are 0.94, 0.95 and 0.96. The above results shows that the mixed wind fields proposed in this study is universal in Zhejiang sea area and can improve the simulation accuracy of typhoon waves.

Ocean eddies are prevalent oceanic phenomenon that play a crucial role in the global transportation of oceanic materials and energy. Although traditional methods for detecting ocean eddies are widely used, they suffer from significant drawbacks such as excessive reliance on expert-set thresholds, continuous manual intervention, large detection errors, low efficiency, and poor global applicability, making it difficult to adapt to the complex and variable marine environment. Currently, the rapid development of artificial intelligence (AI) presents a promising solution for the intelligent detection of ocean eddies. AI can automatically and rapidly extract deep features from images, effectively address the challenges posed by the high similarity in oceanic phenomenon features and significant geometric variability. This paper provides an overview of AI-based oceanic eddy identification methods based on different deep learning methods, focuses on coder-decoder structure, fully convolutional neural network, multi-scale context method and attention mechanism, and aims to provide valuable insights and references for future ocean eddy research.

The towed marine three-component magnetic gradiometer can obtain the geomagnetic three-component and magnetic gradient data at the same time. Compared with the traditional towed geomagnetic total field magnetometer, the towed marine three-component magnetic gradiometer has the advantages of reducing the ship magnetic interference and resisting the influence of geomagnetic daily variation, but it also has some shortcomings such as sensitivity error, zero offset error, orthogonality error and position error. In the actual voyage, a section data measured by the towed marine three-component magnetic gradiometer was calibrated to the total geomagnetic field data measured by the G880 magnetometer, which proved its high stability and reliability. Based on the three component magnetic gradient data, the tensor invariants and the trend of magnetic boundary were obtained, and combined with the Euler deconvolution calculation, the magnetic source body on the measurement line was effectively identified and interpreted. The results show that the towed three-component marine gradiometer can effectively obtain the information of geomagnetic field, component and gradient, which can provide a more effective technical means for marine geomagnetic field measurement.

Extremely deep convective clouds are a precursor to the rapid intensification (RI) of tropical cyclones (TCs). To predict the RI of TCs in the western North Pacific (WNP), a machine learning (ML) model using data related to extremely deep convective clouds was developed. The ML model integrates the Statistical Hurricane Intensity Prediction Scheme-Rapid Intensification Index (SHIPS-RII) data and the coverage area of extremely deep convective clouds within a 300 km radius of the center of the TC. Based on data from 2011 to 2019, the model forecasted RI events that increased by more than 30 kn and 35 kn within 24 h. Compared to models using only SHIPS-RII data, this ML model showed an improvement of 5.66% and 9.58% in the Peirce Skill Score (PSS), and a relative increase of 8.41% and 8.55% in the probability of detection (POD). This model is used to forecast typical typhoon Dujuan (2015), and the results show that the model integrating the coverage area of extremely deep convective clouds has advantages in RI predictions, which is mainly reflected in RI forecasts when the initial intensity is strong. The model has great application potential for forecasting strong typhoons.

Based on the data of satellite altimetry and six tide gauge stations along the coast of China, linear regression function was used to estimate the absolute sea level rise rate in the coastal areas of China from 1993 to 2020, which was 4.17±1.32 mm/a, and the relative sea level rise rate was 4.47±0.90 mm/a. Taking the atmospheric data, ocean data and climate modal index from 1958 to 2020 as prediction factors, a variety of neural network models such as long short-term memory neural network model (LSTM model), recurrent neural network model (RNN model), gated recurrent unit neural network model (GRU model) and support vector machine regression model (SVR model) were established to predict the trend of relative sea level changes around the six tide gauge stations along the coast of China. The model evaluation results show that the average correlation coefficient and root mean square error of the observed value and the predicted value obtained by the LSTM model that simultaneously introduces atmospheric and ocean variables and climate modal index variables are 0.866 and 19.279 mm, respectively, which performs the best among the four models, and therefore the LSTM model can be used as a new method for predicting relative sea level changes.

Seafloor topography is of considerable value in commercial, engineering, military and scientific research. Currently, gravity field data, such as free air gravity anomalies and vertical gravity gradients, are commonly used to inverse seafloor topography. However, due to the strong multi-resolution of the existing methods to inverse seafloor topography, it is still impossible to obtain accurate high-precision seafloor topography. A new data-knowledge-driven method was proposed to reconstruct accurate seafloor topography, which combines the gravity-density method with random forests. This method was applied to the South China Sea and compared with the gravity-density, random forest, and existing SIO models. The inversion results show that the data-knowledge-driven method provides better inversion performance, followed by the random forest and gravity-density methods, and the SIO model is the worst. The mean absolute error, mean relative error and root mean square error of the data-knowledge-driven are reduced by 21%, 25% and 7%, respectively, compared to those of the gravity-density method, while they are also reduced by 20%, 20% and 20%, respectively, compared to those of the random forest. In addition, the data-knowledge-driven model has a high degree of agreement with the shipboard bathymetry data, with approximately 72% of its differences distributed within ±10 m, which is higher than that of the other three models. The results demonstrate the feasibility and effectiveness of the data-knowledge-driven approach in seafloor topography inversion, which helps to accelerate the mapping of high-precision seafloor topography.

Based on multi-platform observed data, an unexpected response of a warm mesoscale eddy to bypassed typhoon Megi in the South China Sea in 2010 was observed and investigated. During the passage of typhoon Megi, the SLA maximum of the warm eddy increased from 30 to 36 cm, the radius increased from 78 to 116 km, the eddy kinetic energy increased from 166 to 303 m²/s², and the amplitude increased from 3 to 9 cm. On the right side of the typhoon, the thermocline water at Argo station on the edge of the warm eddy sank by 20 to 40 m. Diagnosis of the wind stress curl alone indicates that the warm eddy should be weaken and the thermocline should be raised, which are inconsistent with the observation results. Diagnosis based on the reanalysis sea surface velocity indicates that during the passage of typhoon Megi, the water diverges below the typhoon path, while the water converges on the right side of the path in the warm eddy region, and the SLA maximum as well as the amplitude of warm eddy are positively correlated with the convergence intensity. Estimation based on the reanalysis sea surface velocity also indicates that the water at Argo station will sink 29 m. Both the warm eddy characteristics and the thermocline depression are consistent with the observation. The case study shows that the response of mesoscale eddy on the edge of typhoon influence to typhoon is constrained not only by wind stress curl but also by the oceanic background conditions, and further attentions are required to explore the corresponding response and mechanism of upper ocean to typhoon.

Compared with the semi-theoretical and semi-analytical wave forecasting and numerical modeling,artificial intelligence wave forecasting has the advantages of higher forecasting accuracy and lower computational resource requirements. In this paper, a two-dimensional significant wave height (SWH) forecasting model for the southeast coast of China is established based on the convolutional long short-term memory network (ConvLSTM) algorithm using ERA5 (ECMWF Reanalysis v5) reanalysis data as the initial field. The data from 2014-2022 are used to train the forecasts of SWH for the next 6 h, 12 h, 18 h and 24 h, and the data from 2023 are used for testing. Sensitivity tests are carried out to optimize the model configuration and evaluate the prediction performance of SWH in the southeast coast of China at four period validity (6 h, 12 h, 18 h, 24 h) in 2023. Sensitivity tests show that when input time series length N=4(input SWH value of -18 h, -12 h, -6 h, 0 h), the accuracies of the model at four period validity are better than those of other time series length. When the combination of input physical elements is SWH, mean wave direction and sea surface 10 m wind vector, the accuracy of the model is better than other combinations at 12 h, 18 h and 24 h. Through the fine-tuning of ConvLSTM model training and configuration, the two-dimensional and high-precision intelligent prediction of SWH in the southeast coast of China can be realized.

By interpolation of high and low tide data and application of NS_TIDE model, the tidal characteristics of the tidal reach of Xijiang River (Makou-Dahengqin) were analyzed. Compared with cubic spline interpolation and linear interpolation, it is found that Hermite interpolation is the best method to simulate the hourly tide level. The verification results of tide level show that the overall error of NS_TIDE model is low, and the outliers mainly come from the influence of typhoon and flood. The mean water level and the amplitude of tidal component in the tidal reach of Xijiang River are different in wet and dry season. The influence of runoff in the upper reaches is greater than that of the tides, and the opposite is true in the lower reaches. With the increase of runoff and tidal difference, the mean water level of the upper reaches increases, and the influence on the amplitude and the phase of tidal component is different in different section, which is related to the spatial location and the frequency of the tidal component.

Based on Global Navigation Satellite System (GNSS) dynamic precision point positioning technology (PPP), the influence factors of precipitable water vapor (PWV) detection over the ocean were studied. The sampling interval, satellite masking angle, PPP solution method (fixed solution or floating point solution), and the influence of Beidou satellite system combination on ocean PWV retrieval were mainly analyzed. In the marine observation environment, the results show that the accuracy of PWV inversion is the highest when the sampling interval is 30 s. When the number of available satellites is small, the accuracy of PWV inversion is better when the satellite masking angle is set to 5°-10°, and the accuracy decreases gradually with the increase of the satellite masking angle. Whether the PPP solution is fixed or not, it has little effect on the accuracy of PWV inversion. On the basis of GPS/GLONASS system combination, adding Beidou observation value will improve the redundancy of observation and improve the accuracy of PWV inversion.

The one-dimensional theoretical model of internal solitary waves has been widely used in their prediction. However, on one hand, these theoretical models usually rely heavily on temperature and salinity data when calculating wave functions, which requires the use of moorings equipped with temperature and salinity observation instruments, resulting in high observation costs. On the other hand, they tend to have large prediction errors in complex current environments, such as lower accuracy in calculating the nonlinear phase speed and wave function of internal solitary waves. In this study, a Velocity-Gaussian Function Model was proposed, which reversed the amplitude and wave function of internal solitary waves based on the measured current velocity of the upper layer of the South China Sea from a single mooring. Furthermore, key parameters such as wave-induced current and nonlinear phase speed of internal solitary waves were calculated using a one-dimensional theoretical model. By comparing the measured data from the moorings with the results calculated by the Velocity-Gaussian Function Model, it was found that the model can simulate the wave-induced current throughout the entire water depth by inputting only the measured current velocity from the upper 150 meters of the ocean. Additionally, the error in the nonlinear phase speed can be controlled within 10% compared to the measured value. The application of the Velocity-Gaussian Function Model enables accurate prediction of internal solitary waves in the complex South China Sea, without the need for moorings equipped with temperature and salinity observation instruments, thus significantly reducing the cost of internal solitary wave observation.

The influence of sampling period of precision point positioning (PPP) of Global Navigation Satellite System (GNSS) on tide accuracy was studied by using GNSS receiver to collect observation data on marine mobile platform. Different data sets were extracted at periods of 30 s, 60 s, 90 s and 120 s, and dynamic processing was carried out with Trip software to obtain the coordinates of each measuring period. The tide level measurement results of two receivers at four sampling periods were compared respectively, and the standard deviation was used as the evaluation index of accuracy. The results show that the shorter the sampling period, the higher the precision of PPP tide test. When the sampling period is shortened to 60 s, the change is no longer obvious. The sampling period gradually decreases from 120 s to 90 s, 60 s and 30 s, and the accuracy increases by 63.0%, 60.4% and 10.0%, respectively. In addition, the difference of PPP accuracy between BDS/GPS/GLONASS three-system combination GNSS and GPS/GLONASS dual-system combination GNSS is compared. At the sampling periods of 30 s, 60 s, 90 s and 120 s, the PPP tide test accuracy of the three-system combination is 88.9%, 90.4%, 78.7% and 44.7% higher than that of the dual-system combination, respectively.

The type of sea ice is one of the important attributes of polar sea ice, and the physical properties of multi-year ice are significantly different from those of first-year ice. Therefore, the identifying the types of sea ice is of great significance to the research of polar climate change and the navigation security of ships in ice-covered regions. Satellite remote sensing is an effective method to obtain multi-temporal and large-scale sea ice type information. Based on three deep learning models (ResNet, Vision Transformer, Swin Transformer) and Sentinel-1 satellite dual-polarization synthetic aperture radar (SAR) images, this paper studies the classification method for sea ice in the regions of the Northwest and Northeast Passage in the Arctic. The results showed that the sea ice classification effect of 8×8 pixel slice dataset was better than that of other size slice datasets. Offset processing false color images could effectively reduce the influence of noise on sea ice classification. Among the three deep learning models, the Swin Transformer model had the highest classification accuracy, with the overall accuracy and Kappa coefficient above 98%. Comparing the multi-year ice concentration, it was found that the results of the three models deviate less than 10% from the AMSR2 data.

The open source software OpenFOAM was used to solve the Reynolds-averaged Navier-Stokes equations, numerical simulations of wave surges (Fr=1.2~1.3) was implemented, and the results were compared with physical experimental data to verify the accuracy of the numerical simulations. The data was studied based on the CONV1D convolutional neural network model to predict the dynamic development process of tidal bore on terrain with slope. Comparison of the model prediction and numerical simulation results for the arrival time and the maximum water level of the tidal bore at x=30.0 m shows that the average relative error in the arrival time is 2.28%, and the average relative error in the maximum water level is 3.73%. The smaller relative error proves the accuracy of the CONV1D model. This result has certain research significance for the simulation of the hydrodynamic process of tidal bore, early warning of tidal bore disasters, and the study of future development trends of primary tidal bore.