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.

Aiming at the problems of difficulty in verifying the accuracy of the interpolation model of single-beam bathymetric data, a method based on high-precision UAV data to verify the accuracy of the interpolation model was proposed by using the intertidal tidal law. At low tide, UAV photogrammetry was used to construct a high-precision digital surface model (DSM) of the intertidal zone, and at high tide, the single-beam bathymetry data was obtained and the three-dimensional coordinates of the intertidal topographic points were calculated by combining the global navigation satellite system (GNSS) technology, and constructed an intertidal digital elevation model (DEM) by using the following 4 interpolation methods: Kriging, inverse distance weight, completely regularized spline and natural neighborhood interpolation method. Based on UAV data, the accuracy analysis of intertidal zone DEM was carried out. The results show that: (1) PPK technology-assisted UAV photogrammetry can construct high-precision intertidal zone DSM. (2) In the intertidal zone, UAV data can be used as an evaluation criterion for the accuracy of single-beam bathymetry data. (3) When the seabed topography is relatively flat, the completely regularized spline method has higher accuracy than the other three methods, and the coarse difference rate is 12.5%.

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.

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.

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.

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.

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.

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.

Deep-sea sediments have attracted much more attention in recent years because of their potential resources for rare earth elements plus Yttrium (REY). However, the host minerals and enrichment mechanism of REY in deep-sea sediments, and the spatial distribution characteristics and metallogenic regularity of the REY-rich sediments are still unclear. The Clarion-Clipperton Fracture Zone (CCZ) in the East Pacific is the most important polymetallic nodule metallogenic belt, and its potential of REY resources has not been well evaluated. In this study, the whole-rock geochemistry (728 groups of major elements and 625 groups of trace elements) of sediments from 125 stations in the west CCZ over an area of 27 800 km² was analyzed. The results show that the sediments in the study area are significantly rich in MnO, P₂O₅ and REY than those from Australian shales and global subducting sediments. Spatially, ∑REY has a positive correlation with P₂O₅, CaO, and Ce negative anomalies, indicating that calcium apatite is the main host minerals of REY. The average value of ∑REY in the sediments over the study area is 470±202 μg/g, some samples meet the criteria of REY-rich sediments (∑REY>700 μg/g), indicating that the study area has a certain potential of REY resources. Spatial interpolation analysis shows that REY-rich sediments are mainly distributed in the northern area characterized by hilly terrain, while they are poorer in the southern basin with flat terrain. The difference of geomorphology in the study area affects the regional deposition rate and the hydrodynamic sorting of calcium apatite, leading to the north-south zoning of REY resources distribution in the study area.

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.

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.

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 mesoscale atmospheric model WRF and the regional ocean model ROMS, a two-way coupled WRF-ROMS air-sea model was constructed to simulate the super typhoon Mangkhut in 2018. The results showed that the simulation results of the coupled air-sea model were better than those of the only atmospheric or ocean model, and the error of the typhoon track obtained from the coupled model was within 60 km, which was in good agreement with the best track. Compared with the observation results, the simulation results of wind speed and sea level pressure in the coupled model were better than others model. Based on the simulation results of the coupled air-sea model, the spatial and temporal distribution of the wind field, pressure field, sea surface flow field, and storm surge under the super typhoon Mangkhut were further analyzed. The results showed that: (1) In terms of spatial distribution, after the typhoon entered the South China Sea, the radius of the seven-level wind circle was larger behind the right side of the typhoon; the cyclonic flow field showed a significant Ekman effect with the typhoon wind field, and the flow direction was 45° from the wind direction. The wind field, pressure field, wind-generated flow field and water gain distribution all had obvious asymmetry, and the typhoon intensity, flow velocity and water gain were greater on the right side of the typhoon path than on the left side. (2) In terms of time distribution, the distribution of the wind field and the pressure field were similar and synchronized with the typhoon center, while the wind-driven flow field and storm surge were three hours behind the typhoon track.

The intertidal zone is a key area connecting terrestrial ecosystems and marine ecosystems, among which muddy tidal flat is an important and easily overlooked CO₂ collection habitat, and the macrobenthos play a central role in the input, transport and preservation of carbon. Macrobenthos community and living organic carbon pools of muddy tidal flat were analyzed in Aiwan Bay, eastern coast of Zhejiang Province in summer. The average abundance of macrobenthos was 105.2 ±37.2 ind/m², and the average biomass was 46.9 ±6.4 g/m². The major taxa components within the habitat were crustaceans and mollusks, and the ecosystem health status was excellent. The organic carbon contents of macrobenthos at Aiwan Bay from highest to lowest were other animals including fish and nemertinea (40.95%), polychaetas (22.98%), crustaceans (17.24%), echinoderms (15.90%), mollusks (10.76%), and estimated the macrobenthos carbon pool was 163.90 Mg, of which crustaceans have the largest contribution rate, accounting for 59.80%. The exploration of macrobenthos community structure and living organic carbon pools size in muddy tidal flat can provide scientific suggestion for constructing the blue carbon survey system and supply fundamental data to further quantify the overall carbon pool size in coastal habitats.

The waters surrounding South Georgia Island are one of the highest primary productivity regions in the Southern Ocean with enormous carbon sequestration potential. However, the strength of the biological pump efficiency in this area is still uncertain due to the lack of continuous upper ocean observation data.In this study, the hydrological and biogeochemical parameters obtained from the Biogeochemical Argo (BGC-Argo) floats deployed in the South Georgia Island vicinity during the period of 2017-2020 were utilized to investigate the impacts of physical processes on biogeochemical processes and to estimate the carbon export flux in the Antarctic summer. Results indicated that both upstream (northeast of the Antarctic Peninsula) and downstream (Georgia Basin) regions of South Georgia Island exhibited strong seasonal characteristics in Chl-a, with the latter area having a 4-month sustained period of phytoplankton bloom, suggesting a stable and continuous supply of iron. Using the temporal variability of the seasonal particulate organic carbon (POC) export, the summer POC export fluxes of the upstream and downstream regions were estimated to be 7.12±3.90 mmol·m^-2·d^-1 and 45.29±5.40 mmol·m^-2·d^-1, respectively, indicating that the difference might be due to enhanced downward export of organic carbon after the deepening of the mixed layer. The study found that the region maintained a high biological pump efficiency, contrary to the previous conclusion that the Georgia Basin had “high productivity low export efficiency”, which might have been caused by the limited “real-time” representation of the entire seasonal characteristics during ship-based surveys. BGC-Argo provides high spatiotemporal resolution of multi-parameter observation data, and this study demonstrates that it can more accurately quantify and evaluate marine biogeochemical processes and carbon sequestration potential.

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.

Coastal erosion leads to land loss and seriously threatens people’s life and property safety. It is great significant to identify coastal erosion vulnerability for disaster prevention and mitigation. The evaluation index system was constructed from three aspects: coastal dynamics, coastal morphology and social economy. Using the DSAS model and remote sensing data, the coast was discretized into equally spaced units based on section method, the weight and grade of the evaluation index were determined based on the entropy weight method, the coastal erosion vulnerability in the study area was calculated, and the spatial differentiation and influencing factors of coastal erosion vulnerability were identified by geographic detector. The results showed that the proportions of coastal erosion vulnerability for extremely high vulnerability, high vulnerability, medium vulnerability, low vulnerability and extremely low vulnerability in central coast of Jiangsu were 5.60%, 15.80%, 30.93%, 24.21%, and 23.46%, respectively, that showed a decreasing trend from north to south. The extremely vulnerable areas of coastal erosion were mainly located in the coastal area between the Zhongshan Estuary and the Sheyang Estuary. The spatial differentiation of coastal erosion vulnerability in central Jiangsu was the result of the synergistic effect of multiple factors such as coastal dynamics, coastal morphology, and economic and social activities. Among them, tidal slope, land cover, average tidal range, and coastline change rate were the dominant factors for the spatial differentiation of coastal erosion vulnerability.

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.

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.

Taking Dazhuzhi Island (Dongtou, Wenzhou) as the research area, UAV equipped with multispectral sensors was used to acquire high-resolution remote sensing images, the optimal spectral band combination was selected to classify the island vegetation, and the vegetation types was divided into arbors, shrubs and herbs by supervised classification. The accuracy of vegetation classification was 99.72%, and the Kappa coefficient was 0.995 4. The spatial distribution of dominant species of arbors and shrubs was obtained by using the deep convolutional neural network (the precision rate was 0.79), and combined with the biomass equations, the spatial distribution of the biomass of dominant species of arbors and shrubs was inversed (arbors’ R²=0.97, shrubs’ R²=0.99). The biomass inversion equations of 3 shrub dominant species (Ficus erecta, Mallotus japonicas, and Eurya emarginata) were constructed by field sampling, and the other dominant species biomass inversion equations were obtained from literature. Based on the biomass and spatial distribution of dominant species, the carbon storage of arbors and shrubbys was 300.36 t and 47.59 t, respectively. Using normalized difference vegetation index (NDVI) to invert the spatial distribution of herb biomass (R²=0.99), combined with the biomass equation of the dominant herb species (Zoysia sinica) constructed from the measured data, the carbon storage of herbs was 21.59 t on Dazhuzhi Island.