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.

Wave is an important factor to shape the dynamic geomorphology of the open tidal flat, but researches on tidal-flat wave characteristics are still limited. Taking Nanhui tidal flats in the Changjiang Estuary as an example, the wave characteristic parameters and wave spectrum parameters were obtained by inverting flow-velocity and water-pressure data from the Acoustic Doppler Velocimeters (ADVs) at some fixed platforms, and their changes over tidal cycles and associated influence mechanisms were discussed. The results show that both normal wave direction and prominent wave direction at three stations of Nanhui tidal flats are mainly southeast during the observation period, with long-period swells dominating. The effective wave height of the three stations is positively correlated with the water depth, but the fitting coefficients of each station are different over flood and ebb periods. Wave orbital velocities are obviously modulated by the shallow water effect and the flow directions, and their maximum values usually occur at the early flooding stage, while minimum values can be observed to occur during the current transition periods. The wave energy spectrum during ebb tides is featured by the bimodal pattern because of high influence by tidal levels and coastal topography, and the peak energy is continuously attenuated and gradually dispersed with the concurrent shift of peak frequencies.

With the advancement of observation technology and the improvement of ocean numerical simulation capabilities, some stable subsurface coherent vortices have been widely observed in the ocean, which far from the formation source area. These vortices possess distinctive dynamic characteristics, such as a low potential vorticity center, lens-like structure of isopycnals, weak stratification, and anomalous temperature, salinity, or other tracer properties compared to the surrounding water mass. Their core flow is relatively stronger. These subsurface coherent vortices significantly impact ocean water mass transport, thermohaline circulation and marine biological environment. This paper comprehensively summarizes researches on subsurface coherent vortices in the ocean, including their structure, hydrological characteristics, identifying methods, global distribution, dynamic mechanisms and their important effects on ocean environment. Furthermore, the research perspectives are discussed, such as the difficulties in the research and the issues that need to be solved to comprehensively understand subsurface coherent vortices in the ocean.

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.

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.

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.

Nitrate is the main nitrogen form available for phytoplankton life activities in the ocean, and its nitracline depth (Z_N) directly affects the vertical transport of nitrate and the ocean primary productivity, and then further influences the carbon cycle. With the advancement of ocean observation technologies, the profile data of nitrate have been collected in diversified ways, such as ship-based CTD observations and BGC-Argo automatic observations. The vertical sampling resolution of these techniques varies significantly (the vertical sampling resolution of CTD is lower than that of BGC-Argo). In view of different sampling data, it is urgent to conduct systematic and quantitative comparative analysis and study on the computing methods of Z_N. In this study, three different methods: difference method, gradient method and threshold method, are adopted to compute the corresponding Z_N by using the historical ship-based CTD data and BGC-Argo buoy data in the Northwest Pacific Ocean. The results show that in the case of single nitrate profile, based on BGC-Argo data, the difference between observed Z_N and the Z_N calculated by difference method is only 0.2 m, followed by threshold method is 20.0 m and gradient method is 202.8 m at most. Based on CTD data, the difference between observed Z_N and Z_N calculated by difference method is 2.0 m, the threshold method is 49.0 m, and the gradient method is 155.0 m. Compared with the gradient method and threshold method, the difference between the Z_N calculated by the difference method and the observed Z_N is the smallest. According to the results of statistical error analysis, it is found that the Z_N calculated by the three methods based on BGC-Argo data show a good correlation with the observed Z_N. Among them, the error of difference method is the smallest (R²=0.77, RMSE=28.48 m). The R² and RMSE of threshold method are 0.64 and 34.85 m, and the R² and RMSE of gradient method are 0.52 and 53.80 m. For CTD data, due to its low vertical sampling resolution, the Z_N calculated by the three methods is quite different from the observed Z_N. However, compared with the gradient method and threshold method, the error of the difference method is still the smallest (R²=0.81, RMSE =16.13 m). The R² and RMSE of threshold method are 0.47 and 27.65 m, and the R² and RMSE of gradient method are 0.42 and 36.41 m. The applicability of each method is preliminarily explored through comparing and analyzing the characteristics and differences of them so as to provide some scientific reference for the in-depth research on the vertical distribution characteristics and upward transport process of nitrate.

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%.

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.

Two-phase leaching method can separate hydrogenetic and residual mineral phases of ferromanganese nodules, which will provide valuable information with the research of ferromanganese nodule mineralization and pale-environment. In order to study the applicability of the two-phase leaching method in the nodule mineralization research for different types of nodules compared to the bulk sample results, the ferromanganese nodules samples from six stations were selected, which were collected on the seamounts area of western Pacific Ocean and CC Zone of eastern Pacific Ocean, respectively. Geochemical and mineralogical compositions of the bulk samples were analyzed, and elements compositions of the hydrogenetic and residual mineral phases were analyzed, which were obtained using the two-phase leaching method. The results indicated that the mass ration variation of the residual mineral phases was not obvious with about 14.0%-17.6%, which had high contents of Nb, Rb, Ta, Ti, Zr. Contents and relevant rations of elements such as Co, Ni, Cu, Zn, Sr, REY in the hydrogenetic mineral phase showed similar features with those in the bulk samples. Proportion of elements contents like Ti, Nb, Sr between hydrogenetic and residual mineral phases showed well negative correlation with Mn/Fe values, which probably could be regarded as index for ferromanganese nodule mineralized environment research in the future.

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.

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.

Coastline is one of the important geographical elements to describe the boundary between land and sea. Under the dual influence of natural factors and socio-economic factors, coastline dynamic evolution of different intensities continues to occur. Based on Landsat series satellite remote sensing images, the spatial and temporal evolution of the coastline of Nan’ao Island from 1976 to 2021 was analyzed by RS and GIS technology combined with field investigation, and the driving factors were analyzed by grey correlation analysis. The results show that : (1)In the past 45 years, the coastline of Nan’ao Island has changed significantly. The coastline length has increased by 11.06 km, and the fractal dimension have generally increased.(2)During the study period, the type of coastline changed from natural coastline dominated by bedrock to artificial coastline, the comprehensive index of coastline utilization show an increasing trend, and the main structure of coastline development and utilization show a form of single to multiple.(3)The evolution of the coastline of Nan’ao Island has obvious regional differences. That of Houzhai Town is greatly affected by human factors, and its evolution is more significant. The coastlines of Yun’ao and Shen’ao Towns are mainly affected by natural factors, and their evolutions are relatively slow.(4)Typhoon(natural disasters) and population are the main driving factors of the coastline evolution of Nan’ao Island.

Based on the one-year measured wave data in the coastal area of Cangnan, Zhejiang Province, the characteristics of wave parameters were statistically analyzed, the correlation between wave parameters was analyzed by using the least square method, the relationship between the average wave duration and wave height was studied, the wave energy was estimated, and the characteristics of typical typhoon waves during typhoon “Lekima” were analyzed.The results show that the study area is mainly composed of light waves with spectral peak period of 5-9 s, the annual average significant wave height of 1.22 m, the normal wave direction is E, the strong wave direction is ENE.There is a significant linear relationship between the characteristic wave heights, which conforms to the typical Rayleigh Distribution.In typhoon free period and cold wave free period with significant wave height below 2.7 m and typhoon period with significant wave height above 4.1 m, the average duration of wave decreases exponential decays with the increase of wave height, and the attenuation rate of typhoon period with significant wave height above 4.1 m is higher than that of typhoon free period and cold wave free period with significant wave height below 2.7 m.During the impact of typhoon “Lekima”, the maximum wave height, spectral peak period, and spectral peak density show a basically synchronous process of first increasing and then decreasing, with a maximum spectral peak density of 55.10 m²/Hz;the typhoon wave spectrum before and after the impact of the typhoon show a bimodal spectrum, while the wave spectrum during the most significant period of typhoon impact show a unimodal spectrum.

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.

Tidal current energy is the kinetic energy carried in the horizontal movement of tidal water, which has great development prospects. Accurate simulation and characterization of regional tidal currents can help to efficiently evaluate the spatial and temporal distribution of tidal energy resources, which is the key to the development and utilization of tidal current energy resources. In this paper, a high-resolution numerical model of tidal currents is constructed by applying FVCOM ocean model in Zhoushan sea area where has rich tidal current energy, and the reliability of the model is confirmed by tidal level and current verification. According to the simulation results, six waterways with dense tidal current energy resources in the Zhoushan sea area were identified, among which the average energy density of Xihoumen waterway, Cezi waterway and Taohuagang waterway exceeds 2.0 kW/m², and the maximum energy density exceeds 20 kW/m², and the flow speed over 1.0 m/s of the whole month is more than 80%. During tidal current ebb and flow, the reflow is dominant, while the asymmetry and rotation of tidal current are low. The flow stability coefficient is more than 0.98, so it is more suitable for the development and utilization of tidal current energy than other three waterways. The best location for tidal current energy development in these three waterways was then determined by calculating the significant hours and available hours, and the corresponding exploitable tidal current energy resources were evaluated using the Farm method, which were 27.53 MW, 39.96 MW, and 130.26 MW, respectively.

Oujiang River is a typical mountain river whose water and sediment fluxes are characterized by a great disparity between flood and dry seasons. Based on the measured data of water discharge and sediment load at the mainstream control hydrological station of Oujiang River in the past 71 years (1950—2020) and 43 years (1956—1998), respectively, the coefficient of nonuniformity, Mann-Kendall non-parametric statistical test and double mass curve were used to analyze the variations of runoff and sediment load during the flood seasons (including plum rain season from April to June and typhoon season from July to September) and dry seasons (non-flooding season from October to March in next year) in the Oujiang River. The results showed that: (1) The peak and valley month of runoff were the same as sediment load. The peak month of both runoff and sediment load appeared in June, while their valley month appeared in December. The plum rain season was the most important period of water and sediment transporting to sea from Oujiang River. (2) The runoff showed significant decreasing trend in the plum rain season, significant increasing trend in non-flooding season, and non-significant trend in typhoon season during 1950—2020 in Oujiang River. The nonuniformity of intra-annual distribution for runoff had become more uniform obviously, resulting from the regulation of reservoirs. (3) The sediment load showed significant decreasing trend in the plum rain season due to the interception of reservoirs, and no significant trend in typhoon season and non-flooding season during 1956—1998 in Oujiang River. The nonuniformity of intra-annual distribution for sediment load showed little change, which might relate to the nonuniformity of intra-annual distribution for precipitation. (4) The relationship between sediment load and runoff during typhoon and non-flooding season changed in 1975 and 1959, respectively, both of which were related to the heavy rainfall within the river basins.

Using Argo measured data combined with satellite remote sensing data and moored buoy data, the upper ocean temperature and salinity response caused by super typhoon Rammasun in 2014 was analyzed and studied. The result shows that super typhoon Rammasun resulted in cooling of sea surface temperature and deepening of mixing layer. Meanwhile, mixing length and vertical velocity induced by typhoon were calculated in this research, which explained the causes of temperature changes in the subsurface layer. Strong mixing and weak upwelling led to warming of the subsurface layer, whereas weak mixing and strong upwelling led to cooling of the subsurface layer. Compared with the change of temperature, the response of salinity was more complex. Precipitation first caused the decrease of surface salinity, and then vertical mixing led to a large increase of surface salinity. However, the effect of precipitation could greatly inhibit this process. After the typhoon departed, the vertical mixing was weakened, and the salinity was greatly reduced because of the heavy precipitation, it was even lower than that before the typhoon.