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.
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.
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.
Due to its advantages of strong adaptability and high safety,the jacket platform has been widely used in offshore oil and gas development. As more and more jacket platforms will reach or exceed the design life, the platform decommissioning has become one of the important problems in the field of offshore oil and gas development. This paper systematically introduces domestic and international regulations on jacket platform decommissioning, focuses on the decommissioning constraints, application fields, similarities and differences between different international conventions, and summarizes the key points of regulations and requirements on jacket platform decommissioning among China, the United Kingdom, Norway and the United States, and analyzes four typical decommissioning projects worldwide. In view of this, the different decommissioning schemes, and scope of application of jacket platform are summarized and analyzed, as well as the operational difficulties and implementation details of the three key process technologies of dismantling, cutting and transportation during decommissioning. The review can provide a theoretical basis for optimizing the decommissioning plan and key technical methods of the offshore jacket platforms, and has important engineering significance for marine environmental protection, navigation and fishery production.
Submarine earthquake is one of the most major factors causing deep-water international submarine cables damage. Understanding the process of submarine cables damage and the mechanism of submarine cables damage caused by turbidity currents after earthquake are of great significance to the security maintenance of international submarine communications. Combined with the lastest research result of global seabed topography and using professional international submarine cables engineering software Makaiplan, the process of plenty of submarine cables damage after Grand Banks Earthquake and Hengchun Earthquake were studied, then the relationship between the pattern of submarine cable damage and the developing process of turbidity currents after earthquake was found, and the mechanism of submarine cables damage caused by turbidity currents after earthquake was summarized. Study result shows that submarine cables break points are located intentively in submarine canyons and trenches. The movement speed of turbidity currents in submarine canyon and submarine trench, which caused submarine cable damage, can reach several ten kilometers to several hundred kilometres per hour. Terrestrial rivers and continental shelf undersea river channels provide materials transportation for the development of turbidity currents. Submarine canyons and trenchs are the pathes of turbidity currents movement then damage plenty of submarine cables. The turbidity currents that developed from upper continental slope in passive continental margin after earthquake can damage submarine cables laid on continental slope, continental rise and abyssal plain. This kind of turbidity currents achieves maximum speed on continental slope, then self-accelerate on abyssal plain. Multiple turbidity currents can develop at different positions of continental slope at the same time in active continental margin, then strike submarine cables which laid on canyons and trenches for multiple times. This kind of turbidity currents achieves maximum speed and self-accelerates in submarine trenches. There are several earthquake-resistance measures: submarine cable routes trying to avoid crossing submarine canyons and trenches which connected to terrestrial rivers or continental shelf channels; using shallow water type submarine cable which has outer armor protection when crossing inevitably; laying submarine cables suspended slightly on the bottom of canyons or trenches with Uraduct protection on them; changing the cross-section shape of submarine cable.
Deep-sea REY-rich sediments that are rich in lanthanides and yttrium (REY) extensively distributed in regions such as the Western Pacific, Eastern Pacific, Southeastern Pacific, and the Indian Ocean. This study analyzed the mineralogical and geochemical characteristics of deep-sea REY-rich sediments from two sites in the Clarion-Clipperton Fracture Zone (CCFZ) of the Eastern Pacific. Additionally, geochemical data on elements from 92 deep-sea REY-rich sediment sites across the Pacific were collected. Based on geochemical characteristics in conjunction with mineral composition, the Pacific deep-sea REY-rich sediments are categorized into three types: Al-rich, Fe-rich, and Ba-rich. The Al-rich type, prevalent in the Western Pacific region, primarily consists of zeolite clay, with an average whole-rock Al2O3 content reaching up to 14.9%. The Fe-rich type, found near the Eastern Pacific Rise in the Southeastern and Northeastern Pacific, exhibits a high average TFe2O3 content of 18.8%. Some samples within this type show a significant positive Eu anomaly, indicating that hydrothermal activity may contribute to the enrichment of REY and associated carrier minerals. The Ba-rich type, mainly located in the CCFZ of the Eastern Pacific, consists predominantly of (siliceous) clay, with an average Ba content of approximately 8 092×10-6. The elevated Ba levels suggest that the area of sediment formation may have experienced high primary productivity. This environmental condition likely resulted in extensive biogenic apatite deposition, which coupled with strong bottom currents in the CCFZ since the Oligocene, enhanced the accumulation of apatite, thereby promoting the enrichment of rare earth elements.
Nitrate is the main nitrogen form available for phytoplankton life activities in the ocean, and its nitracline depth (ZN) 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 ZN. In this study, three different methods: difference method, gradient method and threshold method, are adopted to compute the corresponding ZN 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 ZN and the ZN 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 ZN and ZN 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 ZN calculated by the difference method and the observed ZN is the smallest. According to the results of statistical error analysis, it is found that the ZN calculated by the three methods based on BGC-Argo data show a good correlation with the observed ZN. 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 ZN calculated by the three methods is quite different from the observed ZN. 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.
Using the data of high resolution satellite sea surface temperature (SST) from January 1, 1990 to December 31, 2020, the spatial characteristics of marine heatwaves (MHWs) in the South China Sea were identified with a deep-first-search algorithm, and the characteristics of marine heatwaves at different spatial scales were further investigated. The results indicated that the small-scale marine heatwave events in the South China Sea (Type I MHWs, area<1.8×104 km2) occurred the most frequently, accounting for 94.20% of the total marine heatwave occurrences. Large-scale marine heatwaves with areas exceeding 1.2×105 km2 (Type III MHWs) occurred only 74 times during the 31-year period, with the largest event recorded in 2015. Further analysis revealed significant differences in the spatial distribution of intensity, duration, and frequency of marine heatwaves for different spatial scales. Compared to Type I MHWs, Type II MHWs (1.8×104~1.2×105 km2) exhibited a noticeable increase in the average coverage area with an intensity exceeding 1.5 ℃. Statistical analysis showed that the intensity, duration, and cumulative intensity of South China Sea MHWs increased with the spatial scale of the MHWs. The intensity of Type III MHWs was 1.4 times that of Type I MHWs and 1.2 times that of Type II MHWs. In addition, the response of South China Sea MHWs areas to the El Ni?o-Southern Oscillation (ENSO) was also investigated. The results showed a significant increase in the areas of Type I to III MHWs during El Ni?o periods, with a lag of 6 to 7 months. The duration of Type III MHWs during El Ni?o was longer by 2 days compared to La Ni?a periods. This study explored the fundamental characteristics of South China Sea MHWs areas and further analyzed the commonalities and differences of MHWs at different spatial scales, providing new insights into the characteristics and mechanisms of the formation and dissipation of South China Sea MHWs.
The unique geographical features of the island countries in South Pacific, which are surrounded by sea and small in size, make most of the island countries in this region "ecologically fragile areas". Based on this, multi-source satellite data were used to monitor the marine ecological environment of Nauru, Palau, Tuvalu, and the Marshall Islands. It was also focused on whether there have been significant changes in the ecological environment of various countries before and after the Tonga volcanic eruption, to help to understand the impact of the Tonga volcanic eruption. The results show that: (1) In terms of temporal and spatial distribution of climatic states, the sea surface temperature and transparency of the surrounding waters of the South Pacific island countries maintain a relatively high level, while chlorophyll and net primary productivity decrease rapidly with the increase of offshore distance. (2) Warming, acidification and sea level rising are common problems faced by the sea areas of the four island countries. (3) The eruption of the Tonga Volcano has no significant impact on the coastal TSM mass concentration and SST. (4) The phenomenon of abnormally rising surface temperature and changed suspended matter mass concentration of the island in the first half month of the volcanic eruption has implications for disaster warning and forecasting using remote sensing methods.
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.
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.
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 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.
Seawalls play an important role in protecting coastal towns from extreme waves damage. Based on two-dimensional incompressible two-phase flow numerical model, the influences of onshore wind on overtopping characteristics of solitary wave under coastal seawall were systematically studied in this paper. The reliability of the numerical model was verified by comparing the numerical results with experimental data, and the influencing factors such as onshore wind speed, incident wave height, crest freeboards of the coastal seawall, beach slope and seawall slope on the hydrodynamic process of solitary wave overtopping of coastal seawalls were discussed in detail. The research results show that with the increase of onshore wind speed, incident wave height and the decrease of crest freeboards of the coastal seawall, the maximum overtopping volume, maximum runup height and spatial distributions of the maximum water elevation gradually increase. With the increase of beach slope and seawall slope, the maximum overtopping volume increase and decrease, respectively, while the maximum runup height gradually increase. Onshore wind can affect the hydrodynamic characteristics of solitary wave overtopping of coastal seawall, increase the wave steepness and the wave crest propagation speed and cause the wave breaking earlier. Compared with the windless condition, the maximum wave overtopping volume, maximum runup height, maximum hydrodynamic forces and spatial distributions of the maximum water elevation are increased under onshore wind. The results of this study can provide a reference for the design of coastal engineering.
Mesoscale eddies widely exist in the ocean and affect the sound propagation. Using AVISO altimeter and Argo buoy data from 2000 to 2018, the multi-year average three-dimensional structure of mesoscale eddies in the Kuroshio and Oyashio extension regions in the Northwest Pacific Ocean was constructed by synthesis method, and the structural characteristics of temperature anomalies, salt anomalies and sound velocity were analyzed. The sound propagation in eddies is simulated by using Bellhop ray acoustic model. The results show that : (1) Under the background of the cold eddy, the temperature anomaly is negative, the salinity anomaly is negative in the upper layer and positive in the lower layer, and the sound velocity contour rises. Under the background of warm eddy, the temperature anomaly is positive, the salinity anomaly is positive in the upper layer and negative in the lower layer, and the sound velocity contour is sinking. (2) The cold eddies cause the convergence region to shift towards the sound source direction and the width of convergence zone to decrease; the warm eddies cause the convergence zone to move away from the sound source and increase its width. The convergence area in the Kuroshio extension region is wider than that in the Oyashio extension region, and is further away from the sound source. (3) The cold eddies make the convergence zone turning depth shallower, while the warm eddies make the convergence zone turning depth deeper. In the Kuroshio extension region, the inversion depth is shallower with the increase of longitude,but in the Oyashio extension region, the inversion depth is deeper with the increase of longitude.
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.
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.
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.
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.
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.
