Networking Observation and Applications of Chinese Ocean Satellites

This paper presents the networking observation capabilities of Chinese ocean satellites and their diverse applications in ocean disaster prevention,ecological monitoring,and resource development.Since the inaugural launch in 2002,China has achieved substantial advancements in ocean satellite technology,forming an observation system composed of the HY-1,HY-2,and HY-3 series satellites.These satellites are integral to global ocean environmental monitoring due to their high resolution,extensive coverage,and frequent observations.Looking forward,China aims to further enhance and expand its ocean satellite capabilities through ongoing projects to support global environmental protection and sustainable development.

Deep learning to estimate ocean subsurface salinity structure in the Indian Ocean using satellite observations

Accurately estimating the ocean subsurface salinity structure(OSSS)is crucial for understanding ocean dynamics and predicting climate variations.We present a convolutional neural network(CNN)model to estimate the OSSS in the Indian Ocean using satellite data and Argo observations.We evaluated the performance of the CNN model in terms of its vertical and spatial distribution,as well as seasonal variation of OSSS estimation.Results demonstrate that the CNN model accurately estimates the most significant salinity features in the Indian Ocean using sea surface data with no significant differences from Argo-derived OSSS.However,the estimation accuracy of the CNN model varies with depth,with the most challenging depth being approximately 70 m,corresponding to the halocline layer.Validations of the CNN model’s accuracy in estimating OSSS in the Indian Ocean are also conducted by comparing Argo observations and CNN model estimations along two selected sections and four selected boxes.The results show that the CNN model effectively captures the seasonal variability of salinity,demonstrating its high performance in salinity estimation using sea surface data.Our analysis reveals that sea surface salinity has the strongest correlation with OSSS in shallow layers,while sea surface height anomaly plays a more significant role in deeper layers.These preliminary results provide valuable insights into the feasibility of estimating OSSS using satellite observations and have implications for studying upper ocean dynamics using machine learning techniques.

Hydrographic Characteristics and Oceanic Heat Flux in the Upper Arctic Ocean over the Alpha Ridge Observed by the DTOP Platform in 2018 and 2021

In 2018 and 2021,the Drift-Towing Ocean Profilers(DTOP)provided extensive temperature and salinity data on the upper 120m ocean through their drifts over the Alpha Ridge north of the Canada Basin.The thickness and temperature maximum of Alaska Coastal Water(ACW)ranged from 20m to 40m and-1.5℃to-0.8℃,respectively,and the salinity generally maintained from 30.2 to 32.5.Comparison with World Ocean Atlas 2018’s climatology manifested a 40m-thick and warm ACW roughly ex-ceeding the temperature maximum by 0.4–0.5℃in June–August 2021.This anomalously warm ACW was highly related to the ex-pansion of the Beaufort Gyre in the negative Arctic Oscillation phase.During summer,the under-ice oceanic heat flux F_(w)^(OHF)was elevated,with a maximum value of above 25Wm^(-2).F_(w)^(OHF)was typically low in the freezing season,with an average value of 1.2Wm^(-2).The estimates of upward heat flux contributed by ACW to the sea ice bottom F_(w)^(OHF)were in the range of 3–4Wm^(-2)in June–August 2021,when ACW contained a heat content of more than 80MJm^(-2).The heat loss over this period was driven by a weak stratification upon the ACW layer associated with a surface mixed layer(SML)approaching the ACW core.After autumn,F_(w)^(OHF)was reduced(<2 Wm^(-2))except during rare events when it elevated F_(w)^(OHF)slightly.In addition,the intensive and widespread Ekman suction,which created a violent upwelling north of the Canada Basin,was largely responsible for the substantial cooling and thinning of the ACW layer in the summer of 2021.

Contrasting physical mechanisms of yellowfin tuna fluctuations between the western and eastern Indian Ocean

As an economically critical pelagic migratory species,yellowfin tuna(Thunnus albacores,YFT)is very sensible to physical and environmental conditions,such as sea surface temperature(SST),ocean heat content(OHC),and the mixed layer depth(MLD).We investigated the impact of SST,OHC,and MLD on fluctuations of YFT catch in the western/eastern Indian Ocean using the long time series of 63-year environmental and YFT datasets.We found that the impact of SST on YFT was heavily overestimated in the past,and MLD plays a more critical role in the YFT catch fluctuation.When the MLD deepens(>34.8 m),SST was more influential in predicting the catches of YFT than OHC in the western Indian Ocean,and OHC was more critical to YFT than SST in the eastern Indian Ocean.However,when the MLD shallows(<34.8 m),MLD was more vital to predict the catch per unit effort(CPUE)of YFT than SST/OHC in the western.After 2000,there was an asynchronous pattern of YFT CPUE induced by higher frequency variations and ocean hiatus of SST/OHC signals in the western and eastern Indian Oceans basins.The impact of the subsurface hiatus may induce the decrease of YFT in the eastern Indian Ocean.The above findings clarified a non-stationary relationship between the environmental factors and catches of YFT and provided new insights into variations in YFT abundance.

Quantifying the Role of the Eddy Transfer Coefficient in Simulating the Response of the Southern Ocean Meridional Overturning Circulation to Enhanced Westerlies in a Coarse-resolution Model

This study assesses the capability of a coarse-resolution ocean model to replicate the response of the Southern Ocean Meridional Overturning Circulation(MOC) to intensified westerlies,focusing on the role of the eddy transfer coefficient(κ).κ is a parameter commonly used to represent the velocities induced by unresolved eddies.Our findings reveal that a stratification-dependent κ,incorporating spatiotemporal variability,leads to the most robust eddy-induced MOC response,capturing 82% of the reference eddy-resolving simulation.Decomposing the eddy-induced velocity into its vertical variation(VV) and spatial structure(SS) components unveils that the enhanced eddy compensation response primarily stems from an augmented SS term,while the introduced VV term weakens the response.Furthermore,the temporal variability of the stratification-dependent κ emerges as a key factor in enhancing the eddy compensation response to intensified westerlies.The experiment with stratification-dependent κ exhibits a more potent eddy compensation response compared to the constant κ,attributed to the structure of κ and the vertical variation of the density slope.These results underscore the critical role of accurately representing κ in capturing the response of the Southern Ocean MOC and emphasize the significance of the isopycnal slope in modulating the eddy compensation mechanism.

Alleviated photoinhibition on nitrification in the Indian Sector of the Southern Ocean

Nitrification,a central process in the marine nitrogen cycle,produces regenerated nitrate in the euphotic zone and emits N_(2)O,a potent greenhouse gas as a by-product.The regulatory mechanisms of nitrification in the Southern Ocean,which is a critical region for CO_(2)sequestration and radiative benefits,remain poorly understood.Here,we investigated the in situ and dark nitrification rates in the upper 500 m and conducted substrate kinetics experiments across the Indian Sector in the Cosmonaut and Cooperation seas in the late austral summer.Our findings indicate that light inhibition of nitrification decreases exponentially with depth,exhibiting a light threshold of 0.53%photosynthetically active radiation.A positive relationship between dark nitrification and apparent oxygen utilization suggests a dependence on substrate availability from primary production.Importantly,an increased NH_(4)^(+) supply can act as a buffer against photo-inhibitory damage.Globally,substrate affinity(α)increases with depth and transitions from light to dark,decreases with increasing ambient NH_(4)^(+)and exhibits a latitudinal distribution,reflecting substrate utilization strategies.We also reveal that upwelling in Circumpolar Deep Water(CDW)stimulates nitrification through the introduction of potentially higher iron and deep diverse nitrifying microorganisms with higherα.We conclude that although light is the primary limiting factor for nitrification in summer,coupling between substrate availability and CDW upwelling can overcome this limitation,thereby alleviating photoinhibition by up to 45%±5.3%.

An efficient method for constructing a random insertional mutant library for forward genetics in Nannochloropsis oceanica

Insertional mutation,phenotypic evaluation,and mutated gene cloning are widely used to clone genes from scratch.Exogenous genes can be integrated into the genome during non-homologous end joining(NHEJ)of the double-strand breaks of DNA,causing insertional mutation.The random insertional mutant library constructed using this method has become a method of forward genetics for gene cloning.However,the establishment of a random insertional mutant library requires a high transformation efficiency of exogenous genes.Many microalgal species show a low transformation efficiency,making constructing random insertional mutant libraries difficult.In this study,we established a highly efficient transformation method for constructing a random insertional mutant library of Nannochloropsis oceanica,and tentatively tried to isolate its genes to prove the feasibility of the method.A gene that may control the growth rate and cell size was identified.This method will facilitate the genetic studies of N.oceanica,which should also be a reference for other microalgal species.

Unveiling three-dimensional sea surface signatures caused by internal solitary waves:insights from the surface water ocean topography mission

Internal solitary waves(ISW),characterized by large amplitude and long propagation distance,are widespread in global oceans.While remote sensing images have played an essential role in studying ISWs,they mainly exploit two-dimensional image information.However,with the launch of the surface water ocean topography(SWOT)satellite on December 16,2022,a unique opportunity has emerged to capture wide-swath three-dimensional ISW-induced sea surface information.In this study,we examine ISWs in the Andaman Sea using data from the Ka-band Radar Interferometer(KaRIN),a crucial sensor onboard SWOT.KaRIN not only provides backscattering satellite images but also employs synthetic aperture interferometry techniques to retrieve wide-swath two-dimensional sea surface height measurements.Our observations in the Andaman Sea revealed the presence of ISWs characterized by dark-bright strips and surface elevation solitons.The surface soliton has an amplitude of 0.32 m,resulting in an estimation of ISW amplitude of approximately 60 m.In contrast to traditional two-dimensional satellite images or nadir-looking altimetry data,the SWOT mission’s capability to capture threedimensional sea surface information represents a significant advancement.This breakthrough holds substantial promise for ISW studies,particularly in the context of ISW amplitude inversion.

Effects of Ocean Acidification on Nitrogen Metabolism of Skeletonema costatum

Ocean acidification(OA),caused by the rising concentration of atmospheric CO_(2),leads to changes in the marine carbonate system.This,in turn,affects the physiological processes of phytoplankton.In response to increased pCO_(2) levels,marine microalgae modulate their physiological responses to meet their energy and metabolic requirements.Nitrogen metabolism is a critical metabolic pathway,directly affecting the growth and reproductive capacity of marine microorganisms.Understanding the molecular mechanisms that regulate nitrogen metabolism in microalgae under OA conditions is therefore crucial.This study aimed to investi-gate how OA affects the expression profiles of key genes in the nitrogen metabolic pathway of the marine diatom Skeletonema costatum.Our findings indicate that OA upregulates key genes involved in the nitrogen metabolic pathway,specifically those related to nitrate assimilation and glutamate metabolism.Moreover,pCO_(2) has been identified as the predominant factor affecting the expression of these genes,with a more significant impact than pH variations in S.costatum.This research not only advances our understanding of the adaptive mechanisms of S.costatum in response to OA but also provides essential data for predicting the ecological consequences of OA on marine diatoms.

Distribution and influencing factors of microeukaryote in different water layers of the southwestern Indian Ocean Ridge

Microeukaryotes play a vital role in shaping marine ecosystems,especially in marine productivity,the microbial food web,and carbon cycle.The Indian Ocean is one of the largest oligotrophic areas in the world,but little is known about the biodiversity of microeukaryotes in the area.The community composition and geographical distribution of microeukaryotes collected from the surface(SUR)and deep chlorophyll maximum(DCM)layers in the southwestern Indian Ocean were studied using high-throughput sequencing of the 18S rRNA gene.The metagenomic data helped quantify the impact of environmental factors on microeukaryotic communities.The relative abundance of different taxa groups exhibited distinct patterns between SUR and DCM layers,except for the most dominant Dinoflagellata that accounted for more than 40.6%abundance in each sample.Radiolaria was much more abundant in the nutrient-rich DCM layer than the SUR layer.The community similarity of microeukaryotes decreased with increasing of geographic distance,whereas the temperature and inorganic nitrogen were the most important environmental parameters to community structure.Abundant communities were more influenced by dispersal limitations and rare communities were more responsive to environmental factors.Correlation network analyses revealed strong biotic interactions indicative of parasitism,predation and competition,and their contribution to microeukaryotic population in diverse environments.Overall,this study provided insights into the biodiversity of microeukaryotes by characterizing the differences between water layers and identifying the driving factors in the ocean.

Prediction of three-dimensional ocean temperature in the South China Sea based on time series gridded data and a dynamic spatiotemporal graph neural network

Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean temperature.Existing graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among data.In this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior knowledge.Temporal and spatial dependencies in the time series were then captured using temporal and graph convolutions.We also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid data.In this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea surface.We compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.

An improved wind quality control for the China-France Oceanography Satellite (CFOSAT) scatterometer

Quality control(QC)is an essential procedure in scatterometer wind retrieval,which is used to distinguish good-quality data from poor-quality wind vector cells(WVCs)for the sake of wind applications.The current wind processor of the China-France Oceanography Satellite(CFOSAT)scatterometer(CSCAT)adopts a maximum likelihood estimator(MLE)-based QC method to filter WVCs affected by geophysical noise,such as rainfall and wind variability.As the first Ku-band rotating fan-beam scatterometer,CSCAT can acquire up to 16 observations over a single WVC,giving abundant information with diverse incidence/azimuth angles,as such its MLE statistical characteristics may be different from the previous scatterometers.In this study,several QC indicators,including MLE,its spatially averaged value(MLE_(m)),and the singularity exponents(SE),are analyzed using the collocated Global Precipitation Mission rainfall data as well as buoy data,to compare their sensitivity to rainfall and wind quality.The results show that wind error characteristics of CSCAT under different QC methods are similar to those of other Ku-band scatterometers,i.e.,SE is more suitable than other parameters for the wind QC at outer-swath and nadir regions,while MLE_(m) is the best QC indicator for the sweet region WVCs.Specifically,SE is much more favorable than others at high wind speeds.By combining different indicators,an improved QC method is developed for CSCAT.The validation with the collocated buoy data shows that it accepts more WVCs,and in turn,improves the quality control of CSCAT wind data.

Contribution of Surface Waves to Sea Surface Temperatures in the Arctic Ocean

The aim of our study was to examine the contribution of surface waves from WAVEWATCH-III(WW3)to the variation in sea surface temperature(SST)in the Arctic Ocean.The simulated significant wave height(SWH)were validated against the products from Haiyang-2B(HY-2B)in 2021,obtaining a root mean squared error(RMSE)of 0.45 with a correlation of 0.96 and scatter index of 0.18.The wave-induced effects,i.e.,wave breaking and mixing induced by nonbearing waves resulting in changes in radiation stress and Stokes drift,were calculated from WW3,ERA-5 wind,SST,and salinity data from the National Centers for Environmental Prediction and were taken as forcing fields in the Stony Brook Parallel Ocean Model.The results showed that an RMSE of 0.81℃ with wave-induced effects was less than the RMSE of 1.11℃ achieved without the wave term compared with the simulated SST with the measurements from Argos.Considering the four wave effects and sea ice freezing,the SST in the Arctic Ocean decreased by up to 1℃ in winter.Regression analysis revealed that the SWH was linear in SST(values without subtraction of waves)in summer and autumn,but this behavior was not observed in spring or winter due to the presence of sea ice.The interannual variation also presented a negative relationship between the difference in SST and SWH.

Assessment of the Southern Ocean Sea Surface Temperature Biases in CMIP5 and CMIP6 Models

This work evaluates the performances of climate models in simulating the Southern Ocean(SO)sea surface temperature(SST)by a large ensemble from phases 5 and 6 of the Coupled Model Intercomparison Project(CMIP5 and CMIP6).By combining models from the same community sharing highly similar SO SST biases and eliminating the effect of global-mean biases on local SST biases,the results reveal that the ensemble-mean SO SST bias at 70°-30°S decreases from 0.38℃ in CMIP5 to 0.28℃ in CMIP6,together with increased intermodel consistency.The dominant mode of the intermodel variations in the zonal-mean SST biases is characterized as a meridional uniform warm bias pattern,explaining 79.1% of the intermodel variance and exhibiting positive principal values for most models.The ocean mixed layer heat budget further demonstrates that the SST biases at 70°-50°S primarily result from the excessive summertime heating effect from surface net heat flux.The biases in surface net heat flux south of 50°S are largely impacted by surface shortwave radiation from cloud and clear sky components at different latitudes.North of 50°S,the underestimated westerlies reduce the northward Ekman transport and hence northward cold advection in models,leading to warm SST biases year-round.In addition,the westerly biases are primarily traced back to the atmosphere-alone model simulations forced by the observed SST and sea ice.These results disclose the thermal origin at the high latitude and dynamical origin at the low latitude of the SO SST biases and underscore the significance of the deficiencies of atmospheric models in producing the SO SST biases.

Predictability of the upper ocean heat content in a Community Earth System Model ensemble prediction system

Upper ocean heat content(OHC)has been widely recognized as a crucial precursor to high-impact climate variability,especially for that being indispensable to the long-term memory of the ocean.Assessing the predictability of OHC using state-of-the-art climate models is invaluable for improving and advancing climate forecasts.Recently developed retrospective forecast experiments,based on a Community Earth System Model ensemble prediction system,offer a great opportunity to comprehensively explore OHC predictability.Our results indicate that the skill of actual OHC predictions varies across different oceans and diminishes as the lead time of prediction extends.The spatial distribution of the actual prediction skill closely resembles the corresponding persistence skill,indicating that the persistence of OHC serves as the primary predictive signal for its predictability.The decline in actual prediction skill is more pronounced in the Indian and Atlantic oceans than in the Pacific Ocean,particularly within tropical regions.Additionally,notable seasonal variations in the actual prediction skills across different oceans align well with the phase-locking features of OHC variability.The potential predictability of OHC generally surpasses the actual prediction skill at all lead times,highlighting significant room for improvement in current OHC predictions,especially for the North Indian Ocean and the Atlantic Ocean.Achieving such improvements necessitates a collaborative effort to enhance the quality of ocean observations,develop effective data assimilation methods,and reduce model bias.

Paper Analysis of Shanghai Ocean University in Bibliometric Method from Web of Science

The data of this research was mainly collected from the Web of Science (WOS) and Incites database platform, which was filtered and cataloged according to the different platforms. For tracing the change in scientific research at Shanghai Ocean University, make use of Bibliometric analysis to get the image and table of highly cited papers and hot papers. In this study, the scientific aspects in highly cited papers and hot papers, published in the last year in the core collection of Web of Science, were taken as objects, and office software was used as the main tool to carry out bibliometric and figure analysis. From the four aspects to find the difference in these fields, the production of specific fields and cited times is inconsistent. And suggest the department and management adjust the policy and method via elastic personnel and rewards to prompt the advancement of the research fields.

Responses of the Southern Ocean mixed layer depth to the eastern and central Pacific El Niño events during austral winter

Based on the Ocean Reanalysis System version 5(ORAS5)and the fifth-generation reanalysis datasets derived from European Centre for Medium-Range Weather Forecasts(ERA5),we investigate the different impacts of the central Pacific(CP)El Niño and the eastern Pacific(EP)El Niño on the Southern Ocean(SO)mixed layer depth(MLD)during austral winter.The MLD response to the EP El Niño shows a dipole pattern in the South Pacific,namely the MLD dipole,which is the leading El Niño-induced MLD variability in the SO.The tropical Pacific warm sea surface temperature anomaly(SSTA)signal associated with the EP El Niño excites a Rossby wave train propagating southeastward and then enhances the Amundsen Sea low(ASL).This results in an anomalous cyclone over the Amundsen Sea.As a result,the anomalous southerly wind to the west of this anomalous cyclone advects colder and drier air into the southeast of New Zealand,leading to surface cooling through less total surface heat flux,especially surface sensible heat(SH)flux and latent heat(LH)flux,and thus contributing to the mix layer(ML)deepening.The east of the anomalous cyclone brings warmer and wetter air to the southwest of Chile,but the total heat flux anomaly shows no significant change.The warm air promotes the sea ice melting and maintains fresh water,which strengthens stratification.This results in a shallower MLD.During the CP El Niño,the response of MLD shows a separate negative MLD anomaly center in the central South Pacific.The Rossby wave train triggered by the warm SSTA in the central Pacific Ocean spreads to the Amundsen Sea,which weakens the ASL.Therefore,the anomalous anticyclone dominates the Amundsen Sea.Consequently,the anomalous northerly wind to the west of anomalous anticyclone advects warmer and wetter air into the central and southern Pacific,causing surface warming through increased SH,LH,and longwave radiation flux,and thus contributing to the ML shoaling.However,to the east of the anomalous anticyclone,there is no statistically significant impact on the MLD.

New Record Ocean Temperatures and Related Climate Indicators in 2023

The global physical and biogeochemical environment has been substantially altered in response to increased atmospheric greenhouse gases from human activities.In 2023,the sea surface temperature(SST)and upper 2000 m ocean heat content(OHC)reached record highs.The 0–2000 m OHC in 2023 exceeded that of 2022 by 15±10 ZJ(1 Zetta Joules=1021 Joules)(updated IAP/CAS data);9±5 ZJ(NCEI/NOAA data).The Tropical Atlantic Ocean,the Mediterranean Sea,and southern oceans recorded their highest OHC observed since the 1950s.Associated with the onset of a strong El Niño,the global SST reached its record high in 2023 with an annual mean of~0.23℃ higher than 2022 and an astounding>0.3℃ above 2022 values for the second half of 2023.The density stratification and spatial temperature inhomogeneity indexes reached their highest values in 2023.

Distribution and abundance of krill in various areas of the Southern Ocean: dataset compilation based on samples collected in CHINARE during 2009-2019

This study investigates the composition,abundance,and basic biological parameters of krill in Prydz Bay,Antarctic Peninsula and Amundsen Sea by analyzing samples and environmental data from the Chinese National Antarctic Research Expeditions conducted between 2009/2010 and 2019/2020.The predominant krill species observed were Euphausia superba,Euphausia crystallorophias,and Thysanoessa macrura.T.macrura,although the most widespread,exhibited the lowest mean abundance 9.96 ind:(1000 m^(-3))and biomass 0.31 g(1000 m^(-3)),predominantly found in low-latitude regions of the Amundsen Sea while E.crystallorophias was most concentrated in polynyas of Prydz Bay.E.superba,with an average abundance of 34.05 ind(1000 m^(-3))and biomass of 11.80 g:(1000 m^(-3)),was mainly distributed in the Antarctic Peninsula and Prydz Bay.This study also identified regional variations in mean body length and frequency distributions of kril.The relationship between krill body length and wet weight followed a power-law pattern.Regional differences were observed in the relationship between krill abundance,biomass,and environmental factors with varying correlations.In the Amundsen Sea,no significant correlation was found between krill abundance and environmental factors.Notably,E.crystallorophias in Prydz Bay demonstrated a significant positive correlation with chlorophyll a concentration,while T.macrura abundance and biomass in the Antarctic Peninsula exhibited a significant negative correlation with ice-free days.The findings contribute valuable regional data on krll distribution,abundance,and biomass in the Southern Ocean,serving as foundational information for the conservation of the Southern Ocean ecosystem and Antarctic krill fishery management on a circumpolar scale.

ST-LSTM-SA:A New Ocean Sound Velocity Field Prediction Model Based on Deep Learning

The scarcity of in-situ ocean observations poses a challenge for real-time information acquisition in the ocean.Among the crucial hydroacoustic environmental parameters,ocean sound velocity exhibits significant spatial and temporal variability and it is highly relevant to oceanic research.In this study,we propose a new data-driven approach,leveraging deep learning techniques,for the prediction of sound velocity fields(SVFs).Our novel spatiotemporal prediction model,STLSTM-SA,combines Spatiotemporal Long Short-Term Memory(ST-LSTM) with a self-attention mechanism to enable accurate and real-time prediction of SVFs.To circumvent the limited amount of observational data,we employ transfer learning by first training the model using reanalysis datasets,followed by fine-tuning it using in-situ analysis data to obtain the final prediction model.By utilizing the historical 12-month SVFs as input,our model predicts the SVFs for the subsequent three months.We compare the performance of five models:Artificial Neural Networks(ANN),Long ShortTerm Memory(LSTM),Convolutional LSTM(ConvLSTM),ST-LSTM,and our proposed ST-LSTM-SA model in a test experiment spanning 2019 to 2022.Our results demonstrate that the ST-LSTM-SA model significantly improves the prediction accuracy and stability of sound velocity in both temporal and spatial dimensions.The ST-LSTM-SA model not only accurately predicts the ocean sound velocity field(SVF),but also provides valuable insights for spatiotemporal prediction of other oceanic environmental variables.