Accurately predicting the spatio-temporal evolution trends and long-term dynamics of three-dimensional ocean temperature and salinity plays a crucial role in monitoring climate system changes and conducting fundamental oceanographic research. Numerical models are the most prevalent of the traditional approaches, which are often too complex and lack of generality. Recently, with the rise of AI, many data-driven methods are proposed. However, most of them take no consideration of natural physical laws that may cause issues of physical inconsistency among different variables. In this paper, we proposed PGTransNet, a novel physics-guided transformer network for 3D Ocean temperature and salinity forecasting. This model is based on Vision Transformer, and to enhance the performance we have three aspects of improvements. Firstly, we design a loss function that deliveries the physical relationship among temperature, salinity and density by fusing the Thermodynamic Equation. Secondly, to capture global and long-term dependencies effectively, we add the Pacific Decadal Oscillation (PDO) and North Pacific Gyre Oscillation (NPGO) in the embedding layer. Thirdly, we adopted the Laplacian sparse positional encodings to alleviate the artifacts caused by high-norm tokens. The former two are the core components to leverage the physical information. Finally, to comprehensively evaluate PGTransnet, we conduct rich experiments in metrics RMSE, Anomoly Correlation Coefficients, Bias and physical consistency. Our proposal demonstrates higher prediction accuracy with fast convergence, and the metrics and visualizations show that our model is insensitive to hyperparameter tuning, ensuring better generalization and adherence to physical consistency. Moreover, as observed from the spatial distribution of the anomaly correlation coefficient, the model exhibits higher forecasting accuracy for coastal and marginal sea regions.

Higher-accuracy long-term ocean temperature prediction plays a critical role in ocean-related research fields and climate forecasting (e.g., oceanic internal waves and mesoscale eddies). The essential component of traditional physics-based numerical models for ocean temperature prediction is solving partial differential equations (PDEs), which has immense challenges in terms of parameterization, initial values, and boundary conditions setting. Moreover, the existing machine learning models for ocean temperature prediction have “black box” problems, and the influence of external dynamic factors is not considered. Moreover, it is hard to judge whether the model satisfies certain physical laws. In this paper, we propose a physics-guided spatio-temporal data analysis model based on the widely used ConvLSTM model to achieve long-term ocean temperature prediction and adopt two schemes to train the model in vector output and multiple parallel input and multi-step output. Meanwhile, considering the spatio-temporal correlation, physical information such as oceanic stable stratification is introduced to guide the model training. We evaluate our proposed approach on several popular deep learning models in different timesteps and data volumes in the northern coast of the South China Sea, where the frequent occurrence of internal waves leads to an intensity trend of a local transformation of sea temperature. The results show higher prediction accuracy compared with the traditional LSTM, and ConvLSTM models, and the introduction of physical laws can improve data utilization while enhancing the physical consistency of the model.

Validating Sea Surface Salinity (SSS) data has become a key component of the Soil Moisture Ocean Salinity (SMOS) satellite mission. In this study, the gridded SMOS SSS products are compared with in situ SSS data from analyzed products, a ship-based thermosalinograph and a tropical moored buoy array. The comparison was conducted at different spatial and temporal scales. A regional comparison in the Baltic Sea shows that SMOS slightly underestimates the mean SSS values. The influence of river discharge overrides the temperature in the Baltic Sea, bringing larger biases near river mouths in warm seasons. The global comparison with two Optimal Interpolated (OI) gridded in situ products shows consistent large-scale structures. Excluding regions with large SSS biases, the mean ΔSSS between monthly gridded SMOS data and OI in situ data is −0.01 PSU in most open sea areas between 60°S and 60°N, with a mean Root Mean Square Deviation (RMSD) of 0.2 PSU and a mean correlation coefficient of 0.50. An interannual tendency of mean ΔSSS shifting from negative to positive between satellite SSS and in situ SSS has been identified in tropical to mid-latitude seas, especially across the tropical eastern Pacific Ocean. A comparison with collocated buoy salinity shows that on weekly and interannual scales, the SMOS Level 3 (L3) product well captures the SSS variations at the locations of tropical moored buoy arrays and shows similar performance with in situ gridded products. Excluding suspicious buoys, the synergetic analysis of SMOS, SMAP and gridded in situ products is capable of identifying the erroneous data, implying that satellite SSS has the potential to act as a real-time 27 Quality Control (QC) for buoy data.

Marine heatwaves (MHWs) can significantly impact marine ecosystems and socio-economic systems, and their severity may increase with global warming. Nevertheless, research on the onset and decline rates of MHWs remains limited, and their historical and future variations are not yet fully understood. This study, therefore, analyzes the spatiotemporal characteristics of MHW onset and decline rates by using historical and future sea surface temperature data from OISSTv2.1 and CMIP6. The results indicate that during the historical period from 1982 to 2014, MHW onset and decline rates were higher in eddy-active mid-latitude current systems and the western tropical region but lower in subtropical gyres. A remarkably high correlation (0.94) exists between the onset and decline rates; regions with higher onset rates also tend to have higher decline rates. Approximately 49.69% of the global ocean exhibits an increasing trend in MHW onset rates, with significant increases observed in the Eastern Equatorial Pacific. Meanwhile, 92.87% of oceanic regions exhibit an increase in decline rates. Looking ahead to the future (2015~2100), both the SSP245 and SSP585 scenarios display consistent spatial patterns of MHW onset and decline rates. The Kuroshio-Oyashio Extension, Gulf Stream, Antarctic Circumpolar Current, and Brazil-Malvinas Confluence regions exhibit relatively higher onset and decline rates. Under the SSP585 scenario, both the onset and decline rates of MHWs are higher than those under the SSP245 scenario. This indicates that as global warming intensifies, more extreme MHWs are likely to occur. This finding indicates that it is necessary to pay attention to the rate of global warming when mitigating its potential impacts.

The algorithms based on Surface Quasi-Geostrophic (SQG) dynamics have been developed and validated by many researchers through model products, however it is still doubtful whether these SQG-based algorithms are worth using in terms of observed data. This paper analyzes the factors impeding the practical application of SQG and makes amends by a simple “first-guess (FG) framework”. The proposed framework includes the correction of satellite salinity and the estimation of the FG background, making the SQG-based algorithms applicable in realistic circumstances. The dynamical-statistical method SQG-mEOF-R is thereafter applied to satellite data for the first time. The results are compared with two dynamical algorithms, SQG and isQG, and three empirical algorithms, multivariate linear regression (MLR), random forest (RF), and mEOF-R. The validation against Argo profiles showed that the SQG-mEOF-R presents a robust performance in mesoscale reconstruction and outperforms the other five algorithms in the upper layers. It is promising that the SQG-mEOF-R and the FG framework are applicable to operational reconstruction.

Sea surface salinity (SSS) observations play a crucial role in the study of ocean circulation, climate variability, and marine ecosystems. However, current satellite SSS products suffer from systematic biases due to factors such as radio frequency interference (RFI) and land contamination, resulting in fundamental limitations to their application for SSS monitoring. To address this issue, we propose a physics-informed neural network (PINN) approach that directly integrates radiative transfer physical processes into the neural network architecture for SMAP L2 SSS bias correction. This method ensures oceanographically consistent corrections by embedding physical constraints into the forward propagation model. The results demonstrate that PINN achieved a root mean square error (RMSE) of 0.249 PSU, representing a 5.3% to 8.5% relative performance improvement compared to conventional methods—GBRT, ANN, and XGBoost. Further temporal stability analysis reveals that PINN exhibits significantly reduced RMSE variations over multi-year periods, demonstrating exceptional long-term correction stability. Meanwhile, this method achieves more uniform bias improvement in contaminated nearshore regions, showing distinct advantages over the inconsistent correction patterns of conventional methods. This study establishes a physics-constrained machine learning framework for satellite SSS data correction by integrating oceanographic domain knowledge, providing a novel technical pathway for reliable enhancement of Earth observation data.