Search Results (12)

Understanding subsurface temperature-transition structures is essential for interpreting upper-ocean stratification; however, most existing methods rely on two-dimensional profiles and fail to resolve the full three-dimensional geometry of temperature anomalies. This study proposes the Three-Dimensional Ocean Temperature Structure Extraction method (3D-OTSE), a flexible data-driven framework that identifies coherent three-dimensional thermal-transition features directly from multi-depth ocean temperature fields. The method defines a Temperature-Contrast Index (TCI) based on local three-dimensional temperature differences, determines an adaptive threshold from the curvature of the TCI distribution, and employs 3D DBSCAN to extract volumetric structures. Rather than assuming a thermocline, 3D-OTSE detects a wide range of vertical temperature anomalies—including thermoclines, inverse thermoclines, and multilayer transitions—according to their spatial organization in the data. Applying this method to the South China Sea Basin (SCS) can reconstruct thermocline-like structures that conform to large-scale regional patterns and can also capture complex lateral variations that are difficult to detect by traditional profile diagnosis methods. The region-adaptive threshold enables this framework to adapt to inhomogeneous formation states and spatio-temporal scales. In general, 3D-OTSE provides a universal, parameter-adaptive tool for finding three-dimensional underground temperature anomaly layers, supplements perspectives for traditional methods, and lays the foundation for future multivariate and time-varying applications. Full article

In this paper, we develop a deep learning neural network characterized by feature fusion and physical guidance (denoted as FFPG-net) for reconstructing subsurface sea temperature (T) and salinity (S) from sea surface data. Designed with the idea of feature fusion, FFPG-net combines the deep learning algorithms of residual and channel attention with the physical constraints of vertical modes of T/S profiles decomposed by empirical orthogonal functions (EOFs). The results from a series of single point experiments show that FFPG-net outperforms the CNN or CNN-PG (without physical guidance or feature fusion) in the reconstruction of subsurface T/S in a region of the South China Sea (SCS), with monthly mean RMSEs of 0.31 °C (0.35 °C) and 0.06 psu (0.07 psu) for the reconstructed T/S profiles in winter (summer), averaged over the water depth of 1200 m and the study area. In addition, the performance of the FFPG-net can be improved significantly by incorporating full surface currents or geostrophic currents derived from SSH into the input variables for training the neural network. The preliminary application of FFPG-net in the SCS using satellite-derived sea surface observations indicates that FFPG-net is reliable and feasible for reconstructing subsurface ocean thermal fields in real situations. Our study highlights the advantages and necessity of combining deep learning algorithms with physical constraints in reconstructing subsurface T/S profiles. It provides an effective tool for reconstructing the subsurface global ocean from remote-sensing sea surface observations in the future. Full article

The South China Sea, a vital marginal sea in tropical–subtropical Southeast Asia, plays a globally significant role in marine biodiversity and climate system dynamics. The accurate monitoring of its thermal structure is essential for ecological and climatic studies, yet retrieving subsurface temperature remains challenging due to complex ocean–atmosphere interactions. This study develops a Convolutional Long Short-Term Memory (ConvLSTM) neural network, integrating multi-source satellite remote sensing data, to reconstruct the Ocean Subsurface Temperature Structure (OSTS). To address the multiparameter complexity of temperature retrieval, physical constraints—particularly the heat budget balance of water bodies—are incorporated into the loss function. Experiments demonstrate that the physics-informed ConvLSTM model significantly improves the temperature estimation accuracy by simultaneously optimizing the physical consistency and predictive performance. The proposed approach advances ocean remote sensing by synergizing data-driven learning with thermodynamic principles, offering a robust framework for understanding the South China Sea’s thermal variability. Full article

Accurately and timely estimating three-dimensional ocean states is crucial for improving operational ocean forecasting capabilities. Although satellite observations provide valuable evolutionary information, they are confined to surface-level variables. While in situ observations can offer subsurface information, their spatiotemporal distribution is highly uneven, making it difficult to obtain complete three-dimensional ocean structures. This study developed an operational-oriented lightweight framework for three-dimensional ocean state reconstruction by integrating multi-source observations through a computationally efficient multivariate empirical orthogonal function (MEOF) method. The MEOF method can extract physically consistent multivariate ocean evolution modes from high-resolution reanalysis data. We utilized these modes to further integrate satellite remote sensing and buoy observation data, thereby establishing physical connections between the sea surface and subsurface. The framework was tested in the South China Sea, with optimal data integration schemes determined for different reconstruction variables. The experimental results demonstrate that the sea surface height (SSH) and sea surface temperature (SST) are the key factors determining the subsurface temperature reconstruction, while the sea surface salinity (SSS) plays a primary role in enhancing salinity estimation. Meanwhile, current fields are most effectively reconstructed using SSH alone. The evaluations show that the reconstruction results exhibited high consistency with independent Argo observations, outperforming traditional baseline methods and effectively capturing the vertical structure of ocean eddies. Additionally, the framework can easily integrate sparse in situ observations to further improve the reconstruction performance. The high computational efficiency and reasonable reconstruction results confirm the feasibility and reliability of this framework for operational applications. Full article

Observational data on ocean subsurface temperature and salinity are patently insufficient because in situ observations are complex and costly, while satellite remote-sensed measurements are abundant but mainly focus on sea surface data. To make up for the ocean interior data shortage and entirely use the abundant satellite data, we developed a data-driven deep learning model named Convformer to reconstruct ocean subsurface temperature and salinity fields from satellite-observed sea surface data. Convformer is designed by deeply optimizing Vision Transformer and ConvLSTM, consisting of alternating residual connections between multiple temporal and spatial attention blocks. The input variables consist of sea surface temperature (SST), sea surface salinity (SSS), sea surface height (SSH), and sea surface wind (SSW). Our results demonstrate that Convformer exhibits superior performance in estimating the temperature-salinity structure of the tropical Pacific Ocean. The all-depth average root mean square error (RMSE) of the reconstructed subsurface temperature (ST)/subsurface salinity (SS) is 0.353 °C/0.0695 PSU, with correlation coefficients (R²) of 0.98663/0.99971. In the critical thermocline, although the root mean square errors of ST and SS reach 0.85 °C and 0.121 PSU, respectively, they remain smaller compared to other models. Furthermore, we assessed Convformer’s performance from various perspectives. Notably, we also delved into the potential of Convformer to extract physical and dynamic information from a model mechanism perspective. Our study offers a practical approach to reconstructing the subsurface temperature and salinity fields from satellite-observed sea surface data. Full article

Mesoscale eddies are common in global oceans, playing crucial roles in ocean dynamics, ocean circulation, and heat transport, and their vertical structures can affect the water layers from tens to thousands of meters. In this study, we integrated sea surface height and sea surface temperature data into deep learning methods to study the mesoscale eddy subsurface temperature structure and to explore the relationship between sea surface data and eddy subsurface layers. In this study, we introduce Dual_EddyNet, a deep learning algorithm designed to invert the subsurface temperature structure of mesoscale eddies. Using this algorithm, we explore the impact of the sea surface height and sea surface temperature on the subsurface temperature structure inversion of mesoscale eddies. Furthermore, we compare different data fusion strategies, namely single-stream neural networks and dual-stream neural networks, to validate the effectiveness of the dual-stream model. To capture the interrelations among surface data and integrate feature information across various dimensions, we introduce the Triplet Attention Mechanism. The experimental results demonstrate that the proposed Dual_EddyNet performs well in reconstructing the three-dimensional structure of mesoscale eddies in the South China Sea (within a depth of 1000 m), with an inversion accuracy of 91.44% for cyclonic eddies and 95.25% for anticyclonic eddies. This algorithm provides a new method for inverting the subsurface temperatures of mesoscale eddies, and can not only be directly deployed in systems, embedded in ship moving platforms, etc., but can also provide a data reference for assimilations and numerical simulations, demonstrating its rich application potential. Full article

Satellite remote sensing can provide observation information of the sea surface, and using the sea surface information to reconstruct the subsurface temperature (ST) and subsurface salinity (SS) information has significant application values. This study proposes an intelligent algorithm based on Dual Path Convolutional Neural Networks (DP-CNNs) to reconstruct the ST and SS. The DP-CNN can integrate known information including sea surface temperature (SST), sea surface salinity (SSS), and sea surface height (SSH) to reconstruct the ST and SS. The reconstruction model based on DP-CNN can solve the problem of detail information loss in traditional CNN (Convolutional Neural Network) models. This study performs experiments for the South China Sea under different seasons using reanalysis data. The experimental results show that the DP-CNN models have higher reconstruction accuracy than the CNN models, and this proves that DP-CNNs effectively mitigate the loss of detailed information in the CNN models. Compared with the ground truth data, the ST/SS reconstruction results of the DP-CNN model exhibited a high coefficient of determination (0.93/0.86) and a low root mean square error (around 0.31 °C/0.05 PSU). Therefore, the DP-CNN models can be used as an effective approach to reconstruct ST and SS using sea surface information. Full article

The ability to monitor and predict sea temperature is crucial for determining the likelihood that ocean-related events will occur. However, most studies have focused on predicting sea surface temperature, and less attention has been paid to predicting sea subsurface temperature (SSbT), which can reflect the thermal state of the entire ocean. In this study, we use a 3D U-Net model to predict the SSbT in the upper 400 m of the Pacific Ocean and its adjacent oceans for lead times of 12 months. Two reconstructed SSbT products are added to the training set to solve the problem of insufficient observation data. Experimental results indicate that this method can predict the ocean temperature more accurately than previous methods in most depth layers. The root mean square error and mean absolute error of the predicted SSbT fields for all lead times are within 0.5–0.7 °C and 0.3–0.45 °C, respectively, while the average correlation coefficient scores of the predicted SSbT profiles are above 0.96 for almost all lead times. In addition, a case study qualitatively demonstrates that the 3D U-Net model can predict realistic SSbT variations in the study area and, thus, facilitate understanding of future changes in the thermal state of the subsurface ocean. Full article

The application of remote sensing observations in estimating ocean sub-surface temperatures has been widely adopted. Machine learning-based methods in particular are gaining more and more interest. While there is promising relevant progress, most temperature profile reconstruction models are still built upon the gridded Argo data regardless of the impacts of mesoscale oceanic processes. As a follow-on to the previous study that demonstrates the influence of ocean fronts is negligible, we focus on the improvement of temperature profile reconstruction by introducing the sea surface temperature (SST) gradient into the neural network model. The model sensitivity assessments reveal that the normalization of the input variables achieves a higher estimation accuracy than the original scale. Five experiments are then designed to examine the model performances with or without the SST gradient input. Our results confirm that, for a given model configuration, the one with the input of the SST gradient has the lowest reconstruction bias in comparison to the in situ Argo measurements. Such improvement is particularly pronounced below 200 m depth. We also found that the non-linear activation functions and deeper network structures facilitate the performance of reconstruction models. Results of this work open new insights and challenges to refine the mapping of upper ocean temperature structures. While more relevant machine learning methods are worth further exploitation, how to better characterize the mesoscale oceanic processes from surface observations and bring them into the reconstruction models is the key and needs much attention. Full article

Reconstructing the vertical structures of the ocean from sea surface information is of great importance for ocean and climate studies. In this study, an ensemble machine learning (Ens-ML) model is proposed to retrieve ocean subsurface thermal structure (OSTS) by using satellite-derived sea surface data and Argo data in the South China Sea (SCS). The input data include sea surface height (SSH), sea surface temperature (SST), sea surface salinity (SSS), sea surface wind (SSW), and geographic information (including longitude and latitude). We select three stable machine learning models, namely, extreme gradient boosting (XGBoost), RandomForest and light gradient boosting machine (LightGBM) as our benchmark models, and then use an artificial neural network (ANN) technique to combine outputs from the three individual models. The proposed Ens-ML model using sea surface data only by SSH, SST, SSS, and SSW performs less satisfactorily than that considering the contribution of geographical information, indicating that the geographical information is essential to estimate the OSTS accurately. The estimated OSTS from the Ens-ML model are compared with Argo data. The results show that the proposed Ens-ML model can accurately estimate the OSTS (upper 1000 m) in the SCS, which is relatively more accurate and precise than the individual models. The performance of the Ens-ML model also varies with season, and better estimation is obtained in winter, which is probably due to stronger mixing and weaker stratification. This study shows the great potential and advantage of the multi-model ensemble of machine learning algorithm for the ocean’s interior information retrieving, showing great potential in expanding the scope of ocean observations. Full article

Mesoscale sea surface temperature (SST) variability triggers mesoscale air–sea interactions and is linked to ocean subsurface mesoscale dynamics. The National Oceanic and Atmospheric Administration (NOAA) daily Optimum Interpolation SST (OISST) products, based on various satellite and in situ SST data, are widely utilized in the investigation of multi-scale SST variabilities and reconstruction of subsurface and deep-ocean fields. The quality of OISST datasets is subjected to temporal inhomogeneity due to alterations in the merged data. Yet, whether this issue can significantly affect mesoscale SST variability is unknown. The analysis of this study detects an abrupt enhancement of mesoscale SST variability after 2007 in the OISST-AVHRR-only version 2 and version 2.1 datasets (hereafter OI.v2-AVHRR-only and OI.v2.1-AVHRR-only). The contrast is most stark in the subtropical western boundary current (WBC) regions, where the average mesoscale SST variance during 2007–2018 is twofold larger than that during 1993–2006. Further comparisons with other satellite SST datasets (TMI, AMSR-E, and WindSAT) suggest that the OISST-AVHRR-only datasets have severely underestimated mesoscale SST variability before 2007. An evaluation of related documents of the OISST data indicates that this bias is mainly caused by the change of satellite AVHRR instrument in 2007. There are no corresponding changes detected in the associated fields, such as the number and activity of mesoscale eddies or the background SST gradient in these regions, confirming that the underestimation of mesoscale SST variability before 2007 is an artifact. Another OISST product, OI.v2-AVHRR-AMSR, shows a similar abrupt enhancement of mesoscale SST variability in June 2002, when the AMSR-E instrument was incorporated. This issue leaves potential influences on scientific research that utilize the OISST datasets. The composite SST anomalies of mesoscale eddies based on the OI.v2-AVHRR-only data are underestimated by up to 37% before 2007 in the subtropical WBC regions. The underestimation of mesoscale variability also affects the total (full-scale) SST variability, particularly in winter. Other SST data products based on the OISST datasets were also influenced; we identify suspicious changes in J-OFURO3 and CFSR datasets; the reconstructed three-dimensional ocean products using OISST data as input may also be inevitably affected. This study reminds caution in the usage of the OISST and relevant data products in the investigation of mesoscale processes. Full article

The mixed layer depth (MLD) is generally estimated using in situ or model data. However, MLD analyses have limitations due to the sparse resolution of the observed data. Therefore, this study reconstructs three-dimensional (3D) ocean thermal structures using only satellite sea surface measurements for a higher spatial and longer temporal resolution than that of Argo and diagnoses the decadal variation of global MLD variability. To simulate the ocean thermal structures, the relationship between the ocean subsurface temperature and the sea surface fields was computed based on gridded Argo data. Based on this relationship, high spatial resolution and extended periods of satellite-derived altimeter, sea surface temperature (SST), and wind stress data were used to estimate the 3D ocean thermal structures with 0.25° spatial resolution and 26 standard depth levels (5–2000 m) for 24 years (1993–2016). Then, the MLD was calculated using a temperature threshold method (∆T = 0.2 °C) and correlated reasonably well (>0.9) with other MLD datasets. The extended 24-year data enabled us to analyze the decadal variability of the MLD. The global linear trend of the 24-year MLD is −0.110 m yr⁻¹; however, from 1998 to 2012, the linear trend is −0.003 m yr⁻¹ which is an order of magnitude smaller than that of other periods and corresponds to a global warming hiatus period. Via comparisons between the trends of the SST anomalies and the MLD anomalies, we tracked how the MLD trend changes in response to the global warming hiatus. Full article