Global Gridded Argo Dataset Based on Gradient-Dependent Optimal Interpolation

ChunLing, Zhang; Dan-Yang, Wang; Liu, Zenghong; Lu, Shaolei; Sun, Cai; Wei, Yongliang; Zhang, Mingxing

doi:10.3390/jmse10050650

Cited by 11 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For assessing the performance of our proposed H-LSTM SSP prediction model, we utilized 60 months of measured SSP historical data obtained from the global Argo dataset spanning from 2017 to 2021 at this designated prediction location. The Argo dataset is provided by the China Argo Real-Time Data Center [28]. The Argo dataset comprises a global grid dataset characterized by a spatial resolution of 1 • × 1 • and a monthly temporal resolution.…”

Section: Data Sourcementioning

confidence: 99%

Predictive Modeling of Future Full-Ocean Depth SSPs Utilizing Hierarchical Long Short-Term Memory Neural Networks

Lu,

Zhang,

et al. 2024

JMSE

View full text Add to dashboard Cite

The spatial-temporal distribution of underwater sound speed plays a critical role in determining the propagation mode of underwater acoustic signals. Therefore, rapid estimation and prediction of sound speed distribution are imperative for facilitating underwater positioning, navigation, and timing (PNT) services. While sound speed profile (SSP) inversion methods offer quicker response times compared to direct measurement methods, these methods often focus on constructing spatial sound velocity fields and heavily rely on sonar observation data, thus imposing stringent requirements on data sources. To delve into the temporal distribution pattern of sound speed and achieve SSP prediction without relying on sonar observation data, we introduce the hierarchical long short-term memory (H-LSTM) neural network for SSP prediction. Our method enables the estimation of sound speed distribution without the need for on-site data measurement, significantly enhancing time efficiency. Compared to other state-of-the-art approaches, the H-LSTM model achieves a root mean square error (RMSE) of less than 1 m/s in predicting monthly average sound speed distribution. Its prediction accuracy has improved several-fold over alternative methods, which validates the robust capability of our proposed model in predicting SSP.

show abstract

Section: Data Sourcementioning

confidence: 99%

Predictive Modeling of Future Full-Ocean Depth SSPs Utilizing Hierarchical Long Short-Term Memory Neural Networks

Lu,

Zhang,

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…With advancements in observational technologies and innovations in data processing methodologies, this domain has witnessed remarkable progress-particularly with the application of neural networks, which has greatly propelled the evolution of ocean temperature and salinity interpolation techniques [4]. In early research endeavors, traditional interpolation methods such as optimal interpolation (OI), Kriging interpolation, and triangular mesh linear interpolation were extensively applied for the processing of ocean temperature and salinity data [5][6][7]. While these methods ameliorated the spatio-temporal distribution of the data, to some extent, they exhibited limitations when dealing with complex oceanic phenomena [8,9], such as the spurious information and discontinuities [10].…”

Section: Introductionmentioning

confidence: 99%

DSE-NN: Discretized Spatial Encoding Neural Network for Ocean Temperature and Salinity Interpolation in the North Atlantic

Liu,

Jia,

Zhang

2024

JMSE

View full text Add to dashboard Cite

The precise interpolation of oceanic temperature and salinity is crucial for comprehending the dynamics of marine systems and the implications of global climate change. Prior neural network-based interpolation methods face constraints related to their capacity to delineate the intricate spatio-temporal patterns that are intrinsic to ocean data. This research presents an innovative approach, known as the Discretized Spatial Encoding Neural Network (DSE-NN), comprising an encoder–decoder model designed on the basis of deep supervision, network visualization, and hyperparameter optimization. Through the discretization of input latitude and longitude data into specialized vectors, the DSE-NN adeptly captures temporal trends and augments the precision of reconstruction, concurrently addressing the complexity and fragmentation characteristic of oceanic data sets. Employing the North Atlantic as a case study, this investigation shows that the DSE-NN presents enhanced interpolation accuracy in comparison with a traditional neural network. The outcomes demonstrate its quicker convergence and lower loss function values, as well as the ability of the model to reflect the spatial and temporal distribution characteristics and physical laws of temperature and salinity. This research emphasizes the potential of the DSE-NN in providing a robust tool for three-dimensional ocean temperature and salinity reconstruction.

show abstract

“…Successive correction analysis (SCA), optimum interpolation (OI), variational methods (3DVAR and 4DVAR), and Kalman filter (KF) are the primary assimilation techniques utilized in ocean research (Cressman, 1959;Danard et al, 1968;Lorenc, 1981;Courtier et al, 1994;Evensen, 1994). Many objective analysis datasets, e.g., the EN4 analysis dataset (Good et al, 2013), the global gridded Argo dataset (Zhang et al, 2022), and reanalysis datasets, e.g., the Simple Ocean Data Assimilation (SODA) reanalysis (Carton and Giese, 2008), the Estimating the Circulation and Climate of the Ocean (ECCO) reanalysis, and the Hybrid Coordinate Ocean Model (HYCOM) reanalysis, have been developed using data assimilation methods. However, as the volume, velocity, variety, and veracity of ocean observation data continue to grow, conventional data assimilation and fusion systems are facing increasingly complicated issues (Bauer et al, 2015;Stammer et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Fusion of ocean data from multiple sources using deep learning: Utilizing sea temperature as an example

Wang

Wang²,

Xiang³

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

For investigating ocean activities and comprehending the role of the oceans in global climate change, it is essential to gather high-quality ocean data. However, existing ocean observation data have deficiencies such as inconsistent spatial and temporal distribution, severe fragmentation, and restricted observation depth layers. Data assimilation is computationally intensive, and other conventional data fusion techniques offer poor fusion precision. This research proposes a novel multi-source ocean data fusion network (ODF-Net) based on deep learning as a solution for these issues. The ODF-Net comprises a number of one-dimensional residual blocks that can rapidly fuse conventional observations, satellite observations, and three-dimensional model output and reanalysis data. The model utilizes vertical ocean profile data as target constraints, integrating physics-based prior knowledge to improve the precision of the fusion. The network structure contains channel and spatial attention mechanisms that guide the network model’s attention to the most crucial features, hence enhancing model performance and interpretability. Comparing multiple global sea temperature datasets reveals that the ODF-Net achieves the highest accuracy and correlation with observations. To evaluate the feasibility of the proposed method, a global monthly three-dimensional sea temperature dataset with a spatial resolution of 0.25°×0.25° is produced by fusing ocean data from multiple sources from 1994 to 2017. The rationality tests on the fusion dataset show that ODF-Net is reliable for integrating ocean data from various sources.

show abstract

Global Gridded Argo Dataset Based on Gradient-Dependent Optimal Interpolation

Cited by 11 publications

References 23 publications

Predictive Modeling of Future Full-Ocean Depth SSPs Utilizing Hierarchical Long Short-Term Memory Neural Networks

Predictive Modeling of Future Full-Ocean Depth SSPs Utilizing Hierarchical Long Short-Term Memory Neural Networks

DSE-NN: Discretized Spatial Encoding Neural Network for Ocean Temperature and Salinity Interpolation in the North Atlantic

Fusion of ocean data from multiple sources using deep learning: Utilizing sea temperature as an example

Contact Info

Product

Resources

About