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.

Constructing Three-Dimension Space Graph for Outlier Detection Algorithms in Data Mining

Outlier detection has very important applied value in data mining literature. Different outlier detection algorithms based on distinct theories have different definitions and mining processes. The three-dimensional space graph for constructing applied algorithms and an improved GridOf algorithm were proposed in terms of analyzing the existing outlier detection algorithms from criterion and theory. Key words outlier - detection - three-dimensional space graph - data mining CLC number TP 311. 13 - TP 391 Foundation item: Supported by the National Natural Science Foundation of China (70371015)Biography: ZHANG Jing (1975-), female, Ph. D, lecturer, research direction: data mining and knowledge discovery.

3D Multiphase Piecewise Constant Level Set Method Based on Graph Cut Minimization

Segmentation of three-dimensional(3D) complicated structures is of great importance for many real applications.In this work we combine graph cut minimization method with a variant of the level set idea for 3D segmentation based on the Mumford-Shah model.Compared with the traditional approach for solving the Euler-Lagrange equation we do not need to solve any partial differential equations.Instead,the minimum cut on a special designed graph need to be computed.The method is tested on data with complicated structures.It is rather stable with respect to initial value and the algorithm is nearly parameter free.Experiments show that it can solve large problems much faster than traditional approaches.

The existence theorem of absolute equilibrium about games on connected graph with state payoff vector

By introducing state payoff vector to every state node on the connected graph in this paper,dynamic game is researched on finite graphs.The concept of simple strategy about games on graph defined by Berge is introduced to prove the existence theorem of absolute equilibrium about games on the connected graph with state payoff vector.The complete algorithm and an example in the three-dimensional connected mesh-like graph are given in this paper.

Exploration of the potential acting on an electron within diatomic molecules

The potential acting on an electron within a molecule (PAEM) is formulated, and then calculated using the ab initio MELD program plus a separate calculation program in the RHF molecular orbital theory, finally the three-dimensional graphs of the potentials have been drawn. We have systematically investigated this kind of the potentials for a series of the diatomic molecules, such as HF, HCl, HBr, LiF, LiCl, and so on. The three-dimensional graph can clearly display the variation of the potential felt by an electron within a molecule and get a deeper understanding of the electronic motion and chemical bonding within a molecule.