Three-dimensional visualization method and system for space weather data
Through three-dimensional visualization methods and machine learning models, the magnetic layer and aurora data are processed, and the magnetic layer and aurora data visualization efficiency in the existing technology is solved, and efficient and accurate data analysis of aurora distribution and magnetic field distribution is achieved, which improves the data Intuitive and real-time.
Patent Information
- Application Number
- CN202410927870.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-11
- Publication Date
- 2024-11-15
AI Technical Summary
In the prior art, the two-dimensional visualization efficiency of magnetosphere and aurora data is low, unable to monitor in real time, poor intuitiveness, and unable to effectively display the complexity of the sun-earth spatial state.
A three-dimensional visualization method is adopted to receive magnetic layer and aurora data, interpolate it into a preset spatial grid, generate magnetic lines and aurora distribution information, and combine machine learning models for data processing and simulation to construct a blue magnetic lines and aurora spatial distribution visualization model.
It realizes efficient and automated analysis of aurora distribution and magnetic field distribution data, improves processing accuracy and efficiency, and enhances the intuitiveness and real-timeness of the data.
Smart Images

Figure CN118965936A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of space magnetosphere and aurora visualization observation, and in particular to a three-dimensional visualization method and system for space weather data. Background Art
[0002] Visualization technology can be used to intuitively display the state of the Sun-Earth space in a specific time zone, which can help meteorologists analyze data and make accurate judgments in a short time. Since the parameters of the Sun-Earth space state are diverse, nonlinear, and highly complex, they are highly dependent on visualization, making the visualization of the Sun-Earth space state one of the focuses of current space science application research.
[0003] In the field of space magnetosphere and aurora observation for the visualization of the Sun-Earth space status, the commonly used data visualization models are mostly two-dimensional. Their disadvantages are low efficiency, inability to monitor in real time, and poor intuitiveness. Summary of the invention
[0004] The present application provides a three-dimensional visualization method and system for space weather data, aiming to solve the technical problem of low efficiency and poor real-time performance in the visualization and monitoring of magnetosphere and aurora data in the prior art.
[0005] In view of the above problems, the present application provides a three-dimensional visualization method and system for space weather data.
[0006] The first aspect disclosed in the present application provides a three-dimensional visualization method for space weather data, including: when receiving a visualization monitoring request for the magnetosphere and aurora, an interactive meteorological observation station receives space weather data, interpolates the space weather data into a preset spatial grid, and obtains space weather data distribution information; processes the space weather data distribution information through a spatial magnetic field distribution model to generate blue magnetic field line spatial distribution information, wherein the blue magnetic field line spatial distribution information has a magnetic field intensity distribution label; configures aurora observation attributes, wherein the aurora observation attributes at least include a coronal mass ejection position index, a coronal mass ejection mass index, and a coronal mass transport speed index; Aurora observation data is collected based on the coronal mass ejection position index, the coronal mass ejection mass index, and the coronal mass transfer speed index, and aurora distribution simulation is performed in combination with the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label to generate aurora spatial distribution information; based on the aurora spatial distribution information, aurora observation line distribution is performed on a preset area to generate aurora observation line spatial distribution information; based on the blue magnetic field line spatial distribution information, a blue magnetic field line spatial distribution visualization model is constructed; based on the aurora spatial distribution information, a global aurora spatial distribution visualization model is constructed; based on the aurora spatial distribution information, an aurora observation line spatial distribution visualization model is constructed.
[0007] Another aspect disclosed in the present application provides a three-dimensional visualization system for space weather data, including: a prediction request receiving module, which is used to receive a visualization monitoring request for the magnetosphere and the aurora, interact with a meteorological observation station, receive space weather data, interpolate the space weather data into a preset space grid, and obtain space weather data distribution information; a space magnetic field distribution module, which is used to process the space weather data distribution information through a space magnetic field distribution model to generate blue magnetic field line spatial distribution information, wherein the blue magnetic field line spatial distribution information has a magnetic field intensity distribution label; an aurora data configuration module, which is used to configure aurora observation attributes, wherein the aurora observation attributes at least include a coronal mass ejection position index, a coronal mass ejection mass index, and a coronal mass transport speed index. an aurora distribution simulation module for collecting aurora observation data based on the coronal mass ejection position index, the coronal mass ejection mass index, and the coronal mass transfer speed index, performing aurora distribution simulation, and generating aurora spatial distribution information; an aurora observation prediction module for performing aurora observation line distribution for a preset area based on the aurora spatial distribution information, and generating aurora observation line spatial distribution information; a magnetic field visualization module for constructing a blue magnetic field line spatial distribution visualization model according to the blue magnetic field line spatial distribution information; an aurora visualization module for constructing a global aurora spatial distribution visualization model according to the aurora spatial distribution information; an aurora observation line visualization module for constructing an aurora observation line spatial distribution visualization model according to the aurora spatial distribution information.
[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0009] By adopting the spatial magnetic field distribution model built based on machine learning, the distribution information of space weather data is processed to generate the spatial distribution information of blue magnetic lines. Then, aurora observation data is collected to simulate the aurora distribution. It is predicted whether the aurora can be observed in the preset area, and the spatial distribution information of aurora observation lines is generated. Finally, a technical solution is constructed to visualize the spatial distribution model of blue magnetic lines, the global aurora spatial distribution visualization model and the aurora observation line spatial distribution visualization model. The model is built through machine learning and combined with motion simulation analysis to achieve efficient and automated analysis of aurora distribution data and magnetic field distribution data. In addition, the large model combined with simulation analysis is more objective and the accuracy is improved, so the technical effect of optimizing processing efficiency and processing accuracy is achieved.
[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Figure 1 A possible flow chart of a method for three-dimensional visualization of space weather data is provided for an embodiment of the present application.
[0012] Figure 2 A schematic diagram of a possible blue magnetic field line spatial distribution visualization model provided in an embodiment of the present application.
[0013] Figure 3 A possible structural schematic diagram of a three-dimensional visualization system for space weather data is provided for an embodiment of the present application.
[0014] Explanation of the accompanying drawings: prediction request receiving module 100, spatial magnetic field distribution module 200, aurora data configuration module 300, aurora distribution simulation module 400, aurora observation prediction module 500, magnetic field visualization module 600, aurora visualization module 700, aurora observation line visualization module 800. DETAILED DESCRIPTION
[0015] Various non-limiting implementation methods of the present application will be described in detail below in conjunction with the accompanying drawings.
[0016] Embodiment 1
[0017] like Figure 1 As shown, the embodiment of the present application provides a three-dimensional visualization method of space weather data, including the steps of:
[0018] S10: When receiving an aurora observation line prediction request, the interactive meteorological observation station receives space weather data, interpolates the space weather data into a preset space grid, and obtains space weather data distribution information.
[0019] Further, receiving space weather data, step S10 comprises the steps of:
[0020] S11: Configuring space weather data attributes, wherein the space weather data attributes include at least a solar wind speed index, a solar wind density index, a solar wind temperature index, an ionospheric electron density index, an ionospheric electron temperature index, an ionospheric F2 layer critical frequency index, a magnetosphere magnetic field strength index, a magnetosphere magnetic field direction index, a magnetosphere plasma density index, and a magnetosphere plasma temperature index.
[0021] S12: Collect the space weather data according to the solar wind speed index, the solar wind density index, the solar wind temperature index, the ionosphere electron density index, the ionosphere electron temperature index, the ionosphere F2 layer critical frequency index, the magnetosphere magnetic field strength index, the magnetosphere magnetic field direction index, the magnetosphere plasma density index, and the magnetosphere plasma temperature index.
[0022] Specifically, when the user needs to generate a three-dimensional visualization model of the aurora observation line, preferably, the aurora observation line prediction request can be input through the user terminal interface. When the server receives the aurora observation line prediction request, that is, the interactive meteorological observation station, collects space weather data of a preset attribute set, exemplarily: the preset attribute set at least includes a solar wind speed index, a solar wind density index, a solar wind temperature index, an ionosphere electron density index, an ionosphere electron temperature index, an ionosphere F2 layer critical frequency index, a magnetosphere magnetic field strength index, a magnetosphere magnetic field direction index, a magnetosphere plasma density index, and a magnetosphere plasma temperature index.
[0023] In detail, by sending the solar wind speed index, solar wind density index, solar wind temperature index, ionosphere electron density index, ionosphere electron temperature index, ionosphere F2 layer critical frequency index, magnetosphere magnetic field strength index, magnetosphere magnetic field direction index, magnetosphere plasma density index, and magnetosphere plasma temperature index to the meteorological observation station, future space weather data can be obtained. Since the above space weather data has a great influence on the earth's magnetic field, the space weather data is first collected and stored to facilitate the subsequent accuracy analysis of the earth's magnetic field distribution.
[0024] Furthermore, the preset spatial grid refers to a space constructed by dividing the earth space into several squares according to the side length preset by the user, which can realize the precise positioning of any position and facilitate the segmentation, analysis and storage of large amounts of data. The spatial weather data is deployed at the corresponding positions of the preset spatial grid according to the collection position, thereby generating the spatial weather data distribution information and waiting for the next step call.
[0025] S20: Processing the spatial weather data distribution information through a spatial magnetic field distribution model to generate blue magnetic field line spatial distribution information, wherein the blue magnetic field line spatial distribution information has a magnetic field intensity distribution label.
[0026] Further, the spatial weather data distribution information is processed by a spatial magnetic field distribution model to generate blue magnetic field line spatial distribution information. The previous step S20 includes the steps of:
[0027] S21: Interactive Earth Magnetic Field Observatory, collecting Earth magnetic field vector historical record data and space weather historical record data.
[0028] S22: interpolating the earth magnetic field vector historical record data and the space weather historical record data in the preset spatial grid to obtain spatial distribution information of the space weather historical record data and spatial distribution information of the earth magnetic field vector historical record data.
[0029] S23: Based on the spatial distribution information of the space weather historical record data and the spatial distribution information of the earth magnetic field vector historical record data, the space magnetic field distribution model is trained based on a graph neural network.
[0030] Further, based on the spatial distribution information of the space weather historical record data and the spatial distribution information of the earth magnetic field vector historical record data, the spatial magnetic field distribution model is trained based on a graph neural network, and step S23 includes the steps of:
[0031] S231: Based on the preset spatial grid, construct a graph neural network topology, wherein the graph neural network topology is the same as the preset spatial grid.
[0032] S232: Taking the spatial distribution information of the space weather historical record data corresponding one-to-one to the preset spatial grids as input, and taking the spatial distribution information of the earth magnetic field vector historical record data corresponding one-to-one to the preset spatial grids as output supervision information, the graph neural network topology is trained to generate the spatial magnetic field distribution model.
[0033] S24: Processing the space weather data distribution information through the space magnetic field distribution model to generate earth magnetic field vector distribution information.
[0034] S25: Decomposing the earth magnetic field vector distribution information to obtain the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label.
[0035] Specifically, the spatial magnetic field distribution model refers to a model built based on machine learning, which aims to analyze the distribution state of the earth's magnetic field in combination with the distribution information of space weather data. After the training of the spatial magnetic field distribution model is completed, the space weather data distribution information can be processed to generate the earth's magnetic field vector distribution information to characterize the distribution state of the earth's magnetic field. Furthermore, the earth's magnetic field vector distribution information is disassembled to obtain the spatial distribution information of the blue magnetic field lines that characterize the direction of the magnetic field distribution and the magnetic field intensity distribution label that characterizes the intensity of the magnetic field distribution. Through the spatial distribution information of the blue magnetic field lines that characterize the direction of the magnetic field distribution and the magnetic field intensity distribution label that characterizes the intensity of the magnetic field distribution, the three-dimensional distribution model of the earth's magnetic field can be constructed in the next step, which can also be used as the basic data for the simulation of the aurora distribution in the next step.
[0036] The spatial magnetic field distribution model is preferably constructed as follows:
[0037] Step 1: The Earth Magnetic Field Observatory is any interactive data authority magnetic field monitoring organization. The Earth Magnetic Field Vector Historical Record Data refers to the data obtained by the Earth Magnetic Field Observatory when it monitored the magnetic field in the past; the Space Weather Historical Record Data refers to the meteorological information stored by the Earth Magnetic Field Observatory when it monitored the magnetic field in the past and interacted with the meteorological observation station. Preferably, the attributes of the meteorological data are the same as the preset attribute set. Therefore, the Space Weather Historical Record Data is the cause data that leads to the Earth Magnetic Field Vector Historical Record Data, and the Earth Magnetic Field Vector Historical Record Data is the result data that follows the changes in the Space Weather Historical Record Data. The mapping relationship between the two can be analyzed based on machine learning.
[0038] Step 2: In order to make the final result coordinates consistent, the historical record data of the earth's magnetic field vector is interpolated into the preset spatial grid to obtain the spatial distribution information of the space weather historical record data; the space weather historical record data is interpolated into the preset spatial grid to obtain the spatial distribution information of the earth's magnetic field vector historical record data.
[0039] Step 3: When the amount of data meets the required amount for training a large model, the spatial distribution information of the Earth's magnetic field vector historical record data is used as supervision information, and the spatial distribution information of the space weather historical record data is used as input data to train the graph neural network and obtain a spatial magnetic field distribution model.
[0040] Furthermore, the graph neural network uses a neural network to learn a special neural network of graph structured data. The distribution of the earth's magnetic field is a typical graph distribution data, and the input spatially distributed weather data is also graph distribution data, so the applicability graph neural network fits the mapping relationship between the two. Preferably, a graph neural network topology is constructed based on a preset spatial grid, wherein the graph neural network topology is the same as the preset spatial grid, that is, each grid in the preset spatial grid is regarded as a topological node of the graph neural network topology, that is, the distribution environment of the earth's magnetic field is simulated in the graph neural network topology.
[0041] When the graph neural network topology is completed, it is preferred that the mean square loss function is used as the objective function, which is in the following form: MSE represents the mean square loss for each N training, y i,j,0 Represents the jth magnetic field vector supervision value of the i-th training, y i,j represents the predicted value of the j-th magnetic field vector in the i-th training, N represents the fitting period of the loss function, and M represents the number of magnetic field vectors in the i-th training.
[0042] The spatial distribution information of the space weather historical record data and the spatial distribution information of the earth magnetic field vector historical record data are combined into an initial data set, and divided according to a ratio of 8:2. The data with a ratio of 8 is set as a training data set, and the data with a ratio of 2 is set as a verification data set. The spatial distribution information of the space weather historical record data corresponding to the preset spatial grid in the training data set is used as input, and the spatial distribution information of the earth magnetic field vector historical record data corresponding to the preset spatial grid is used as output supervision information to train the graph neural network topology. When the output value of the objective function is less than the convergence threshold, the verification data set is used for verification. When the output value of the objective function is less than the convergence threshold ratio and greater than the set convergence ratio in the preset number of verifications, the model is considered to have converged, and the spatial magnetic field distribution model is output. Otherwise, the model is considered to have not converged, and the training process is returned to repeat the training.
[0043] S30: Configuring aurora observation attributes, wherein the aurora observation attributes at least include a coronal mass ejection position index, a coronal mass ejection mass index, and a coronal mass transport speed index.
[0044] Specifically, coronal mass is the material ejected from the sun's corona, and its main component is plasma composed of electrons and protons. Since the motion state of electrons and protons in space is greatly affected by the initial position, velocity and mass factors, the embodiment of the present application selects the coronal mass ejection position index, coronal mass ejection mass index, and coronal mass transport speed index as aurora observation attributes. In actual applications, users can make custom settings and changes. However, conventional changes are also within the scope of protection of this application.
[0045] S40: Based on the coronal mass ejection position index, the coronal mass ejection mass index, and the coronal mass transfer speed index, aurora observation data is collected, and aurora distribution simulation is performed in combination with the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label to generate aurora spatial distribution information.
[0046] Specifically, since the movement of coronal matter is mainly affected by the Earth's magnetic field when it is close to the Earth's atmosphere, and the motion state of charged particles in the magnetic field can be mechanically simulated, a simplified Earth magnetic field model can be constructed based on the spatial distribution information of the blue magnetic field lines and the magnetic field intensity distribution label determined in the previous article. Then, the motion simulation analysis of the coronal matter in the Earth's magnetic field model can be performed based on the ejection position, ejecta mass and transmission speed, and the motion trajectory of the coronal matter in the Earth's magnetic field can be obtained. According to the corresponding motion trajectory, the spatial distribution information of the aurora can be determined.
[0047] S50: Based on the aurora spatial distribution information, distribute aurora observation lines in a preset area to generate aurora observation line spatial distribution information.
[0048] Specifically, based on the aurora spatial distribution information, the predicted distribution area of the aurora in space can be determined. When the aurora spatial distribution information intersects with a preset area, the corresponding area is set as the aurora observation line spatial distribution information to instruct people in the preset area to observe the aurora.
[0049] S60: Constructing a blue magnetic field line spatial distribution visualization model according to the blue magnetic field line spatial distribution information.
[0050] S70: Constructing a global aurora spatial distribution visualization model based on the aurora spatial distribution information.
[0051] S80: Constructing a visualization model of the spatial distribution of aurora observation lines according to the spatial distribution information of the aurora observation lines.
[0052] Specifically, if Figure 2 As shown in the figure, a visualization model of the spatial distribution of blue magnetic lines of force is constructed based on the spatial distribution information of blue magnetic lines of force. The blue line part in the figure is the distribution state of the magnetic field; based on the spatial distribution information of the aurora, a visualization model of the spatial distribution of global aurora is constructed, that is, the dimensional range that the aurora may cover. Since the specific distribution coordinates of the blue magnetic lines of force and the spatial distribution coordinates of the aurora observation lines have been analyzed and determined, at this time, only rendering based on the coordinate data is needed to determine the spatial distribution visualization model of the blue magnetic lines of force, the global aurora spatial distribution visualization model, and the aurora observation line spatial distribution visualization model.
[0053] Further, based on the coronal mass ejection position index, the coronal mass ejection mass index, and the coronal mass transport speed index, aurora observation data is collected, and aurora distribution simulation is performed in combination with the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label to generate aurora spatial distribution information. Step S40 includes the steps of:
[0054] S41: The aurora observation data includes the position of the coronal mass ejection, the mass of the coronal mass ejection and the coronal mass transport velocity.
[0055] S42: Based on the magnetic field intensity distribution label, identify the earth's influence range to obtain the earth's influence spatial range.
[0056] S43: When the coronal mass does not enter the Earth's influence space range, a space trajectory simulation is performed based on the coronal mass ejection position, the coronal mass ejection mass and the coronal mass transfer speed to generate the predicted coronal mass motion position, the coronal mass residual mass and the coronal mass predicted transfer speed.
[0057] S44: When the coronal mass enters the Earth's influence space, the predicted movement position of the coronal mass, the mass of the coronal mass remnant and the predicted transmission speed of the coronal mass are simulated based on the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label to obtain the aurora spatial distribution information.
[0058] Furthermore, the space operation trajectory simulation is implemented through a space operation trajectory simulation model, wherein the space operation trajectory simulation model is a static simulation model constructed based on the space magnetic field environment.
[0059] Furthermore, the simulation of the trajectory of movement around the earth is implemented through a simulation model of the trajectory of movement around the earth, wherein the simulation model of the trajectory of movement around the earth is a dynamic simulation model that is updated in real time based on the spatial distribution information of the blue magnetic field lines and the magnetic field intensity distribution labels.
[0060] Specifically, there are two stages in the simulation of coronal mass motion: the first stage is the space motion that is not affected by the Earth's magnetic field; the second stage is the motion around the Earth that is affected by the Earth's magnetic field. Therefore, it is necessary to configure the Earth's influence space range and regard all areas outside the Earth's influence space range as the space motion area.
[0061] Preferably, during the first stage of motion simulation, the space trajectory simulation is implemented through a space trajectory simulation model, and the space trajectory simulation model is a static simulation model constructed based on the space magnetic field environment, that is, in the embodiment of the present application, the space magnetic field environment is regarded as unchanged and is a fixed value pre-set by the user. Therefore, during the first stage of motion simulation, it is necessary to perform a force analysis in a preset space magnetic field environment based on the coronal mass ejection position, the mass of the coronal mass ejection and the coronal mass transfer speed, and then perform a motion state simulation to obtain the real-time predicted coronal mass motion position, the mass of the coronal mass residue and the predicted coronal mass transfer speed.
[0062] Preferably, in the second stage of motion simulation, the simulation of the trajectory around the earth is realized by the trajectory simulation model around the earth, which is a dynamic simulation model based on the spatial distribution information of the blue magnetic field lines and the magnetic field intensity distribution label, which is updated in real time, that is, the magnetic field around the earth needs to be adjusted in real time according to the earth's magnetic field environment obtained by each prediction. Therefore, in the second stage of motion simulation, when the coronal mass enters the earth's influence space range, the coronal mass is mechanically analyzed according to the earth's magnetic field environment, and then the motion state simulation is performed to obtain the motion trajectory of the coronal mass, thereby generating the aurora spatial distribution information.
[0063] Further, based on the magnetic field intensity distribution label, the earth's influence range is identified to obtain the earth's influence space range. Step S42 includes the following steps:
[0064] S421: Collecting historical monitoring data of the earth's magnetic field influence range with the magnetic field intensity distribution label as a constraint, wherein the historical monitoring data of the earth's magnetic field influence range includes multiple groups of historical monitoring data of the earth's magnetic field influence range in multiple directions.
[0065] S422: traverse the multiple groups of historical monitoring data of the earth's magnetic field influence range to perform centralized trend analysis and obtain multiple earth influence sub-range identification results.
[0066] S423: Constructing the earth's influence spatial range based on the earth according to the multiple directions and the multiple earth's influence sub-range identification results.
[0067] Specifically, due to the changes in the intensity and direction of the earth's magnetic field, the range that the earth's magnetic field can affect is also different. Preferably, the determination method is as follows: with the magnetic field intensity distribution label as a constraint, the historical monitoring data of the earth's magnetic field influence range of the magnetic field intensity distribution label in the same historical process is collected. Since the change of the earth's magnetic field presents a certain regularity, the magnetic field influence range of the earth in each direction with similar magnetic field distribution can be collected from the historical state, that is, based on the maximum influence distance of the vertical surface in a certain direction, the collected data is stored as the historical monitoring data of the earth's magnetic field influence range. Extract multiple groups of historical monitoring data of the earth's magnetic field influence range in multiple directions of the historical monitoring data of the earth's magnetic field influence range. For any group of historical monitoring data of the earth's magnetic field influence range, cluster analysis is performed according to the threshold of the earth's magnetic field influence range preset by the user, and then the clusters with the number within the class less than the threshold of the number within the class are deleted, and the remaining clusters are averaged to obtain the identification result of the earth's magnetic field influence range in the corresponding direction. Traversing all the multiple groups of historical monitoring data of the earth's magnetic field influence range in multiple directions, multiple earth influence sub-range identification results can be obtained, and then based on multiple directions and the multiple earth influence sub-range identification results, the earth's influence space range is constructed based on the earth. It can be seen that the spatial range of the Earth's influence may be an irregular field. The spatial range of the Earth's influence determined by statistical analysis of a large amount of historical data is relatively accurate, providing a data basis for the accurate visualization of the spatial distribution of aurora.
[0068] In summary, the three-dimensional visualization method and system of space weather data provided by the embodiments of the present application have the following technical effects:
[0069] 1. Due to the adoption of a spatial magnetic field distribution model based on machine learning, the distribution information of space weather data is processed to generate the spatial distribution information of blue magnetic lines. Then, aurora observation data is collected, and aurora distribution simulation is performed based on the spatial distribution information of blue magnetic lines to generate the spatial distribution information of aurora observation lines. Finally, a technical solution for a visualization model of the spatial distribution of blue magnetic lines and aurora observation lines is constructed. The model is built through machine learning and combined with motion simulation analysis to achieve efficient and automated analysis of aurora distribution data and magnetic field distribution data. In addition, due to the strong objectivity of the large model combined with simulation analysis, the accuracy is improved, so the technical effect of optimizing processing efficiency and processing accuracy is achieved.
[0070] Embodiment 2
[0071] Based on the same inventive concept as the three-dimensional visualization method of space weather data in the aforementioned embodiment, Figure 3 As shown, the embodiment of the present application provides a three-dimensional visualization system for space weather data, including:
[0072] The prediction request receiving module 100 is used to receive an aurora observation line prediction request, interact with the meteorological observation station, receive space weather data, interpolate the space weather data into a preset space grid, and obtain space weather data distribution information.
[0073] The spatial magnetic field distribution module 200 is used to process the spatial weather data distribution information through a spatial magnetic field distribution model to generate blue magnetic field line spatial distribution information, wherein the blue magnetic field line spatial distribution information has a magnetic field intensity distribution label.
[0074] The aurora data configuration module 300 is used to configure aurora observation attributes, wherein the aurora observation attributes at least include a coronal mass ejection position index, a coronal mass ejection mass index, and a coronal mass transport speed index.
[0075] The aurora distribution simulation module 400 is used to collect aurora observation data based on the coronal mass ejection position index, the coronal mass ejection mass index, and the coronal mass transfer speed index, and to perform aurora distribution simulation in combination with the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label to generate aurora spatial distribution information.
[0076] The aurora observation prediction module 500 is used to distribute aurora observation lines in a preset area based on the aurora spatial distribution information to generate aurora observation line spatial distribution information.
[0077] The magnetic field visualization module 600 is used to construct a blue magnetic field line spatial distribution visualization model according to the blue magnetic field line spatial distribution information.
[0078] The aurora visualization module 700 is used to construct a global aurora spatial distribution visualization model based on the aurora spatial distribution information.
[0079] The aurora observation line visualization module 800 is used to construct an aurora observation line spatial distribution visualization model according to the aurora observation line spatial distribution information.
[0080] Further, the prediction request receiving module 100 performs the steps including: configuring space weather data attributes, wherein the space weather data attributes at least include a solar wind speed index, a solar wind density index, a solar wind temperature index, an ionosphere electron density index, an ionosphere electron temperature index, an ionosphere F2 layer critical frequency index, a magnetosphere magnetic field strength index, a magnetosphere magnetic field direction index, a magnetosphere plasma density index, and a magnetosphere plasma temperature index. The space weather data is collected according to the solar wind speed index, the solar wind density index, the solar wind temperature index, the ionosphere electron density index, the ionosphere electron temperature index, the ionosphere F2 layer critical frequency index, the magnetosphere magnetic field strength index, the magnetosphere magnetic field direction index, the magnetosphere plasma density index, and the magnetosphere plasma temperature index.
[0081] Furthermore, the execution steps of the spatial magnetic field distribution module 200 include: interacting with the earth magnetic field observation station to collect earth magnetic field vector historical record data and space weather historical record data; interpolating the earth magnetic field vector historical record data and the space weather historical record data into the preset spatial grid to obtain spatial distribution information of space weather historical record data and spatial distribution information of earth magnetic field vector historical record data; based on the spatial distribution information of space weather historical record data and the spatial distribution information of earth magnetic field vector historical record data, based on the graph neural network, training the spatial magnetic field distribution model; processing the space weather data distribution information through the spatial magnetic field distribution model to generate earth magnetic field vector distribution information; disassembling the earth magnetic field vector distribution information to obtain the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label.
[0082] Furthermore, the spatial magnetic field distribution module 200 executes the steps including: constructing a graph neural network topology based on the preset spatial grid, wherein the graph neural network topology is the same as the preset spatial grid; taking the spatial distribution information of the space weather historical record data corresponding one-to-one to the preset spatial grid as input, and taking the spatial distribution information of the earth magnetic field vector historical record data corresponding one-to-one to the preset spatial grid as output supervision information, training the graph neural network topology to generate the spatial magnetic field distribution model.
[0083] Furthermore, the aurora distribution simulation module 400 executes the steps including: the aurora observation data includes the coronal mass ejection position, the coronal mass ejection mass and the coronal mass transfer speed; based on the magnetic field intensity distribution label, the earth's influence range is marked to obtain the earth's influence space range; when the coronal mass does not enter the earth's influence space range, based on the coronal mass ejection position, the coronal mass ejection mass and the coronal mass transfer speed, the space trajectory simulation is performed to generate the coronal mass predicted motion position, the coronal mass residual mass and the coronal mass predicted transmission speed; when the coronal mass enters the earth's influence space range, the predicted motion position of the coronal mass, the coronal mass residual mass and the coronal mass predicted transmission speed are simulated around the earth based on the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label to obtain the aurora spatial distribution information.
[0084] Furthermore, the aurora distribution simulation module 400 executes the steps including: collecting historical monitoring data of the earth's magnetic field influence range based on the magnetic field intensity distribution label as a constraint, wherein the historical monitoring data of the earth's magnetic field influence range includes multiple groups of historical monitoring data of the earth's magnetic field influence range in multiple directions; traversing the multiple groups of historical monitoring data of the earth's magnetic field influence range to perform central trend analysis, and obtain multiple earth influence sub-range identification results; and constructing the earth's influence spatial range based on the earth according to the multiple directions and the multiple earth influence sub-range identification results.
[0085] Furthermore, the execution steps of the aurora distribution simulation module 400 include: space trajectory simulation is implemented through a space trajectory simulation model, wherein the space trajectory simulation model is a static simulation model constructed based on the space magnetic field environment; the simulation of the trajectory around the earth is implemented through a trajectory simulation model around the earth, wherein the trajectory simulation model around the earth is a dynamic simulation model that is updated in real time based on the spatial distribution information of the blue magnetic field lines and the magnetic field intensity distribution label.
[0086] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.
[0087] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the present application and its equivalent technologies, the present application intends to include these modifications and variations.
Claims
1. A 3D visualization method for space weather data, It is characterized in that include: When receiving a visualization monitoring request for the magnetosphere and aurora, the interactive meteorological observation station receives space weather data, interpolates the space weather data into a preset space grid, and obtains space weather data distribution information; The spatial weather data distribution information is processed by a spatial magnetic field distribution model to generate blue magnetic field line spatial distribution information, wherein the blue magnetic field line spatial distribution information has a magnetic field intensity distribution label; Configuring aurora observation attributes, wherein the aurora observation attributes at least include a coronal mass ejection position index, a coronal mass ejection mass index, and a coronal mass transport velocity index; Based on the coronal mass ejection position index, the coronal mass ejection mass index, and the coronal mass transport speed index, aurora observation data is collected, and aurora distribution simulation is performed in combination with the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label to generate aurora spatial distribution information; Based on the aurora spatial distribution information, aurora observation line distribution is performed on a preset area to generate aurora observation line spatial distribution information; Constructing a visualization model of the spatial distribution of blue magnetic lines of force according to the spatial distribution information of the blue magnetic lines of force; According to the aurora spatial distribution information, a global aurora spatial distribution visualization model is constructed; According to the spatial distribution information of the aurora observation lines, a visualization model of the spatial distribution of the aurora observation lines is constructed.
2. The method according to claim 1, It is characterized in that Receive space weather data, including: Configuring space weather data attributes, wherein the space weather data attributes at least include a solar wind speed index, a solar wind density index, a solar wind temperature index, an ionosphere electron density index, an ionosphere electron temperature index, an ionosphere F2 layer critical frequency index, a magnetosphere magnetic field strength index, a magnetosphere magnetic field direction index, a magnetosphere plasma density index, and a magnetosphere plasma temperature index; The space weather data is collected according to the solar wind speed index, the solar wind density index, the solar wind temperature index, the ionosphere electron density index, the ionosphere electron temperature index, the ionosphere F2 layer critical frequency index, the magnetosphere magnetic field strength index, the magnetosphere magnetic field direction index, the magnetosphere plasma density index, and the magnetosphere plasma temperature index.
3. The method according to claim 1, It is characterized in that The spatial weather data distribution information is processed by a spatial magnetic field distribution model to generate blue magnetic field line spatial distribution information, including: Interactive Earth Magnetic Field Observatory, collecting historical record data of Earth magnetic field vector and historical record data of space weather; Interpolating the earth magnetic field vector historical record data and the space weather historical record data in the preset spatial grid to obtain spatial distribution information of the space weather historical record data and spatial distribution information of the earth magnetic field vector historical record data; Based on the spatial distribution information of the space weather historical record data and the spatial distribution information of the earth magnetic field vector historical record data, the spatial magnetic field distribution model is trained based on a graph neural network; Processing the space weather data distribution information by using the space magnetic field distribution model to generate earth magnetic field vector distribution information; The earth's magnetic field vector distribution information is disassembled to obtain the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label.
4. The method according to claim 3, It is characterized in that Based on the spatial distribution information of the space weather historical record data and the spatial distribution information of the earth magnetic field vector historical record data, the spatial magnetic field distribution model is trained based on a graph neural network, including: Based on the preset spatial grid, construct a graph neural network topology, wherein the graph neural network topology is the same as the preset spatial grid; Taking the spatial distribution information of the space weather historical record data corresponding one-to-one to the preset spatial grids as input, and taking the spatial distribution information of the earth magnetic field vector historical record data corresponding one-to-one to the preset spatial grids as output supervision information, the graph neural network topology is trained to generate the spatial magnetic field distribution model.
5. The method according to claim 1, It is characterized in that Based on the coronal mass ejection position index, the coronal mass ejection mass index, and the coronal mass transport speed index, aurora observation data is collected, and aurora distribution simulation is performed in combination with the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label to generate aurora spatial distribution information, including: The aurora observation data include the coronal mass ejection position, the coronal mass ejection mass and the coronal mass transport velocity; Based on the magnetic field intensity distribution label, the earth's influence range is marked to obtain the earth's influence spatial range; When the coronal mass does not enter the Earth's influence space range, a space trajectory simulation is performed based on the coronal mass ejection position, the coronal mass ejection mass and the coronal mass transmission speed to generate a predicted coronal mass motion position, a coronal mass residual mass and a predicted coronal mass transmission speed; When the coronal mass enters the Earth's influence space, the predicted movement position of the coronal mass, the mass of the coronal mass remnant and the predicted transmission speed of the coronal mass are simulated based on the blue magnetic field line spatial distribution information and the magnetic field intensity distribution label to obtain the aurora spatial distribution information.
6. The method according to claim 5, It is characterized in that Based on the magnetic field intensity distribution label, the earth's influence range is marked to obtain the earth's influence space range, including: Taking the magnetic field intensity distribution label as a constraint, collecting historical monitoring data of the earth's magnetic field influence range, wherein the historical monitoring data of the earth's magnetic field influence range includes multiple groups of historical monitoring data of the earth's magnetic field influence range in multiple directions; Traversing the multiple groups of historical monitoring data of the earth's magnetic field influence range to perform a centralized trend analysis, and obtaining multiple earth influence sub-range identification results; According to the multiple directions and the multiple earth influence sub-range identification results, the earth influence spatial range is constructed based on the earth.
7. The method according to claim 5, It is characterized in that include: The space operation trajectory simulation is implemented by a space operation trajectory simulation model, wherein the space operation trajectory simulation model is a static simulation model constructed based on the space magnetic field environment; The simulation of the trajectory of movement around the earth is realized by a simulation model of the trajectory of movement around the earth, wherein the simulation model of the trajectory of movement around the earth is a dynamic simulation model that is updated in real time based on the spatial distribution information of the blue magnetic field lines and the magnetic field intensity distribution labels.
8. A 3D visualization system for space weather data, It is characterized in that include: A prediction request receiving module is used to, upon receiving a visualization monitoring request of the magnetosphere and aurora, interact with a meteorological observation station, receive space weather data, interpolate the space weather data into a preset space grid, and obtain space weather data distribution information; A spatial magnetic field distribution module, used for processing the spatial weather data distribution information through a spatial magnetic field distribution model to generate blue magnetic field line spatial distribution information, wherein the blue magnetic field line spatial distribution information has a magnetic field intensity distribution label; An aurora data configuration module, used to configure aurora observation attributes, wherein the aurora observation attributes at least include a coronal mass ejection position index, a coronal mass ejection mass index, and a coronal mass transport velocity index; an aurora distribution simulation module, for collecting aurora observation data based on the coronal mass ejection position index, the coronal mass ejection mass index, and the coronal mass transport speed index, performing aurora distribution simulation, and generating aurora spatial distribution information; An aurora observation prediction module, used to distribute aurora observation lines in a preset area based on the aurora spatial distribution information, and generate aurora observation line spatial distribution information; A magnetic field visualization module, used for constructing a blue magnetic field line spatial distribution visualization model according to the blue magnetic field line spatial distribution information; An aurora visualization module is used to construct a global aurora spatial distribution visualization model based on the aurora spatial distribution information; The aurora observation line visualization module is used to construct an aurora observation line spatial distribution visualization model based on the aurora observation line spatial distribution information.
