Dst index calculation method and system fusing neutral atom imaging data and machine learning

Abstract

The invention discloses a Dst index calculation method and system fusing neutral atom imaging data and machine learning, and the method is realized based on a satellite-borne high-energy neutral atom imager, and comprises the steps: receiving collected neutral atom image data of different energy segments, and carrying out the preprocessing through combining satellite position data; inputting the preprocessed neutral atom image data and satellite position data into a pre-established and trained index prediction model, and outputting a Dst index at the current moment; the index prediction model is combined with a residual network and a multi-layer perceptron, and comprises an image feature extraction module used for extracting image features and capturing distribution information related to a Dst index in a neutral atom image; the feature fusion module is used for performing multi-modal fusion on the image features and the satellite position data; and the regression prediction module is used for performing nonlinear regression on the fused features and outputting a Dst index at the current moment.

Description

Technical Field

[0001] The present invention belongs to the field of space physics and geomagnetic index calculation technology, and in particular relates to a Dst index calculation method and system integrating neutral atom imaging data and machine learning. Background Art

[0002] Geomagnetic storms are the direct product of the interaction between the solar wind and the Earth's magnetosphere, and can cause global magnetic field disturbances. They are mainly manifested in dramatic changes in the strength of the Earth's magnetic field, which have a significant impact on human modern technological systems, such as communications, navigation, satellite operations, and power transmission networks. In order to measure the intensity and dynamic evolution of geomagnetic storms, scientists have proposed a variety of geomagnetic indices, among which the Dst index is one of the most important standards. The Dst index is observed by ground magnetometers in low-latitude regions, reflecting the global magnetic field changes caused by the Earth's ring currents, and can better characterize the temporal evolution of the intensity of geomagnetic storms.

[0003] Although the traditional Dst index calculation method has met the needs of scientific research and space weather monitoring to a certain extent, it also has some significant limitations: (1) Limited spatial coverage: The distribution of ground-based magnetometers is limited by geographical restrictions, resulting in limitations in spatial coverage. (2) Low temporal resolution: Ground-based magnetometers usually record data once an hour, which is not enough to cope with rapidly developing space weather events. (3) Insufficient capture of the overall dynamics of the magnetosphere: Ground-based observations can only provide local information on the geomagnetic field, and it is difficult to fully reflect the ring current structure in the magnetosphere and its dynamic evolution.

[0004] In order to overcome the above limitations, neutral atom imaging (ENA) technology has become an important tool for studying ring currents and geomagnetic storms. ENA imaging can remotely sense the distribution and intensity of ring currents from a global perspective by detecting neutral atoms generated by charge exchange between high-energy ions in the ring current and neutral gases. This technology avoids the spatial limitations of ground-based observations and provides a new perspective for the study of magnetospheric physics. Previous studies have shown that there is a strong correlation between the ENA flux and the Dst index, especially during the main phase and recovery phase of the magnetic storm. However, existing methods mostly rely on theoretical models and empirical formulas to calculate this correlation, which makes it difficult to capture complex nonlinear relationships. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the prior art and propose a Dst index calculation method and system that integrates neutral atom imaging data and machine learning.

[0006] In view of this, the present invention proposes a Dst index calculation method that integrates neutral atom imaging data and machine learning, which is implemented based on a satellite-borne high-energy neutral atom imager, including:

[0007] Receive the collected neutral atom image data of six energy bands and pre-process them in combination with the satellite position data;

[0008] Input the preprocessed neutral atom image data and satellite position data into the pre-established and trained index prediction model, and output the Dst index at the current moment;

[0009] The index prediction model combines a residual network and a multi-layer perceptron, and includes: an image feature extraction module, a feature fusion module, and a regression prediction module; wherein,

[0010] The image feature extraction module is used to extract image features and capture distribution information related to the Dst index in the neutral atom image;

[0011] The feature fusion module is used to perform multimodal fusion of image features and satellite position data;

[0012] The regression prediction module is used to perform nonlinear regression on the fused features and output the Dst index at the current moment.

[0013] Preferably, the six energy bands include: 10keV, 10-16keV, 16-27keV, 27-39keV, 39-50keV and 50-60keV, including neutral particles of all energies.

[0014] Preferably, the satellite position data includes: the longitude, latitude and distance from the center of the Earth of the satellite.

[0015] Preferably, the preprocessing includes: noise filtering and coordinate conversion and encoding; wherein,

[0016] Noise filtering: used to remove data from neutral atom image data whose flux does not meet the conditions;

[0017] Coordinate conversion and encoding: used to convert satellite positions from rectangular coordinates to spherical coordinates, and use sine-cosine encoding for magnetic latitude and longitude.

[0018] Preferably, the image feature extraction module adopts a ResNet34 network and outputs a 1×512 feature vector.

[0019] Preferably, the processing process of the feature fusion module includes:

[0020] The 6×20×20 tensor of image features and the 1×5 vector of satellite position data are concatenated to obtain a 1×517 fused feature.

[0021] Preferably, the regression prediction module uses an MLP model to perform nonlinear regression on the fusion features and outputs the Dst index at the current moment.

[0022] Preferably, the method further comprises a step of training an exponential prediction model, comprising:

[0023] Collect neutral atom image data of six energy bands in a specified year, the corresponding satellite position data and the Dst index of the corresponding time period;

[0024] The neutral atom image data is preprocessed in combination with the satellite position data; the Dst index of each hour is marked on the neutral atom image data of the corresponding time period to achieve time alignment;

[0025] The cross-validation method is used to divide the data into training set and test set. The mean square error is used as the loss function. The Adam optimization algorithm is used for training. The learning rate is dynamically adjusted to accelerate convergence until the training requirements are met. The trained exponential prediction model is obtained, and the root mean square error and correlation coefficient are used to evaluate the trained exponential prediction model.

[0026] Preferably, the method further includes: combining the Dst index at the current moment with other space weather observation indicators to provide multimodal space weather monitoring and early warning services; the other space weather observation indicators include: solar wind parameters and SYM-H index.

[0027] On the other hand, the present invention proposes a Dst index calculation system that integrates neutral atom imaging data and machine learning, which is implemented based on a satellite-borne high-energy neutral atom imager and includes:

[0028] A receiving preprocessing module is used to receive the collected neutral atom image data of six energy bands and perform preprocessing in combination with the satellite position data;

[0029] The prediction output module is used to input the pre-processed neutral atom image data and satellite position data into the pre-established and trained index prediction model, and output the Dst index at the current moment;

[0030] The index prediction model combines a residual network and a multi-layer perceptron, and includes: an image feature extraction module, a feature fusion module, and a regression prediction module; wherein,

[0031] The image feature extraction module is used to extract image features and capture distribution information related to the Dst index in the neutral atom image;

[0032] The feature fusion module is used to perform multimodal fusion of image features and satellite position data;

[0033] The regression prediction module is used to perform nonlinear regression on the fused features and output the Dst index at the current moment.

[0034] Compared with the prior art, the advantages of the present invention are:

[0035] This invention innovatively combines neutral atom imaging technology with deep learning methods, and realizes the confirmation of Dst index based on ENA data for the first time, breaking through the spatial coverage and temporal resolution limitations of traditional geomagnetic index calculations. By designing a model that combines residual network (ResNet) and multi-layer perceptron (MLP), the nonlinear relationship between Dst index and ring current is accurately captured by integrating ENA images and satellite position information, significantly improving the calculation accuracy and real-time performance. The model achieved excellent performance with a correlation coefficient of 0.87 and a root mean square error of 18.96nT on the test set, providing a new solution with a global perspective and high resolution for geomagnetic storm monitoring and space weather warning, and has broad scientific research and practical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a flow chart of a Dst index calculation method of the present invention that integrates neutral atom imaging data and machine learning;

[0037] Figure 2 It is the comparison result between the Dst index predicted by the method of the present invention and the actual value. DETAILED DESCRIPTION

[0038] In recent years, with the rapid development of artificial intelligence and machine learning technologies, their applications in the field of space weather have gradually increased. For example, machine learning models have been successfully applied to modeling the relationship between solar wind parameters and the Dst index, and have made significant progress. However, it is the first time that machine learning technology has been introduced into the correlation analysis of neutral atom imaging data and the Dst index. Neutral atom imaging data has the characteristics of high dimension and multimodality, which brings challenges to traditional analysis methods, while deep learning technology provides the possibility of processing such complex data.

[0039] The present invention proposes a new Dst index confirmation method by combining high-energy neutral atom imaging data and machine learning technology. This method uses deep learning models (such as multi-layer perceptrons and residual networks) to extract features from neutral atom images, and combines relevant information about satellite positions and magnetic field disturbances to construct an accurate and efficient Dst index calculation model. This method breaks through the spatial and temporal limitations of traditional Dst index calculations, provides a new technical means for global geomagnetic storm monitoring and research, and significantly improves the accuracy and resolution of space weather forecasts.

[0040] This paper proposes a new method based on neutral atom imaging data, which uses machine learning technology to model the relationship between high-energy neutral atom flux and Dst index, and realizes accurate confirmation and prediction of Dst index. This method can greatly improve the accuracy and efficiency of geomagnetic storm monitoring and space weather forecasting.

[0041] 1. Data Collection and Processing

[0042] ·Use the High Energy Neutral Atom Imager (HENA) of space exploration satellites (such as the IMAGE satellite) to collect neutral atom observation data from 2000 to 2005. The data includes neutral atom images in six energy bands, satellite position data (longitude, latitude and distance from the center of the earth), and the Dst index at the corresponding time. The six energy bands are for the IMAGE satellite data used in the calculation process. According to the instrument design, six energy bands of neutral atom data are provided, including <10keV, 10-16keV, 16-27keV, 27-39keV, 39-50keV, 50-60keV. The main purpose is to include all detected particles. If different satellite data are applied, the energy division will be different according to the instrument design.

[0043] Preprocess the observation data, including denoising, coordinate transformation and data alignment. Convert the satellite position into spherical coordinates and perform sine-cosine encoding on the angle information to enhance the model's ability to recognize position features.

[0044] 2. Machine Learning Model Construction

[0045] Build a deep learning model combining a multi-layer perceptron (MLP) and a residual network (ResNet).

[0046] The model input includes neutral atom image data of six energy segments (each segment is a 20×20 pixel matrix) and satellite position features; the image features are extracted through ResNet, and the position features are fused with the image features in the fully connected layer.

[0047] The model output is the Dst index at the current moment.

[0048] 3. Model training and validation

[0049] Use cross-validation method to divide the data into training set and test set to ensure that the model has good generalization ability.

[0050] The mean square error (MSE) is used as the loss function, and the correlation coefficient (R) and root mean square error (RMSE) are used as performance evaluation indicators.

[0051] The RMSE of the optimized model on the test set reached 18.96nT, and the correlation coefficient was 0.87, indicating that it can accurately predict the Dst index.

[0052] 4. Model application and optimization

[0053] The method of the present invention can process neutral atom imaging data in real time for Dst index confirmation during space weather events (such as geomagnetic storms).

[0054] It can be further extended to the calculation of geomagnetic indices with higher temporal resolution (such as the SYM-H index) to improve the space weather forecasting capability.

[0055] The technical solution of the present invention is described in detail below with reference to the accompanying drawings and embodiments.

[0056] Example 1

[0057] like Figure 1 As shown, Embodiment 1 of the present invention proposes a Dst index calculation method integrating neutral atom imaging data and machine learning, comprising the following steps:

[0058] 1 Data collection and preprocessing

[0059] 1.1 Data Collection

[0060] Using the High Energy Neutral Atom Imager (HENA) instrument on board satellites such as the IMAGE satellite, which collected observations from 2000 to 2005.

[0061] The collection content includes:

[0062] ENA image data of six energy bands (resolution of each image is 20×20 pixels);

[0063] Satellite position data (magnetic latitude, longitude and distance from the center of the Earth);

[0064] The Dst index for the corresponding time period is used as a label for supervised learning of the model.

[0065] 1.2 Data Preprocessing

[0066] Noise filtering: Eliminate data with abnormally high or low neutral atom flux and set filtering conditions (such as total flux > 40, distance from the center of the earth > 3 earth radii).

[0067] Coordinate transformation and encoding: The satellite positions are transformed from rectangular coordinates to spherical coordinates, and sine-cosine encoding is used for magnetic latitude and longitude to enhance the model's ability to handle periodic data.

[0068] Time alignment: Annotate the hourly Dst index to the ENA data of the corresponding time period to ensure the consistency of input and output data.

[0069] 2 Model design and training

[0070] 2.1 Model Architecture

[0071] The present invention designs a deep learning model combining residual network (ResNet) and multi-layer perceptron (MLP), which specifically includes the following modules:

[0072] Image feature extraction module

[0073] Input: ENA images of six energy bands (stacked into a 6×20×20 tensor).

[0074] The ResNet34 network is used to extract features from the ENA image and output a feature vector of size 1×512 to capture the distribution information related to the Dst index in the neutral atom image.

[0075] Feature fusion module

[0076] The image features extracted by ResNet and the satellite position information (1×5 vector) are concatenated into a 1×517 input feature vector for multimodal data fusion.

[0077] Regression prediction module

[0078] Use the MLP model to perform nonlinear regression on the fused features and output the Dst index at the current moment.

[0079] 2.2 Model Training

[0080] Using cross-validation, the data was divided into a training set (80%) and a test set (20%),

[0081] And perform five-fold cross validation on the training set.

[0082] The mean square error (MSE) is used as the loss function, the Adam optimization algorithm is used for training, and the learning rate is dynamically adjusted to accelerate convergence.

[0083] Model performance was evaluated by root mean square error (RMSE) and correlation coefficient (R).

[0084] 3 Model validation and performance evaluation

[0085] 3.1 Validation set test

[0086] The model achieved good performance on the test set, with a correlation coefficient (R) of 0.87 and a root mean square error (RMSE) of 18.96nT.

[0087] The results show that the model can accurately capture the changing trend of the Dst index, especially during magnetic storms with large negative Dst values.

[0088] 4 Real-time processing and application

[0089] 4.1 Real-time data processing

[0090] Deploy the model to the ground data center, receive the ENA data sent by the satellite in real time, input it into the model after preprocessing, and quickly output the Dst index estimation value.

[0091] 4.2 System Integration

[0092] Combine the output Dst index with other space weather observation indicators (such as solar wind parameters and SYM-H index) to provide multi-modal space weather monitoring and early warning services.

[0093] Example 2

[0094] Embodiment 2 of the present invention proposes a Dst index calculation system that integrates neutral atom imaging data and machine learning, which is implemented based on a satellite-borne high-energy neutral atom imager and adopts the method of embodiment 1. The system includes:

[0095] A receiving preprocessing module is used to receive the collected neutral atom image data of six energy bands and perform preprocessing in combination with the satellite position data;

[0096] The prediction output module is used to input the pre-processed neutral atom image data and satellite position data into the pre-established and trained index prediction model, and output the Dst index at the current moment;

[0097] The index prediction model combines a residual network and a multi-layer perceptron, and includes: an image feature extraction module, a feature fusion module, and a regression prediction module; wherein,

[0098] The image feature extraction module is used to extract image features and capture distribution information related to the Dst index in the neutral atom image;

[0099] The feature fusion module is used to perform multimodal fusion of image features and satellite position data;

[0100] The regression prediction module is used to perform nonlinear regression on the fused features and output the Dst index at the current moment.

[0101] like Figure 2 Shown is a comparison result between the Dst index predicted by the method of the present invention and the actual value.

[0102] This paper proposes a new method based on neutral atom imaging data, which uses machine learning technology to model the relationship between high-energy neutral atom flux and Dst index, and realizes accurate confirmation and prediction of Dst index. This method can greatly improve the accuracy and efficiency of geomagnetic storm monitoring and space weather forecasting.

[0103] Based on neutral atom imaging data, the present invention effectively realizes the estimation and confirmation of the Dst index through a deep learning model, providing a new technical means for geomagnetic storm monitoring and space weather forecasting.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention is described in detail with reference to the embodiments, it should be understood by those skilled in the art that any modification or equivalent replacement of the technical solutions of the present invention does not depart from the spirit and scope of the technical solutions of the present invention and should be included in the scope of the claims of the present invention.

Claims

1. A Dst index calculation method that integrates neutral atom imaging data and machine learning, based on a satellite-borne high-energy neutral atom imager, includes: Receive the collected neutral atom image data of six energy bands and perform pre-processing in combination with the satellite position data; Input the preprocessed neutral atom image data and satellite position data into the pre-established and trained index prediction model, and output the Dst index at the current moment; The index prediction model combines a residual network and a multi-layer perceptron, and includes: an image feature extraction module, a feature fusion module, and a regression prediction module; wherein, The image feature extraction module is used to extract image features and capture distribution information related to the Dst index in the neutral atom image; The feature fusion module is used to perform multimodal fusion of image features and satellite position data; The regression prediction module is used to perform nonlinear regression on the fused features and output the Dst index at the current moment.

2. The Dst index calculation method integrating neutral atom imaging data and machine learning according to claim 1, characterized in that: The six energy bands include: 10keV, 10-16keV, 16-27keV, 27-39keV, 39-50keV and 50-60keV, including neutral particles of all energies.

3. The Dst index calculation method integrating neutral atom imaging data and machine learning according to claim 1, characterized in that: The satellite position data includes: the longitude, latitude and distance from the center of the earth of the satellite.

4. The Dst index calculation method integrating neutral atom imaging data and machine learning according to claim 2, characterized in that: The preprocessing includes: noise filtering and coordinate conversion and encoding; wherein, Noise filtering: used to remove data from neutral atom image data whose flux does not meet the conditions; Coordinate conversion and encoding: used to convert satellite positions from rectangular coordinates to spherical coordinates, and use sine-cosine encoding for magnetic latitude and longitude.

5. The Dst index calculation method integrating neutral atom imaging data and machine learning according to claim 1, characterized in that: The image feature extraction module uses a ResNet34 network and outputs a 1×512 feature vector.

6. The Dst index calculation method integrating neutral atom imaging data and machine learning according to claim 1, characterized in that: The processing process of the feature fusion module includes: The 6×20×20 tensor of image features and the 1×5 vector of satellite position data are concatenated to obtain a 1×517 fused feature.

7. The Dst index calculation method integrating neutral atom imaging data and machine learning according to claim 1, characterized in that: The regression prediction module uses the MLP model to perform nonlinear regression on the fusion features and outputs the Dst index at the current moment.

8. The Dst index calculation method integrating neutral atom imaging data and machine learning according to claim 1, characterized in that: The method also includes a step of training an exponential prediction model, including: Collect neutral atom image data of six energy bands in a specified year, the corresponding satellite position data and the Dst index of the corresponding time period; The neutral atom image data is preprocessed in combination with the satellite position data; the Dst index of each hour is marked on the neutral atom image data of the corresponding time period to achieve time alignment; The cross-validation method is used to divide the data into training set and test set. The mean square error is used as the loss function. The Adam optimization algorithm is used for training. The learning rate is dynamically adjusted to accelerate convergence until the training requirements are met. The trained exponential prediction model is obtained, and the root mean square error and correlation coefficient are used to evaluate the trained exponential prediction model.

9. The Dst index calculation method integrating neutral atom imaging data and machine learning according to claim 1, characterized in that: The method also includes: combining the Dst index at the current moment with other space weather observation indicators to provide multi-modal space weather monitoring and early warning services; the other space weather observation indicators include: solar wind parameters and SYM-H index.

10. A Dst index calculation system integrating neutral atom imaging data and machine learning, based on a satellite-borne high-energy neutral atom imager, comprising: A receiving preprocessing module is used to receive the collected neutral atom image data of six energy bands and perform preprocessing in combination with the satellite position data; and The prediction output module is used to input the pre-processed neutral atom image data and satellite position data into the pre-established and trained index prediction model, and output the Dst index at the current moment; The index prediction model combines a residual network and a multi-layer perceptron, and includes: an image feature extraction module, a feature fusion module, and a regression prediction module; wherein, The image feature extraction module is used to extract image features and capture distribution information related to the Dst index in the neutral atom image; The feature fusion module is used to perform multimodal fusion of image features and satellite position data; The regression prediction module is used to perform nonlinear regression on the fused features and output the Dst index at the current moment.

Images