Mammox magnetic reconnection event detection method and system based on deep learning algorithm

Abstract

The invention belongs to the application research of a machine learning technology in the field of space physics, and particularly relates to a wooden star magnetic reconnection event detection method and system based on a deep learning algorithm, and the method comprises the steps: obtaining the magnetic field observation data of a wooden star based on a time period, and carrying out the preprocessing; inputting the preprocessed data into a pre-established and trained magnetic reconnection event detection model, and outputting a detection result of whether a star magnetic reconnection event is included in a specific time period; the magnetic reconnection event detection model adopts a 1DResNet residual network, and is used for mining magnetic field observation data, realizing a semantic reasoning process from a bottom layer to a high layer, and identifying a region block containing star magnetic reconnection of each region block in time sequence magnetic field data, thereby realizing the detection of a magnetic reconnection event. According to the method, an end-to-end mode is utilized, and the method is suitable for automatic analysis and processing of a large amount of wood star magnetic field data.

Description

Technical Field

[0001] The present invention relates to the application research of machine learning technology in the field of space physics, and specifically to a method and system for detecting Jupiter magnetic reconnection events based on a deep learning algorithm. Background Art

[0002] Magnetic reconnection is a physical process in which magnetic field energy is rapidly converted into plasma kinetic energy. It often occurs in planetary space and is generally believed to be closely related to particle acceleration and planetary magnetic storms. In satellite observations of the Earth's magnetosphere, a wealth of magnetic reconnection events have been generated and recorded. With the implementation of various deep space planetary exploration satellite programs, more and more planetary magnetosphere observation data are being accumulated, and scientists have also discovered magnetic reconnection events similar to those in the Earth's magnetosphere on various planets.

[0003] The magnetic reconnection events of the magnetosphere of different planets have similar physical characteristics. However, due to the differences in the size of different planets and the differences in the strength of the planetary magnetic field, the magnetic reconnection phenomena of different planets also have their own unique characteristics. The main purpose of the present invention is to detect and discover the magnetic reconnection events of Jupiter. At present, the magnetosphere observation data of Jupiter mainly come from the Galileo satellite and the Juno satellite. The Juno satellite began to observe the magnetosphere of Jupiter since it arrived at Jupiter in 2016. Its orbital period is about 53 Earth days and its aphelion is about 113 Jupiter radii. In the articles of Vogt et al. (2010) and Vogt et al. (2019), 200+ magnetic reconnection events of Jupiter observed by Galileo and Juno satellites through manual judgment were listed. And through comparison, the characteristics of its Jupiter observation were found.

[0004] In traditional research, magnetic reconnection events are often found through human visual judgment, setting standards to find events from massive satellite observation time series data. This requires scientists to spend a lot of time and energy, and is quite subjective and brings errors. Summary of the invention

[0005] In view of the problems of low manual identification efficiency and subjectivity in the existing methods for detecting Jupiter's magnetic reconnection events, as well as difficulty in processing massive Jupiter magnetic field data, the purpose of the present invention is to overcome the above-mentioned defects of the prior art and propose a Jupiter magnetic reconnection event detection method and system based on a deep learning algorithm.

[0006] In view of this, the present invention proposes a Jupiter magnetic reconnection event detection method based on a deep learning algorithm, comprising:

[0007] Obtain Jupiter's magnetic field observation data based on time periods and perform preprocessing;

[0008] The pre-processed data is input into a pre-established and trained magnetic reconnection event detection model, and the detection result of whether a specific time period contains a Jupiter magnetic reconnection event is output;

[0009] The magnetic reconnection event detection model adopts the 1DResNet residual network to mine the magnetic field observation data, realize the semantic reasoning process from the bottom layer to the high layer, and identify the regional blocks containing Jupiter's magnetic reconnection in each regional block in the time series magnetic field data, thereby realizing the detection of magnetic reconnection events.

[0010] Preferably, the time resolution of the magnetic field observation data is 1 second.

[0011] Preferably, the method comprises a step of training a magnetic reconnection event detection model, comprising:

[0012] Collect data, perform preprocessing, and build a training set;

[0013] The data of the training set are input into the 1DResNet residual network in sequence for supervised learning. The cross entropy loss function is used until the training requirements are met to obtain a trained magnetic reconnection event detection model.

[0014] Preferably, the data collection includes: selecting original observation data of the magnetic field observation instrument FGM of the Juno satellite.

[0015] Preferably, the preprocessing includes: data outlier processing, missing value filling, magnetic field spherical coordinate conversion and background average magnetic field removal.

[0016] Preferably, a linear interpolation method is used to process data outliers and fill in missing values.

[0017] Preferably, the magnetic field spherical coordinate transformation includes:

[0018] The magnetic field observation data is converted from the magnetic field observation components in the three directions of x, y, and z in the Cartesian coordinate system at the center of Jupiter , and , converted into three magnetic field components in the spherical coordinate system , and , satisfying the following formula:

[0019]

[0020]

[0021]

[0022] in, is the pitch angle, is the azimuth, r is the distance from the center of Jupiter, x, y, z represent the position components of the observation point, respectively, satisfying the following formula:

[0023]

[0024] When x>0, ;when hour, .

[0025] Preferably, the background average magnetic field removal includes:

[0026] The average magnetic field in the set hour before calculation is taken as the background magnetic field, and the background magnetic field is subtracted from the magnetic field value during the observation period.

[0027] Preferably, establishing a training set includes:

[0028] The pre-processed data are annotated with Jupiter's magnetic reconnection events, including the start and end time, start and end position, and duration of each magnetic reconnection event;

[0029] Slice the annotated data with Jupiter magnetic reconnection events according to the time slice pairs to obtain the magnetic reconnection event data fragments and corresponding labels to form positive samples;

[0030] Corresponding time slices of equal length are intercepted, and data and corresponding labels without Jupiter magnetic reconnection events are taken to form negative samples; thus, a training set is obtained.

[0031] On the other hand, the present invention provides a Jupiter magnetic reconnection event detection system based on a deep learning algorithm, including a preprocessing module and a detection output module, wherein:

[0032] The preprocessing module is used to obtain the magnetic field observation data of Jupiter based on the time period and perform preprocessing;

[0033] The detection output module is used to input the pre-processed data into a pre-established and trained magnetic reconnection event detection model, and output a detection result of whether a specific time period contains a Jupiter magnetic reconnection event;

[0034] The magnetic reconnection event detection model adopts the 1DResNet residual network to mine the magnetic field observation data, realize the semantic reasoning process from the bottom layer to the high layer, and identify the regional blocks containing Jupiter's magnetic reconnection in each regional block in the time series magnetic field data, thereby realizing the detection of magnetic reconnection events.

[0035] Compared with the prior art, the advantages of the present invention are:

[0036] According to the typical characteristics of Jupiter's magnetic reconnection events, the present invention proposes a Jupiter magnetic reconnection event recognition model based on a supervised deep network model 1DResNet, realizes the reasoning process from bottom to top, and finally extracts the observation time period containing Jupiter's magnetic reconnection events. The proposed technical solution uses an end-to-end approach. After the model is trained, no parameters need to be adjusted. Only the corresponding time period data needs to be input into the model, and the corresponding discrimination results of the corresponding time period can be directly output. It is suitable for the automatic analysis and processing of a large amount of Jupiter magnetic field data. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a schematic diagram of the spherical coordinate transformation method;

[0038] Figure 2 is a flow chart of the Jupiter magnetic reconnection event detection method constructed by the present invention;

[0039] Figure 3 This is an example of a major magnetic reconnection event of Jupiter observed by the JUNO probe;

[0040] Figure 4 is a positive label instance (reconnection event occurs);

[0041] Figure 5 It is the local connection structure of the residual network;

[0042] Figure 6 An example of magnetic reconnection detection at Jupiter. DETAILED DESCRIPTION

[0043] As deep learning neural networks have achieved great success and wide application in various image and time series data feature extraction tasks, researchers in the field of space weather and planetary science have also used machine learning technology to analyze various image data and time series data. The search and determination of magnetic reconnection events is a typical task of finding characteristic events from time series data. Therefore, based on this demand, the present invention mainly uses the algorithm for processing time series data features in deep learning, based on the magnetic field observation of the Juno satellite, and uses the manually screened magnetic reconnection events in the article by Vogt et al. (2019) as a data set to establish a set of recognition algorithms for Jupiter magnetic reconnection event detection, improve the batch automatic processing capability of Jupiter magnetic field observation data, and promote the statistical analysis of Jupiter magnetic reconnection event big data. The present invention constructs a Jupiter magnetic reconnection event detection method based on deep learning technology, realizes the automatic, rapid and accurate extraction of Jupiter magnetic reconnection event areas from long-term series observation data, and meets the statistical analysis needs of Jupiter magnetic field magnetic reconnection researchers for long-term and large sample sizes.

[0044] like Figure 2 As shown, this technical solution mainly includes the following steps:

[0045] 1. Data collection: Select the original observation data of the Juno satellite's magnetic field observation instrument Fluxgate Magnetometer (FGM).

[0046] 2. Data preprocessing: including data outlier processing, missing value filling, magnetic field spherical coordinate transformation, background average magnetic field removal and other data preprocessing;

[0047] 3. Dataset preparation: By manually screening samples containing magnetic reconnection events and marking their start and end times, we can build the labeled dataset required for training the magnetic reconnection event recognition model;

[0048] 4. Model selection and testing: Verify the applicability of the model to Juno magnetic field data, and select a network model structure with better performance based on the characteristics of magnetic reconnection events and FGM magnetic field observation data.

[0049] 5. Model evaluation: Use the labeled dataset sample data as the input of the selected magnetic reconnection event identification model, adjust the parameters to train the identification model, obtain the model identification results and evaluate them.

[0050] Below we further explain the specific steps:

[0051] Step 1 is data collection. First, according to the literature and the FGM data of the JUNO satellite magnetic field instrument that needs to be applied, the manually annotated magnetic reconnection events from 2016 to 2019 and the corresponding magnetic field data files are screened out. Magnetic field data is usually stored as one file per day, and the time resolution uses a 1s file type. The file header mainly records the corresponding observation auxiliary parameters, coordinate system characteristics, etc. The physical meaning and storage format of each observed parameter are explained in detail.

[0052] Step 2 is data preprocessing, including data outlier processing, missing value filling, magnetic field spherical coordinate conversion, background average magnetic field removal, etc. Since the original data may be abnormal at some observation points or missing in some time periods (short time) during the operation of the observation instrument, it is necessary to process the outliers and missing values ​​of the data through linear interpolation and other methods. The rationality of the magnetic field data is guaranteed by time resampling. In fact, in judging the magnetic reconnection event of Jupiter, it is mainly dependent on the tangential component of the pitch angle of the magnetic field. Therefore, it is necessary to convert the magnetic field observation data from the components in the three directions of x, y, and z of the Cartesian coordinate system at the center of Jupiter. , and , converted into three magnetic field components in the spherical coordinate system , and , are unit vectors in the corresponding directions respectively.

[0053] like Figure 1 The figure shows the spherical coordinate transformation method. Subsequent calculations are based on the three components in the spherical coordinate system to calculate the corresponding features. The transformation method and formula are as follows:

[0054]

[0055]

[0056]

[0057] in, is the pitch angle, is the azimuth, satisfying the following formulas respectively:

[0058]

[0059]

[0060] When x>0, ;when hour, .

[0061] At the same time, magnetic reconnection events are mainly determined by observing the disturbance of the magnetic field. Therefore, it is often necessary to calculate the disturbance equivalent to the background magnetic field. Here, the magnetic field calm value 10 hours before the calm period is used as the standard for the background magnetic field.

[0062] Step 3 is the data set production. By collecting the annotations of Jupiter's magnetic reconnection events on JUNO and manual corrections in publicly published papers, we preliminarily screened out 233 Jupiter magnetic reconnection events from 2016-2019, and annotated the features required for this study for each event. It mainly records the start and end time, start and end position, duration, etc. of each magnetic reconnection event. According to the corresponding magnetic reconnection event time, we slice the corresponding time segment through the magnetic field data to obtain the corresponding magnetic reconnection event data segment and the corresponding label (positive sample). In order to meet the needs of subsequent detection methods, we also need a certain degree of negative samples. For this reason, we intercept the data of the corresponding equal time that does not contain magnetic reconnection events and the corresponding labels to make negative samples.

[0063] Step 4 is model selection and experimentation. Considering the characteristics of magnetic reconnection events and magnetic field time series observation data, the 1DResNet residual network with excellent performance in multi-scale feature fusion is used as the network model for Jupiter magnetic reconnection event detection. This model improves the performance of deep neural networks by introducing improvements such as span fusion of features at each layer. At the same time, this network model is experimentally compared with other commonly used one-dimensional feature network models to verify the advantages of the 1DResNet model in detecting Jupiter magnetic reconnection events.

[0064] Step 5 is model evaluation. The sample data of the labeled dataset is used as the input of the selected Jupiter magnetic reconnection detection model, and the parameters are adjusted to train the Jupiter magnetic reconnection detection model. The model extraction results are obtained and evaluated. The confusion matrix, a commonly used evaluation indicator in the classification field, is used to measure the model performance. This task is mainly to identify whether a time series data is a magnetic reconnection event, which is a typical binary classification problem. In the binary classification problem, the four basic components of the confusion matrix are: True Positives (TP), True Negatives (TN), False Positives (FP), and False Negatives (FN).

[0065] True Positive (TP) is when the model predicts the positive class, and the prediction is correct, we call it True Positive.

[0066] True Negative (TN) is when the model predicts a negative class, and the prediction is correct, we call it True Negative.

[0067] False Positive (FP) is when the model predicts a positive class, but the prediction is wrong, which we call a false positive.

[0068] False Negative (FN) is when the model predicts a negative class, but the prediction is wrong, we call it False Negative.

[0069] Precision is the ratio of the number of samples that the model predicts to be positive and are actually positive to the number of samples that the model predicts to be positive. .

[0070] Recall is the ratio of the number of samples predicted by the model to be positive and actually positive to the number of actual positive samples. Since magnetic reconnection events are low-probability events in the observation of the entire Jupiter magnetosphere, precision and recall are relatively important indicators in this mission.

[0071] The technical solution of the present invention is described in detail below with reference to the accompanying drawings and embodiments.

[0072] Example 1

[0073] Embodiment 1 of the present invention proposes a method for detecting Jupiter magnetic reconnection events based on a deep learning algorithm, and its research and development technical route is as follows:

[0074] (1) First, according to the literature and the FGM data of the JUNO satellite magnetic field instrument that needs to be applied, the manually annotated magnetic reconnection events and the corresponding magnetic field data files from 2016 to 2019 are screened. In order to construct an intelligent identification method, according to the physical laws of the magnetic reconnection phenomenon and the characteristics of the data, the data needs to be preprocessed in a certain step, mainly including missing data point completion, spherical coordinate vector conversion, and background magnetic field subtraction.

[0075] like Figure 3 Shown is an example of the main magnetic reconnection events of Jupiter observed by the JUNO probe.

[0076] The above table mainly records the start and end time, start and end position, duration, etc. of each magnetic reconnection event. According to the corresponding magnetic reconnection event time, we slice the corresponding time segment through the magnetic field data to obtain the corresponding magnetic reconnection event data segment and the corresponding label (positive sample). In order to meet the needs of subsequent detection methods, we also need a certain degree of negative samples. For this reason, we intercept the data and corresponding labels of the corresponding equal time that do not contain magnetic reconnection events to make negative samples. In this study, due to the limited Jupiter data and magnetic reconnection events, in order to ensure the reliability and stability of the algorithm. Instead of splitting the data set and the test set separately, the 3-fold cross-validation method is adopted. That is, the entire sample set is divided into 3 equal parts, and each training and test uses 2 equal parts as the training set, and the remaining 1 equal part as the validation set. In this way, one training obtains one accuracy, and the 3-fold validation needs to be repeated 3 times, and each equal part must be used as a validation set. The average accuracy obtained in this way is more in line with the actual effect of the model algorithm.

[0077] like Figure 4 The following are typical examples of positive and negative samples.

[0078] (2) After completing the data cleaning process, the main classifier algorithm is constructed. The main applications are the traditional empirical mode decomposition analysis method and the deep learning network analysis method. The corresponding classifiers and judgment criteria are constructed to determine whether the magnetic reconnection event occurs within the target time.

[0079] Empirical mode decomposition (EMD) is based on the concept of instantaneous frequency intrinsic mode function (IMF). It can decompose complex signals into several intrinsic mode functions. Each IMF represents the local characteristics of the signal. The signal is decomposed based on the time scale characteristics of the data itself. The basic idea is to transform an irregular frequency wave into multiple single frequency waves + residual waves. In this detection algorithm, the sample labels of the training set are firstly taken, and the average background of the past 10 hours is subtracted from the magnetic field data. Then, after obtaining the changing waveform, the empirical mode decomposition is performed to obtain 5 single frequency waves + residual waves. Then, in the corresponding detection time area, the corresponding three components of the magnetic field are subjected to the corresponding empirical mode decomposition, and the label data is compared to calculate the similarity distance. Finally, according to the threshold of the set similarity distance, it is judged whether the area contains a magnetic reconnection event. And the corresponding recall rate and accuracy are obtained.

[0080] 1DResnet is a 1D application based on the classic deep learning algorithm Resnet50. Similarly, we first need to use the public pre-trained model based on 1DResnet and apply it to our task. This task uses a 2-classification task, that is, to determine whether the corresponding time segment contains a magnetic reconnection event, which is a positive / negative sample judgment problem. Unlike traditional methods, the method based on deep learning 1DResnet also needs to train negative samples, and the Loss uses cross entropy, which is suitable for 2-classification tasks. The ResNet network refers to the VGG19 network, and is modified on its basis, and residual units are added through a short-circuit mechanism, such as Figure 5 As shown in the figure, x is the input variable of each layer of the residual network, weight layer is the weight parameter of each layer of the model, F(x) is the result after the weight calculation of this layer, and finally added with the original variable (identity) x to form the output of this layer, and relu is the activation function, which is the commonly used linear rectification function.

[0081] In order to verify the reliability of the classifier construction algorithm, the experimental results of the classification need to be cross-validated, that is, to eliminate the bias of manually dividing the training set and the validation set. After obtaining reliable results, the constructed intelligent recognition model is used to perform forward inference of the model, screen out more magnetic reconnection events, and manually verify the screened events. Screening out Jupiter's magnetic reconnection events through intelligent recognition algorithms greatly saves the energy consumed by scientists in manual judgment, while compensating for the errors caused by human subjective factors, and providing support for subsequent research on Jupiter's magnetic reconnection events. After experimental testing, the accuracy of Jupiter's magnetic reconnection event detection obtained by the traditional method of empirical mode decomposition is 78%, the recall rate is 80.8%, and the F1 value is 79.5%. The accuracy of Jupiter's magnetic reconnection event detection obtained by the deep learning 1DResnet method is 82.1%, the recall rate is 77%, and the F1 value is 79.4%. The following are typical magnetic reconnection event detection results. Figure 6 As shown in Figure 195, the event was detected on the 195th day of 2016. The time span in the figure is 1800-2300 UT. The four columns in the figure respectively plot the three components B and B of the magnetic field vector observed by the FGM instrument in the spherical coordinate system after coordinate transformation. r ,B θ ,B φ And the total magnetic field size B t The time of the corresponding detected magnetic reconnection area is shown in the pink shaded area. The time of the magnetic reconnection area is roughly from 1952 to 2049 UT. As can be seen from the figure, the change characteristics of the magnetic field components in the area where magnetic reconnection occurs are similar to the positive samples in the above figure, with corresponding bipolar structures, which is also more in line with the usual theoretical experience. It can be seen that the corresponding detection algorithm has basically reached the expected level in the detection of typical magnetic reconnection events.

[0082] Example 2

[0083] Embodiment 2 of the present invention provides a Jupiter magnetic reconnection event detection system based on a deep learning algorithm, which is implemented based on the method of embodiment 1. The system includes a preprocessing module and a detection output module, wherein:

[0084] The preprocessing module is used to obtain the magnetic field observation data of Jupiter based on the time period and perform preprocessing;

[0085] The detection output module is used to input the pre-processed data into a pre-established and trained magnetic reconnection event detection model, and output a detection result of whether a specific time period contains a Jupiter magnetic reconnection event;

[0086] The magnetic reconnection event detection model adopts the 1DResNet residual network to mine the magnetic field observation data, realize the semantic reasoning process from the bottom layer to the high layer, and identify the regional blocks containing Jupiter's magnetic reconnection in each regional block in the time series magnetic field data, thereby realizing the detection of magnetic reconnection events.

[0087] Innovation:

[0088] This technical solution introduces deep learning technology for the first time to conduct information mining on massive Jupiter magnetic field data, realize the semantic reasoning process from bottom to top, identify each regional block in the time series magnetic field data that contains Jupiter magnetic reconnection and extract it.

[0089] The model is highly robust. After the model is trained, there is no need to adjust any parameters. Simply input the data of the corresponding time period into the model, and it will directly output whether the corresponding time period contains Jupiter's magnetic reconnection event. Therefore, it is suitable for automatic analysis and processing of large amounts of time series data.

[0090] 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 method for detecting Jupiter magnetic reconnection events based on a deep learning algorithm, comprising: Obtain Jupiter's magnetic field observation data based on time periods and perform preprocessing; The preprocessed data is input into a pre-established and trained magnetic reconnection event detection model, and the detection result of whether the time period contains the Jupiter magnetic reconnection event is output; The magnetic reconnection event detection model adopts the 1DResNet residual network to mine the magnetic field observation data, realize the semantic reasoning process from the bottom layer to the high layer, and identify the regional blocks containing Jupiter's magnetic reconnection in each regional block in the time series magnetic field data, thereby realizing the detection of magnetic reconnection events.

2. The Jupiter magnetic reconnection event detection method based on deep learning algorithm according to claim 1 is characterized in that: The time resolution of the magnetic field observation data is 1 second.

3. The Jupiter magnetic reconnection event detection method based on deep learning algorithm according to claim 1, characterized in that: The method includes a step of training a magnetic reconnection event detection model, including: Collect data, perform preprocessing, and build a training set; The data of the training set are input into the 1DResNet residual network in sequence for supervised learning. The cross entropy loss function is used until the training requirements are met to obtain a trained magnetic reconnection event detection model.

4. The Jupiter magnetic reconnection event detection method based on deep learning algorithm according to claim 3 is characterized in that: The data collection includes: selecting the original observation data of the magnetic field observation instrument FGM of the Juno satellite.

5. The Jupiter magnetic reconnection event detection method based on deep learning algorithm according to claim 3 is characterized in that: The preprocessing includes: data outlier processing, missing value filling, magnetic field spherical coordinate transformation and background average magnetic field removal.

6. The Jupiter magnetic reconnection event detection method based on deep learning algorithm according to claim 5, characterized in that: Linear interpolation methods are used to process data outliers and fill in missing values.

7. The Jupiter magnetic reconnection event detection method based on deep learning algorithm according to claim 5, characterized in that: The magnetic field spherical coordinate transformation includes: The magnetic field observation data is converted from the components of the x, y, and z directions of the Cartesian coordinate system centered on Jupiter , and , converted into three magnetic field components in spherical coordinates , and , satisfying the following formula: ； ； ； in, is the pitch angle, is the azimuth, r is the distance from the center of Jupiter, x, y, z represent the position components of the observation point, respectively, satisfying the following formula: ； When x>0, ;when hour, .

8. The Jupiter magnetic reconnection event detection method based on deep learning algorithm according to claim 5, characterized in that: The background average magnetic field removal includes: The average magnetic field in the set hour before calculation is taken as the background magnetic field, and the background magnetic field is subtracted from the magnetic field value during the observation period.

9. The Jupiter magnetic reconnection event detection method based on deep learning algorithm according to claim 3, characterized in that: The establishing of the training set comprises: The pre-processed data are annotated with Jupiter's magnetic reconnection events, including the start and end time, start and end position, and duration of each magnetic reconnection event; Slice the annotated data with Jupiter magnetic reconnection events according to the time slice pairs to obtain the magnetic reconnection event data fragments and corresponding labels to form positive samples; Corresponding time slices of equal length are intercepted, and data and corresponding labels without Jupiter magnetic reconnection events are taken to form negative samples; thus, a training set is obtained.

10. A Jupiter magnetic reconnection event detection system based on deep learning algorithm, characterized in that: It includes a preprocessing module and a detection output module, wherein: The preprocessing module is used to obtain the magnetic field observation data of Jupiter based on the time period and perform preprocessing; The detection output module is used to input the pre-processed data into a pre-established and trained magnetic reconnection event detection model, and output a detection result of whether a specific time period contains a Jupiter magnetic reconnection event; The magnetic reconnection event detection model adopts the 1DResNet residual network to mine the magnetic field observation data, realize the semantic reasoning process from the bottom layer to the high layer, and identify the regional blocks containing Jupiter's magnetic reconnection in each regional block in the time series magnetic field data, thereby realizing the detection of magnetic reconnection events.

Images