Seismic source position and magnitude simultaneous inversion method based on graph neural network induction

Abstract

The invention provides a method for simultaneously inverting the position and magnitude of an induced earthquake source based on a graph neural network. Comprising the following steps: Step 1: data input and preprocessing; 2, making a graph neural network to train label data; 3, establishing a graph neural network model; step 4: training a graph neural network model; and Step 5, predicting the position and magnitude of the seismic source through the graph neural network. According to the method, training and testing data sets are made based on a gas storage induced seismic event catalog accumulated in the early stage, three-component original induced seismic waveforms and station coordinates of all stations serve as node attributes of a graph neural network, and a self-adaptive moment estimation method is adopted to train and predict a model; the method provides technical support for high-efficiency and high-precision intelligent seismic source positioning of seismic events induced by the gas storage, and lays a theoretical foundation for evaluating the dynamic sealing performance of the gas storage, guiding optimization and adjustment of injection-production parameters of the gas storage and guaranteeing safe production and operation.

Description

Technical Field

[0001] The present invention belongs to the field of long-term monitoring of earthquakes induced by gas storage reservoirs; in particular, it relates to a method for simultaneous inversion of the source position and magnitude of earthquakes induced by gas storage reservoirs based on a graph neural network. Background Art

[0002] In the process of dynamic monitoring of gas storage, induced seismic monitoring has fast feedback speed and high sensitivity, and can identify the seismic activity phenomena that may be caused by production activities, and then image the geometric occurrence of induced fractures. Through the real-time inversion of the time and spatial distribution and source intensity of induced seismic sources, the geometric occurrence of induced fractures, the changes in ground stress and the connectivity of fracture grids can be estimated, and the rock fracture activities such as faults, caprocks and bottom layers can be monitored in real time, providing a scientific basis for safety warning of gas storage and optimization of injection and production parameters.

[0003] Unlike hydraulic fracturing monitoring of tight oil and gas reservoirs, dynamic monitoring of gas storage requires long-term monitoring of the target area, with large amounts of data and the characteristics of large interference from human activities and high noise. These noises intersect with the distribution range of effective signals in the time domain and frequency domain, making it difficult to accurately pick up the first arrival of the seismic phase of the induced earthquake event, making the source location method based on the first arrival information less accurate. In addition, the accuracy of conventional source location methods strongly depends on the accuracy of the velocity model of the monitoring area, and often requires experienced processing personnel to repeatedly adjust the velocity model and the corresponding processing parameters to obtain reasonable positioning results. The efficiency is low and cannot meet the requirements of real-time monitoring of induced earthquakes in gas storages.

[0004] With the rise of deep learning in recent years, some scholars have used machine learning to locate earthquake sources. Perol et al. (2018) used a convolutional neural network to roughly predict the location of an earthquake based on the input single-station seismic record, but this method can only predict the approximate area where the earthquake occurred and cannot obtain the accurate location of the earthquake source. Zhu et al. (2022) combined machine learning with cloud computing large-capacity seismic records, used the deep learning model PhaseNet to select the first arrival of P waves and S waves, and used machine learning methods to associate the picked P and S wave first arrivals with the earthquake source location, proving the feasibility of using machine learning to predict the earthquake source location, but this method still does not directly predict the exact location of the earthquake source in space. Cui Yi et al. (2023) disclosed a method for locating microseismic events by combining spectrum analysis and convolutional neural networks. This method uses wavelet transform to convert single-component high-energy frequency band microseismic waveforms into time-frequency spectrum diagrams containing time-frequency domain energy information, and constructs a mapping relationship model between the time-frequency spectrum diagram of the microseismic waveform and the earthquake source location. Zhang Yan et al. (2023) disclosed a microseismic source location method based on convolutional neural network, which uses convolutional neural network to extract the characteristics of single-component seismic waveform and associate it with the source position, thereby realizing the prediction of the spatial position of the source. However, these methods do not use the location information of the station and cannot predict the magnitude of the induced earthquake. Summary of the invention

[0005] The purpose of the present invention is to provide a method for simultaneous inversion of the source position and magnitude of induced earthquakes based on graph neural networks, to establish an intelligent induced earthquake positioning system with adaptability and high learning efficiency, and to simultaneously obtain the source spatial position and magnitude of induced earthquakes during the injection and production process of gas storage reservoirs.

[0006] The present invention is achieved through the following technical solutions:

[0007] The present invention relates to a method for simultaneously inverting the location and magnitude of an induced earthquake source based on a graph neural network, comprising the following steps:

[0008] Step 1: Data input and preprocessing: Input the original induced seismic three-component waveform data and seismic station coordinates, and perform normalization preprocessing on them; integrate the induced seismic waveform data of different periods in the gas storage monitoring area, and establish a training database and a test database;

[0009] Step 2: Create graph neural network training label data: Based on the existing induced earthquake catalog of the gas storage facility, extract the spatial location and magnitude of the induced earthquake event and save it in text form as the training label of the graph neural network model;

[0010] Step 3: Establish a graph neural network model: Based on the convolutional neural network, a feature extractor for the attributes of each node in the graph neural network is established. A multi-layer perceptron is used to fuse the node attribute features with the coordinates of the seismic station. After maximum aggregation, an aggregated feature vector of the graph neural network model is formed. Finally, a multi-layer perceptron is used to map the aggregated feature vector to the spatial position and magnitude of the earthquake source.

[0011] Step 4: Graph neural network model training: Adopt the adaptive learning rate, high computational efficiency, and strong memory adaptive moment estimation algorithm to train the initialized graph neural network model, so that it can fully learn the relationship between the induced earthquake waveform characteristics, the coordinates of the seismic station and the spatial position and magnitude of the induced earthquake, and obtain a trained graph neural network model;

[0012] Step 5: Graph neural network predicts the source location and magnitude: Based on the graph neural network model trained in Step 4, the three-component waveform data of induced earthquakes and the coordinates of seismic stations in the test database are input to obtain the predicted spatial location and magnitude of the induced earthquake source.

[0013] Preferably, in Step 1, the original induced seismic three-component waveform data is the three-component induced seismic waveform data in the training database and the test database, and the processing formula is:

[0014]

[0015] Where x is the waveform data of a component of the original induced seismic event, x m is the maximum absolute value of the waveform of all stations corresponding to the induced seismic event, and y is the normalized waveform data of this component.

[0016] Furthermore, the induced seismic waveform data of different periods in the integrated gas storage monitoring area are divided into a training data set and a test data set according to a certain ratio.

[0017] Preferably, in Step 2, extracting the spatial position and magnitude of the induced seismic event specifically comprises: extracting the x-coordinate, y-coordinate, z-coordinate and moment magnitude corresponding to the induced seismic event.

[0018] Preferably, in Step 3, the specific steps of establishing the graph neural network model are: using the convolutional neural network model to extract the attribute characteristics of each node in the graph neural network, inputting the original three-component induced seismic waveform data into the convolutional neural network for dimensionality reduction, and extracting waveform characteristics of each scale; integrating the extracted waveform characteristics of each scale with the seismic station coordinates (x-coordinate, y-coordinate and z-coordinate), and using a multi-layer perceptron to form feature vectors of each node containing induced seismic waveform characteristics and seismic station information.

[0019] Preferably, in Step 3, the specific step of forming the aggregated feature vector of the graph neural network model through maximum aggregation is: merging the feature vectors of each node to form a feature matrix, and performing aggregation according to the maximum row, and the formula is:

[0020] b i =max(A ij )

[0021] In the formula, A ij is the feature matrix formed by merging the feature vectors of each node, i and j are the row and column numbers of the feature matrix respectively, max is the maximum value, b i The graph neural network aggregate feature vector formed after feature matrix aggregation.

[0022] Preferably, in Step 3, the specific steps of using a multilayer perceptron to map the aggregated feature vector to the spatial position and magnitude of the earthquake source are: passing the aggregated feature vector of the graph neural network through a multilayer perceptron, mapping it to the x-coordinate, y-coordinate, z-coordinate and moment magnitude of the induced earthquake source, so as to realize the prediction of the spatial position and magnitude of the induced earthquake event.

[0023] Preferably, in Step 4, the activation function of the graph neural network model uses the Relu function as follows: thereby alleviating the problem of gradient disappearance:

[0024] f(m)=max(0,m)

[0025] Where f(m) is the activation function value, and m is the difference between the predicted source attribute and the label:

[0026]

[0027] In the formula, x ^ ,y ^ 、z ^ and are the x, y, z coordinates and moment magnitude of the induced earthquake predicted by the graph neural network model, x o ,y o 、z o and are the true x, y, z coordinates and moment magnitude of the induced seismic event, respectively.

[0028] Preferably, in Step 4, the formula for training the graph neural network model initialized by the adaptive moment estimation algorithm with adaptive learning rate, high computational efficiency and strong memory is as follows: the learning rate can be automatically adjusted in different parameter dimensions, thereby accelerating the convergence speed and improving the stability of training:

[0029]

[0030] In the formula, gt is the gradient of the loss function J at the tth iteration, For the Hamiltonian operator, the adaptive moment estimation algorithm constructs the first-order moment c of the gradient of the loss function t and the second moment v t To update the parameter m:

[0031] c t =β1·c t-1 +(1-β1)·g t

[0032]

[0033] Where β1 and β2 are exponential decay rates, usually 0.9 and 0.999 respectively. The deviation correction of the first-order moment and the second-order moment is:

[0034]

[0035] In the formula, and are the deviation corrections of the first-order moment and the second-order moment respectively, so the parameters can be updated as follows:

[0036]

[0037] In the formula, α is the learning rate, and τ is a small constant, usually 1e -4 , which is used to ensure numerical stability.

[0038] Preferably, in Step 5, the specific steps of predicting the source location and magnitude of the earthquake by the graph neural network are: inputting the original induced earthquake three-component waveform data and the seismic station coordinates in the test database into the trained graph neural network model to obtain the normalized source spatial position and magnitude, and then denormalizing to obtain the source location and magnitude of the induced earthquake predicted in the gas storage monitoring area.

[0039] Principle of the method of the present invention: The method of simultaneous inversion of the source location and magnitude of induced earthquakes based on graph neural networks involved in the present invention uses the original three-component waveform of induced earthquakes at each station and the station coordinates as the attributes of each node of the graph neural network, uses a convolutional neural network to reduce the dimension of each node attribute of the graph neural network, extracts the feature vector of each node through a multilayer perceptron, and uses the maximum aggregation method to obtain the aggregated feature vectors of all nodes of the graph neural network, and uses the multilayer perceptron to realize the attribute prediction of the graph neural network.

[0040] The present invention has the following advantages:

[0041] (1) The present invention uses an adaptive moment estimation algorithm to train the established graph neural network model without the need for accurate prior information of the velocity model, so that the model can fully learn the relationship between the induced earthquake waveform information, station coordinates and source location and magnitude, thereby efficiently obtaining high-precision source location and magnitude inversion results, reducing the cost of human-computer interaction and the error introduced by manual picking, and providing technical support for the establishment of an intelligent monitoring system for induced earthquakes of gas storage reservoir integrity.

[0042] (2) The method for simultaneous inversion of the source location and magnitude of induced earthquakes based on graph neural networks proposed in the present invention is applicable to the field of long-term monitoring of induced earthquakes in gas storage reservoirs. It can obtain the spatial location and magnitude of the source of induced earthquake events during the injection and production process of gas storage reservoirs, provide technical support for quantitative judgment of accidents such as rock fractures and fault activation inside gas storage reservoirs, and is of great significance for rapid and accurate dynamic monitoring and evaluation of the geological integrity and natural gas leakage of gas storage reservoirs. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of inverting the source location and magnitude of induced earthquake events based on the graph neural network model;

[0044] Figure 2 This is a schematic diagram of the principle of inverting the source location and magnitude of induced earthquake events based on the graph neural network model;

[0045] Figure 3 It is the observation system diagram of the forward model for 3D simulation of gas storage induced earthquake monitoring;

[0046] Figure 4 This is a demonstration diagram of the xz slice of the simulated gas storage longitudinal wave velocity model;

[0047] Figure 5 The waveform of the Vx component of a certain induced earthquake is obtained by using the three-dimensional staggered grid finite difference simulation of the elastic wave equation;

[0048] Figure 6 It is a graph of the loss function of the graph neural network model simulating gas storage-induced earthquake monitoring;

[0049] Figure 7 Comparison of the predicted results of the hypocenter location of the simulated gas storage-induced earthquake based on the graph neural network model and the actual results: the hypocenter location results are compared with the top view (left), the hypocenter location results are compared with the side view (middle), and the hypocenter location results are compared with the front view (right);

[0050] Figure 8 The intersection diagrams of the predicted results of the hypocenter location and magnitude of the simulated gas storage-induced earthquake based on the graph neural network model and the actual results are as follows: the hypocenter x-coordinate intersection diagram (a), the hypocenter y-coordinate intersection diagram (b), the hypocenter z-coordinate intersection diagram (c) and the moment-magnitude intersection diagram (d);

[0051] Fig. 9 This is the observation system and velocity model effect diagram of the actual induced seismic monitoring of a gas storage reservoir: the xy slice of the longitudinal wave velocity (left), the xz slice of the longitudinal wave velocity (right);

[0052] Fig.10 It is the waveform of the Vx component of a certain induced earthquake in the measured gas storage reservoir;

[0053] Fig.11 It is a graph of the loss function of the graph neural network model for testing gas storage-induced earthquake monitoring;

[0054] Fig.12 This is a comparison of the predicted results of the measured gas storage-induced earthquake source location based on the graph neural network model and the actual results: the source location result comparison top view (left), the source location result comparison side view (middle) and the source location result comparison front view (right);

[0055] Fig.13 These are the intersection diagrams of the predicted results of the measured gas storage-induced earthquake source locations and magnitudes based on the graph neural network model and the actual results: the x-coordinate intersection diagram of the earthquake source (a), the y-coordinate intersection diagram of the earthquake source (b), the z-coordinate intersection diagram of the earthquake source (c), and the moment-magnitude intersection diagram (d). DETAILED DESCRIPTION

[0056] The present invention is described in detail below in conjunction with specific embodiments. It should be noted that the following embodiments are only further descriptions of the present invention, but the protection scope of the present invention is not limited to the following embodiments.

[0057] Example 1

[0058] This example simulates the induced seismic data of a gas storage reservoir. Figure 1 As shown, the specific steps are:

[0059] (1) Input the three-component waveform data of simulated gas storage-induced earthquakes (SimulatedWave.segy) and the coordinates of seismic stations (Stations.csv), normalize and preprocess the raw data, and establish training and testing databases.

[0060] (2) Based on the catalog of simulated gas storage-induced earthquake events, the x-coordinate, y-coordinate, z-coordinate and moment magnitude of the induced earthquake events are extracted as labels for training data and test data.

[0061] (3) Initialize the graph neural network model. Figure 2As shown in the figure, a convolutional neural network model is used to extract the characteristic attributes of each node, and a multi-layer perceptron is used to obtain the characteristic vector of each node. After maximum aggregation, the aggregated characteristic vector of the graph neural network is mapped to the spatial position and moment magnitude of the earthquake source in the training label through the multi-layer perceptron.

[0062] (4) The adaptive moment estimation method is used to train the graph neural network model, the learning rate is set to 0.0002, the iteration cycle is set to 500, and the data batch size is set to 10.

[0063] (5) The three-component waveform data of induced earthquakes and the seismic station data in the test database are input into the trained graph neural network model to obtain the predicted spatial location of the earthquake source and the moment magnitude corresponding to the induced event.

[0064] Figure 3 To simulate the forward model of induced earthquake monitoring in gas storage, the triangles in the figure are seismic stations arranged on the ground, and the circles are induced earthquake events distributed in three different areas. 100 induced earthquake events are set in each area, 250 of which are selected for training, and the other 50 events are selected for testing. Figure 4 The figure shows the xz slice demonstration of the longitudinal wave velocity model of the simulated gas storage reservoir. It can be seen that the velocity distribution of this forward simulation is relatively complex, including abnormal velocity distribution such as faults and uplifts. Figure 5 To obtain the Vx component waveform of an induced earthquake using the three-dimensional staggered grid finite difference simulation of the elastic wave equation, Figure 6 This is the loss function diagram of the graph neural network model for simulating gas storage-induced earthquake monitoring. It can be seen that after 500 iterations of training, the loss function value remains basically stable, that is, the training is completed. Figure 7 The predicted results (black dots) of the hypocenter location of earthquakes induced by simulated gas storage reservoirs based on the graph neural network model are compared with the actual results (circles). As can be seen from the figure, the distribution ranges of the two are basically the same, which verifies the correctness of the method. Figure 8 The cross-plot of the hypocenter location and magnitude prediction results of the simulated gas storage-induced earthquake based on the graph neural network model and the actual results; Figure 8 a. Figure 8 b. Figure 8 c and Figure 8 d are the intersection diagrams of the predicted x-coordinate, y-coordinate, z-coordinate and moment magnitude of the earthquake source and the actual results. Figure 8 It can be seen that the predicted results and the actual results are basically distributed around the 45° oblique line, which further proves the correctness of the method of the present invention.

[0065] Example 2

[0066] This embodiment is to measure the induced seismic data of the gas storage reservoir, and the specific steps are as follows:

[0067] (1) Input the three-component waveform data of gas storage-induced earthquakes (FieldWave.segy) and the coordinates of seismic stations (FieldStations.csv), normalize and preprocess the raw data, and establish training and testing databases.

[0068] (2) Based on the catalog of measured gas storage-induced earthquake events, the x-coordinate, y-coordinate, z-coordinate and moment magnitude of the induced earthquake events are extracted as labels for training data and test data.

[0069] (3) Initialize the graph neural network model. Figure 2 As shown in the figure, a convolutional neural network model is used to extract the characteristic attributes of each node, and a multi-layer perceptron is used to obtain the characteristic vector of each node. After maximum aggregation, the aggregated characteristic vector of the graph neural network is mapped to the spatial position and moment magnitude of the earthquake source in the training label through the multi-layer perceptron.

[0070] (4) The adaptive moment estimation method is used to train the graph neural network model, the learning rate is set to 0.0002, the iteration cycle is set to 500, and the data batch size is set to 10.

[0071] (5) The three-component waveform data of induced earthquakes and the seismic station data in the test database are input into the trained graph neural network model to obtain the predicted spatial location of the earthquake source and the moment magnitude corresponding to the induced event.

[0072] Fig. 9 This is the P-wave velocity model for monitoring gas storage-induced earthquakes. The left figure shows the P-wave velocity xy slice, the right figure shows the P-wave velocity xz slice, and the triangles in the figure are seismic stations arranged along the surface. 285 events of measured gas storage-induced earthquakes were selected for training, and another 15 events were used for testing. Fig.10 This is the waveform of the Vx component of an induced earthquake in a gas storage reservoir. It can be seen that the measured waveform has a large recording noise and several channels do not record valid signals. Fig.11 This is the loss function diagram of the graph neural network model for the test gas storage-induced earthquake monitoring. It can be seen that after 500 iterations of training, the loss function value remains basically stable, that is, the training is completed. Fig.12 The comparison chart of the predicted results (black dots) and the actual results (circles) of the hypocenter locations of gas storage-induced earthquakes based on the graph neural network model is shown in Figure 2. Fig.12 It can be seen that the distribution ranges of the two are basically the same, which verifies the correctness of this method.

[0073] Fig.13 The graph shows the intersection of the predicted results of the source location and magnitude of the measured gas storage-induced earthquake based on the graph neural network model and the actual results. Fig.13 a. Fig.13 b. Fig.13 c and Fig.13d are the intersection diagrams of the predicted source x-coordinate, y-coordinate, z-coordinate and moment magnitude with the actual results. As can be seen from the figure, the predicted results and the actual results are basically distributed around the 45° oblique line, which further proves the correctness of the method of the present invention.

[0074] The present invention uses an adaptive moment estimation algorithm to train the established graph neural network model, without the need for accurate prior information of the velocity model, so that the model can fully learn the relationship between the induced earthquake waveform information, station coordinates and source location, and magnitude, thereby efficiently obtaining high-precision source location and magnitude inversion results, reducing the cost of human-computer interaction and the error introduced by manual picking, and providing technical support for the establishment of an intelligent monitoring system for induced earthquakes of gas storage reservoir integrity.

[0075] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art may make various modifications or variations within the scope of the claims, which will not affect the essence of the present invention.

Claims

1. A method for simultaneous inversion of earthquake source location and magnitude based on graph neural network, characterized in that: The steps include: Step 1: Data input and preprocessing: Input the original induced seismic three-component waveform data and seismic station coordinates, and perform normalization preprocessing on them; integrate the induced seismic waveform data of different periods in the gas storage monitoring area, and establish a training database and a test database; Step 2: Create graph neural network training label data: Based on the information in the training database and the test database, extract the spatial location and magnitude of the induced earthquake event and save it in text form as the training label of the graph neural network model; Step 3: Establish a graph neural network model: Based on the convolutional neural network, a feature extractor for the attributes of each node in the graph neural network is established. A multi-layer perceptron is used to fuse the node attribute features with the coordinates of the seismic station. After maximum aggregation, an aggregated feature vector of the graph neural network model is formed. Finally, a multi-layer perceptron is used to map the aggregated feature vector to the spatial position and magnitude of the earthquake source. Step 4: Graph neural network model training: Adopt the adaptive learning rate, high computational efficiency, and strong memory adaptive moment estimation algorithm to train the initialized graph neural network model, so that it can fully learn the relationship between the induced earthquake waveform characteristics, the coordinates of the seismic station and the spatial position and magnitude of the induced earthquake, and obtain a trained graph neural network model; Step 5: Graph neural network predicts the source location and magnitude: Based on the graph neural network model trained in Step 4, the three-component waveform data of induced earthquakes and the coordinates of seismic stations in the test database are input to obtain the predicted spatial location and magnitude of the induced earthquake source.

2. The method for simultaneous inversion of earthquake source location and magnitude based on graph neural network induced earthquake according to claim 1, characterized in that: In Step 1, the original induced seismic three-component waveform data is the three-component induced seismic waveform data in the training database and the test database, and the processing formula is: Where x is the waveform data of a component of the original induced seismic event, x m is the maximum absolute value of the waveform of all stations corresponding to the induced seismic event, and y is the normalized waveform data of this component.

3. The method for simultaneous inversion of earthquake source location and magnitude based on graph neural network induced earthquake according to claim 1, characterized in that: In Step 2, the extraction of the spatial position and magnitude of the induced earthquake event specifically includes: extracting the x-coordinate, y-coordinate, z-coordinate and moment magnitude corresponding to the induced earthquake event.

4. The method for simultaneous inversion of earthquake source location and magnitude based on graph neural network induced earthquake according to claim 1, characterized in that: In Step 3, the specific steps of establishing the graph neural network model are: using the convolutional neural network model to extract the attribute characteristics of each node in the graph neural network, inputting the original three-component induced seismic waveform data into the convolutional neural network for dimensionality reduction, and extracting waveform characteristics of each scale; integrating the extracted waveform characteristics of each scale with the coordinates of the seismic station (x-coordinate, y-coordinate, z-coordinate), and using a multi-layer perceptron to form a feature vector of each node containing the induced seismic waveform characteristics and the seismic station information.

5. The method for simultaneous inversion of earthquake source location and magnitude based on graph neural network induced earthquake according to claim 1, characterized in that: In Step 3, the specific steps of forming the aggregated feature vector of the graph neural network model through maximum aggregation are: merging the feature vectors of each node to form a feature matrix, and aggregating according to the maximum row, and the formula is: b i =max(A ij ) In the formula, A ij is the feature matrix formed by merging the feature vectors of each node, i and j are the row and column numbers of the feature matrix respectively, max is the maximum value, b i The graph neural network aggregate feature vector formed after feature matrix aggregation.

6. The method for simultaneous inversion of earthquake source location and magnitude based on graph neural network induced earthquake according to claim 1, characterized in that: In Step 3, the specific steps of using a multilayer perceptron to map the aggregated feature vector to the spatial position and magnitude of the earthquake source are as follows: the aggregated feature vector of the graph neural network is passed through a multilayer perceptron to map it to the x-coordinate, y-coordinate, z-coordinate and moment magnitude of the induced earthquake source, so as to realize the prediction of the spatial position and magnitude of the induced earthquake event.

7. The method for simultaneous inversion of earthquake source location and magnitude based on graph neural network induced earthquake according to claim 1, characterized in that: In Step 4, the activation function of the graph neural network model uses the Relu function, as follows: f(m)=max(0,m) Where f(m) is the activation function value, and m is the difference between the predicted source attribute and the label: In the formula, x ^ ,y ^ 、z ^ and are the x, y, z coordinates and moment magnitude of the induced earthquake predicted by the graph neural network model, x o ,y o 、z o and are the true x, y, z coordinates and moment magnitude of the induced seismic event, respectively.

8. The method for simultaneous inversion of earthquake source location and magnitude based on graph neural network induced earthquake according to claim 1, characterized in that: In Step 4, the formula for training the initialized graph neural network model using the adaptive moment estimation algorithm with adaptive learning rate, high computational efficiency and strong memory is as follows: In the formula, g t is the gradient of the loss function J at the tth iteration, For the Hamiltonian operator, the adaptive moment estimation algorithm constructs the first-order moment c of the gradient of the loss function t and the second moment v t To update the parameter m: c t =β1·c t-1 +(1-β1)·g t Where β1 and β2 are exponential decay rates, which are 0.9 and 0.999 respectively. The deviation correction of the first-order moment and the second-order moment is: In the formula, and are the deviation corrections of the first-order moment and the second-order moment respectively, so the parameters can be updated as follows: In the formula, α is the learning rate, and τ is a small constant, usually 1e -4 , which is used to ensure numerical stability.

9. The method for simultaneous inversion of earthquake source location and magnitude based on graph neural network induced earthquake according to claim 1, characterized in that: In Step 5, the specific steps of predicting the source location and magnitude of the earthquake by the graph neural network are as follows: the original induced earthquake three-component waveform data and seismic station coordinates in the test database are input into the trained graph neural network model to obtain the normalized source spatial location and magnitude, and then the source location and magnitude of the induced earthquake predicted in the gas storage monitoring area are obtained through denormalization.

Images