Earthquake monitoring and early warning method and system based on GNSS multi-source information fusion

Abstract

The application discloses a GNSS multi-source information fusion-based earthquake monitoring and early warning method and system, relates to the technical field of earthquake monitoring, and comprises the following steps: feature extraction is performed on processed multi-source earthquake-related data to obtain earthquake feature data, comprehensive feature fusion calculation is performed on the earthquake feature data to obtain earthquake fusion feature coefficients, environment comprehensive influence calculation is performed on ground environment data to obtain comprehensive environment influence coefficients, comprehensive earthquake probability evaluation calculation is performed based on the comprehensive environment influence coefficients and the earthquake fusion feature coefficients to obtain a comprehensive earthquake probability score, the size of the comprehensive earthquake probability score is used to determine an earthquake probability level, and earthquake monitoring and early warning are performed based on the earthquake probability level, so that accurate judgment of earthquake monitoring and early warning is realized under the condition of combination of multi-source data and environment influence.

Description

Technical Field

[0001] This invention relates to the field of earthquake monitoring technology, specifically to an earthquake monitoring and early warning method and system based on GNSS multi-source information fusion. Background Technology

[0002] Real-time monitoring of seismic activity is crucial for preventing earthquake disasters and reducing casualties and property damage. Traditional earthquake monitoring technologies are primarily based on the detection and analysis of seismic waves. However, these methods have significant limitations: First, seismic waves are susceptible to various factors when propagating through the Earth's crust, such as the complexity of geological structures and environmental noise, which can lead to signal attenuation and interference, thus affecting the accuracy and timeliness of monitoring. Second, traditional methods often cannot effectively integrate data from different sources and types, such as geological, meteorological, and human activity data, which limits the comprehensiveness of predictive models and the early identification capability of warnings.

[0003] Existing multimodal data fusion methods still face some technical challenges, failing to efficiently process and integrate large-scale heterogeneous data; and when various environmental changes occur, they cannot accurately assess earthquake monitoring and early warning. Summary of the Invention

[0004] To address the shortcomings mentioned in the background section, the present invention aims to provide an earthquake monitoring and early warning method and system based on GNSS multi-source information fusion.

[0005] Firstly, the objective of this invention can be achieved through the following technical solution: an earthquake monitoring and early warning method based on GNSS multi-source information fusion, the method comprising the following steps: Receive multi-source earthquake correlation data, preprocess the multi-source earthquake correlation data to obtain processed multi-source earthquake correlation data, wherein the multi-source earthquake correlation data includes seismic wave signal data, surface deformation data, geological structure data and acoustic wave data; Feature extraction is performed on the processed multi-source earthquake correlation data to obtain earthquake feature data. The earthquake feature data is then fused to obtain earthquake fusion feature coefficients. The earthquake feature data includes seismic wave features, surface deformation features, geological structure features, and acoustic wave features. Receive ground environmental data, perform comprehensive environmental impact calculations on the ground environmental data, and obtain a comprehensive environmental impact coefficient. The ground environmental data includes ground temperature data, ground humidity data, and ground pressure data. The comprehensive earthquake probability assessment is performed based on the comprehensive environmental impact coefficient and the earthquake fusion characteristic coefficient to obtain a comprehensive earthquake probability score. The earthquake probability level is determined based on the magnitude of the comprehensive earthquake probability score, and earthquake monitoring and early warning are carried out based on the earthquake probability level.

[0006] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the calculation of the surface deformation data is based on the collection of the horizontal distance and vertical distance of the surface, and is obtained by comprehensive calculation using preset standard coefficients and preset ratios.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the calculation formula for the surface deformation data is as follows: In the formula, exp() is an exponential function, Si is the horizontal distance to the ground surface, Ci is the vertical distance to the ground surface, Xi is the ground surface deformation data, S0 is the preset standard horizontal coefficient, C0 is the preset standard vertical coefficient, k1 and k2 are preset weight coefficients; i is the acquisition number of the multi-source seismic correlation data, and i = 1, 2, 3, ..., n, where n is the total number of acquisitions of the multi-source seismic correlation data.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: performing feature extraction on the processed multi-source seismic correlation data based on a deep learning algorithm. Seismic wave features are obtained by extracting time-domain and frequency-domain features from seismic wave signal data, followed by feature fusion and splicing. Structural and tectonic features are extracted from geological structural data, and then the geological structural features are fused to obtain the geological structural features. Temporal deformation features and spatial deformation features were extracted from the surface deformation data, and then the deformation features were fused to obtain the geological deformation features. After extracting time-domain features from acoustic wave data, an attention mechanism is introduced to obtain acoustic wave features.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the calculation process of performing comprehensive feature fusion calculation on the seismic feature data is as follows: Seismic wave characteristics are labeled as Bzi, surface deformation characteristics as Xzi, geological structure characteristics as Gzi, and acoustic wave characteristics as Vzi. Using formula The seismic fusion characteristic coefficient Wzi was calculated. In the formula, For the Sigmoid function, a1 is the seismic wave influence coefficient, a2 is the surface deformation influence coefficient, a3 is the geological structure influence coefficient, a4 is the acoustic wave influence coefficient, k1 is the seismic wave proportionality coefficient, k2 is the surface deformation proportionality coefficient, k3 is the geological structure proportionality coefficient, k4 is the acoustic wave proportionality coefficient, and f is the bias term.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of calculating the comprehensive environmental impact of ground environmental data to obtain a comprehensive environmental impact coefficient, including: Ground temperature is labeled as Tj, ground humidity as Qj, and pressure gradient as Yj, where j is the data label of the ground environmental data, and j = 1, 2, 3, ..., m, where m is the total number of ground environmental data. Using calculation formula The comprehensive environmental impact coefficient Hj was calculated. In the formula, T0 is the preset standard ground temperature coefficient, Q0 is the preset standard ground humidity coefficient, and Y0 is the preset standard pressure gradient coefficient; For the rate of temperature change, The rate of change of humidity. The pressure change rate is represented by w1, w2, and w3, which are preset proportional coefficients, and w1 + w2 + w3 = 1.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of calculating the comprehensive earthquake probability assessment based on the comprehensive environmental impact coefficient and the earthquake fusion characteristic coefficient, comprising: Using formula The comprehensive earthquake probability score Pij is calculated. In the formula, α is the overall weight coefficient of ground features, and β is the overall characteristic coefficient of environmental impact.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of determining the earthquake probability level based on the magnitude of the comprehensive earthquake probability score, comprising: Preset the upper and lower limits of earthquake probability safety [Pmin, Pmax]; Where Pmin is the lower limit of earthquake probability safety and Pmax is the upper limit of earthquake probability safety; The comprehensive earthquake probability score Pij is calculated by comparing it with the lower limit of earthquake probability safety Pmin and the upper limit of earthquake probability safety Pmax, and the earthquake probability level is determined based on the magnitude of the ratio.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: the process of determining the earthquake probability level based on the obtained ratio, comprising: Calculate the first ratio ; Calculate the second ratio ; Wherein, the first ratio is greater than the second ratio; When γ1≥1 and γ2<1, it is determined that the earthquake is of high probability level, an early warning is issued, and a high probability period is set as the monitoring period for earthquakes. When γ1 < 1 or γ1 ≥ 1 and γ2 ≥ 1, the low-probability period is set as the monitoring earthquake period.

[0014] Secondly, in order to achieve the above objectives, this invention discloses an earthquake monitoring and early warning system based on GNSS multi-source information fusion, comprising: The data processing module is used to receive multi-source earthquake-related data, preprocess the multi-source earthquake-related data, and obtain processed multi-source earthquake-related data, wherein the multi-source earthquake-related data includes seismic wave signal data, surface deformation data, geological structure data, and acoustic wave data. The feature processing module is used to extract features from the processed multi-source earthquake-related data to obtain earthquake feature data, and to perform comprehensive feature fusion calculation on the earthquake feature data to obtain earthquake fusion feature coefficients. The earthquake feature data includes seismic wave features, surface deformation features, geological structure features, and acoustic wave features. The environmental impact processing module is used to receive ground environmental data, perform comprehensive environmental impact calculations on the ground environmental data, and obtain a comprehensive environmental impact coefficient. The ground environmental data includes ground temperature data, ground humidity data, and ground pressure data. The monitoring and early warning module is used to perform comprehensive earthquake probability assessment calculations based on the comprehensive environmental impact coefficient and earthquake fusion characteristic coefficient, obtain a comprehensive earthquake probability score, determine the earthquake probability level based on the magnitude of the comprehensive earthquake probability score, and perform earthquake monitoring and early warning based on the earthquake probability level.

[0015] The beneficial effects of this invention are: This invention first extracts features from processed multi-source earthquake-related data to obtain earthquake feature data. Then, it performs comprehensive feature fusion calculations on the earthquake feature data to obtain earthquake fusion feature coefficients. Next, it calculates the comprehensive environmental impact of ground environmental data to obtain a comprehensive environmental impact coefficient. Based on the comprehensive environmental impact coefficient and the earthquake fusion feature coefficients, it performs a comprehensive earthquake probability assessment to obtain a comprehensive earthquake probability score. Based on the magnitude of the comprehensive earthquake probability score, it determines the earthquake probability level. Finally, it performs earthquake monitoring and early warning based on the earthquake probability level, thus achieving accurate judgment of earthquake monitoring and early warning based on multi-source data and the combination of environmental impacts. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1: like Figure 1 As shown, an earthquake monitoring and early warning method based on GNSS multi-source information fusion includes the following steps: S101: Receive multi-source earthquake correlation data, preprocess the multi-source earthquake correlation data, and obtain processed multi-source earthquake correlation data, wherein the multi-source earthquake correlation data includes seismic wave signal data, surface deformation data, geological structure data, and acoustic wave data. Specifically, the process of acquiring multi-source earthquake-related data includes the following steps: Seismic wave signal data is obtained by installing and deploying broadband seismographs near ground faults to form a triangular observation network, with a sampling frequency of 20 Hz. The data includes the arrival time and oscillation frequency of the seismic waves, thus providing the basis for locating the seismic source. Surface deformation data is obtained by collecting horizontal and vertical distances from the surface, and then comprehensively calculating the data using preset standard coefficients and preset proportions. The specific calculation process is as follows: In the formula, exp() is an exponential function, Si is the horizontal distance to the ground surface, Ci is the vertical distance to the ground surface, Xi is the ground surface deformation data, S0 is the preset standard horizontal coefficient, C0 is the preset standard vertical coefficient, and k1 and k2 are preset weight coefficients; in the formula, i is the acquisition number of the multi-source seismic correlation data, and i = 1, 2, 3, ..., n, where n is the total number of acquisitions of the multi-source seismic correlation data. The preset weighting coefficients are obtained by training based on the proportion of horizontal distance and distance to surface deformation. Furthermore, in the specific implementation process, the preset standard horizontal coefficient and the preset standard vertical coefficient are obtained by repeatedly simulating and calculating the average value of the data after collecting the horizontal and vertical distances of the ground surface on a daily basis. Geological structure data is collected in real time using ground-penetrating radar to acquire relevant information about geological structures. Acoustic data is dynamically acquired through infrasound sensors and ground acoustic sensors. The infrasound sensors are installed in an array and protected by windproof covers to avoid the influence of wind noise. The ground acoustic sensors monitor the sound generated when faults slide by directly coupling with the bedrock. Specifically, in this embodiment, the preprocessing of multi-source seismic data includes: Outlier removal and cleaning were performed on both seismic signal data and geological structure data. Outlier removal was performed using variance threshold detection, and zero-point drift was avoided by calculating and removing the mean. The resulting seismic signal data and geological structure data were processed in this way. This preprocessing method prevented the occurrence of outlier data that could affect subsequent judgments of seismic signals and geological structures. The surface deformation data, namely GNSS deformation data, is standardized in terms of data format. This standardization makes the format of this part of the surface deformation data easier to process later, resulting in processed surface deformation data. Noise suppression of wind waves is performed on the acoustic data, and the propagation speed of the sound waves is corrected to be consistent, so that the acoustic data can be further correlated with other data when used later to obtain processed acoustic data; The processed seismic wave signal data, geological structure data, surface deformation data, and acoustic wave data are fused into multi-source data. By synchronizing the data time and transforming the coordinates, the processed seismic wave signal data, geological structure data, surface deformation data, and acoustic wave data are unified, and finally processed multi-source earthquake-related data are obtained. S102: Extract features from the processed multi-source earthquake correlation data to obtain earthquake feature data. Perform comprehensive feature fusion calculation on the earthquake feature data to obtain earthquake fusion feature coefficients. The earthquake feature data includes seismic wave features, surface deformation features, geological structure features, and acoustic wave features. The feature extraction process for the processed multi-source seismic correlation data is based on deep learning algorithms, including: Seismic wave signal data were subjected to time-domain feature extraction and frequency-domain feature extraction respectively, and then the features were fused and stitched together to obtain seismic wave features. Among them, time-domain feature extraction was performed using a one-dimensional convolutional neural network, and frequency-domain feature extraction was performed using a two-dimensional convolutional neural network. Structural features and tectonic features are extracted from the geological structure data, and then the geological structure features are fused to obtain the geological structure features. Specifically, in this embodiment, structural features are extracted using a three-dimensional convolutional neural network, and tectonic features are extracted using a two-dimensional convolutional neural network. Temporal deformation features and spatial deformation features are extracted from the surface deformation data, and then the deformation features are fused to obtain geological deformation features. Specifically, the temporal deformation features are extracted by combining a one-dimensional convolutional neural network and an LSTM network, while the spatial deformation features are extracted by a two-dimensional convolutional neural network or a three-dimensional convolutional neural network. After extracting time-domain features from acoustic wave data, an attention mechanism is introduced to assign signal weights, thereby obtaining acoustic wave features. Specifically, the calculation process for integrating and fusing seismic feature data is as follows: Seismic wave characteristics are labeled as Bzi, surface deformation characteristics as Xzi, geological structure characteristics as Gzi, and acoustic wave characteristics as Vzi. Using formula The seismic fusion characteristic coefficient Wzi was calculated. In the formula, The sigmoid function is used for calculations. a1 is the seismic wave influence coefficient, a2 is the surface deformation influence coefficient, a3 is the geological structure influence coefficient, a4 is the acoustic wave influence coefficient, k1 is the seismic wave proportionality coefficient, k2 is the surface deformation proportionality coefficient, k3 is the geological structure proportionality coefficient, k4 is the acoustic wave proportionality coefficient, and f is the bias term used to adjust the sensitivity of the model during calculations. In this embodiment, the seismic wave influence coefficient, surface deformation influence coefficient, geological structure influence coefficient, and acoustic wave influence coefficient are calculated by comprehensively evaluating the influence of external factors during the routine extraction of seismic wave features, surface deformation features, geological structure features, and acoustic wave features. These factors include human factors, factors extracted by machine algorithms, and environmental factors. Human factors are those caused by improper human operation or scanning. Factors extracted by machine algorithms include the structural instability of the convolutional neural network and extraction errors. In this embodiment, the seismic wave proportionality coefficient represents the effective descriptive proportion of the signal released by the seismic wave during the process of the seismic wave affecting the earthquake, which provides an early warning of the earthquake; the surface deformation proportionality coefficient represents the descriptive proportion of the medium-term strain accumulation state of the crustal surface; the geological structure proportionality coefficient represents the descriptive proportion of the background of the long-term geological structure in the region; and the acoustic wave proportionality coefficient represents the descriptive proportion of the acoustic influence signal generated when various underground media rupture. S103: Receive ground environmental data, perform comprehensive environmental impact calculation on the ground environmental data, and obtain a comprehensive environmental impact coefficient. The ground environmental data includes ground temperature data, ground humidity data, and ground pressure data. Specifically, in this embodiment, the ground temperature data includes ground temperature and temperature change rate, the ground humidity data includes ground humidity and humidity change rate, and the ground pressure data is pressure gradient; Specifically, the process of calculating the comprehensive environmental impact of ground environmental data includes: The ground environmental data are labeled. Specifically, the ground temperature is labeled as Tj, the ground humidity as Qj, and the pressure gradient as Yj, where j is the data label of the ground environmental data, and j = 1, 2, 3, ..., m, where m is the total number of ground environmental data. Using calculation formula The comprehensive environmental impact coefficient Hj was calculated. In the formula, T0 is the preset standard ground temperature coefficient, Q0 is the preset standard ground humidity coefficient, and Y0 is the preset standard pressure gradient coefficient; For the rate of temperature change, The rate of change of humidity. The pressure change rate is represented by w1, w2, and w3, which are preset proportional coefficients, and w1 + w2 + w3 = 1. The preset proportional coefficient is derived from the weighting of the influence of ground temperature, ground humidity and pressure gradient on the comprehensive environmental impact coefficient. S104: Based on the comprehensive environmental impact coefficient and the seismic fusion characteristic coefficient, a comprehensive earthquake probability assessment calculation is performed to obtain a comprehensive earthquake probability score. The earthquake probability level is determined based on the magnitude of the comprehensive earthquake probability score, and earthquake monitoring and early warning are carried out based on the earthquake probability level.

[0019] The process of calculating the comprehensive earthquake probability assessment based on the comprehensive environmental impact coefficient and the earthquake fusion characteristic coefficient includes: Using formula The comprehensive earthquake probability score Pij is calculated. α is the overall weighting coefficient of ground features, and β is the overall characteristic coefficient of environmental impact; Among them, the overall weight coefficient of ground features represents the fundamental control effect of the internal dynamic process of the ground on the probability of earthquake occurrence, reflecting the decisive role of crustal accumulation, ground deformation and geological structure, etc.; the overall characteristic coefficient of environmental impact represents the influence of environmental impact on the modulation and triggering effect of earthquake occurrence by changing the mechanical state of fault zones, reflecting the decisive role of overall temperature, humidity and pressure gradient, etc. The process of determining the earthquake probability level based on the magnitude of the comprehensive earthquake probability score includes: Preset the upper and lower limits of earthquake probability safety [Pmin, Pmax]; Where Pmin is the lower limit of earthquake probability safety and Pmax is the upper limit of earthquake probability safety; The comprehensive earthquake probability score Pij is calculated by ratioing it to the lower earthquake probability safety limit Pmin and the upper earthquake probability safety limit Pmax, respectively. The earthquake probability level is determined based on the magnitude of the ratio. The process includes: Calculate the first ratio Calculate the second ratio The first ratio is greater than the second ratio; When γ1≥1 and γ2<1, it is determined that the earthquake is at a high probability level. Earthquake early warning is issued for earthquakes at the high probability level, including issuing early warning information. A high probability period (15 minutes) is set as the monitoring period for earthquakes. The situation of whether an earthquake occurs on the ground is monitored every 15 minutes. When γ1 < 1 or γ1 ≥ 1 and γ2 ≥ 1, it is determined to be a low probability earthquake level. For low probability earthquakes, a low probability period (half a day) is normally set as the monitoring period for earthquake monitoring and early warning.

[0020] Example 2: Figure 2 As shown, the earthquake monitoring and early warning system based on GNSS multi-source information fusion includes: Data processing module 11 is used to receive multi-source earthquake-related data, preprocess the multi-source earthquake-related data, and obtain processed multi-source earthquake-related data, wherein the multi-source earthquake-related data includes seismic wave signal data, surface deformation data, geological structure data, and acoustic wave data. The feature processing module 12 is used to extract features from the processed multi-source earthquake-related data to obtain earthquake feature data, and to perform comprehensive feature fusion calculation on the earthquake feature data to obtain earthquake fusion feature coefficients. The earthquake feature data includes seismic wave features, surface deformation features, geological structure features, and acoustic wave features. The environmental impact processing module 13 is used to receive ground environmental data, perform comprehensive environmental impact calculations on the ground environmental data, and obtain a comprehensive environmental impact coefficient. The ground environmental data includes ground temperature data, ground humidity data, and ground pressure data. The monitoring and early warning module 14 is used to perform comprehensive earthquake probability assessment calculation based on the comprehensive environmental impact coefficient and the earthquake fusion characteristic coefficient, obtain a comprehensive earthquake probability score, determine the earthquake probability level based on the magnitude of the comprehensive earthquake probability score, and perform earthquake monitoring and early warning based on the earthquake probability level.

[0021] Based on the same inventive concept, this invention also provides a computer device, comprising: one or more processors, and a memory for storing one or more computer programs; the programs include program instructions, and the processor executes the program instructions stored in the memory. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, used to implement one or more instructions, specifically for loading and executing one or more instructions stored in a computer storage medium to implement the above-described method.

[0022] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, performs the above-described method. This storage medium can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0023] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0024] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0025] The foregoing has shown and described the basic principles, main features, and advantages of this disclosure. Those skilled in the art should understand that this disclosure is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of this disclosure. Various changes and modifications can be made to this disclosure without departing from its spirit and scope, and all such changes and modifications fall within the scope of this disclosure as claimed.

Claims

1. An earthquake monitoring and early warning method based on GNSS multi-source information fusion, characterized in that, The method includes the following steps: Receive multi-source earthquake correlation data, preprocess the multi-source earthquake correlation data to obtain processed multi-source earthquake correlation data, wherein the multi-source earthquake correlation data includes seismic wave signal data, surface deformation data, geological structure data and acoustic wave data; Feature extraction is performed on the processed multi-source earthquake correlation data to obtain earthquake feature data. The earthquake feature data is then fused to obtain earthquake fusion feature coefficients. The earthquake feature data includes seismic wave features, surface deformation features, geological structure features, and acoustic wave features. Receive ground environmental data, perform comprehensive environmental impact calculations on the ground environmental data, and obtain a comprehensive environmental impact coefficient. The ground environmental data includes ground temperature data, ground humidity data, and ground pressure data. The comprehensive earthquake probability assessment is performed based on the comprehensive environmental impact coefficient and the earthquake fusion characteristic coefficient to obtain a comprehensive earthquake probability score. The earthquake probability level is determined based on the magnitude of the comprehensive earthquake probability score, and earthquake monitoring and early warning are carried out based on the earthquake probability level.

2. The earthquake monitoring and early warning method based on GNSS multi-source information fusion according to claim 1, characterized in that, The calculation of the surface deformation data is based on the collection of horizontal and vertical distances from the surface, and is obtained through a comprehensive calculation using preset standard coefficients and preset proportions.

3. The earthquake monitoring and early warning method based on GNSS multi-source information fusion according to claim 2, characterized in that, The formula for calculating the surface deformation data is as follows: In the formula, exp() is an exponential function, Si is the horizontal distance of the ground surface, Ci is the vertical distance of the ground surface, Xi is the ground surface deformation data, S0 is the preset standard horizontal coefficient, C0 is the preset standard vertical coefficient, and k1 and k2 are preset weight coefficients. i is the acquisition number of the multi-source seismic correlation data, and i = 1, 2, 3, ..., n, where n is the total number of acquisitions of the multi-source seismic correlation data.

4. The earthquake monitoring and early warning method based on GNSS multi-source information fusion according to claim 1, characterized in that, The feature extraction of the processed multi-source earthquake correlation data is performed using a deep learning algorithm. Seismic wave features are obtained by extracting time-domain and frequency-domain features from seismic wave signal data, followed by feature fusion and splicing. Structural and tectonic features are extracted from geological structural data, and then the geological structural features are fused to obtain the geological structural features. Temporal deformation features and spatial deformation features were extracted from the surface deformation data, and then the deformation features were fused to obtain the geological deformation features. After extracting time-domain features from acoustic wave data, an attention mechanism is introduced to obtain acoustic wave features.

5. The earthquake monitoring and early warning method based on GNSS multi-source information fusion according to claim 3, characterized in that, The calculation process for performing comprehensive feature fusion calculation on seismic feature data is as follows: Seismic wave characteristics are labeled as Bzi, surface deformation characteristics as Xzi, geological structure characteristics as Gzi, and acoustic wave characteristics as Vzi. Using formula The seismic fusion characteristic coefficient Wzi was calculated. In the formula, For the Sigmoid function, a1 is the seismic wave influence coefficient, a2 is the surface deformation influence coefficient, a3 is the geological structure influence coefficient, a4 is the acoustic wave influence coefficient, k1 is the seismic wave proportionality coefficient, k2 is the surface deformation proportionality coefficient, k3 is the geological structure proportionality coefficient, k4 is the acoustic wave proportionality coefficient, and f is the bias term.

6. The earthquake monitoring and early warning method based on GNSS multi-source information fusion according to claim 5, characterized in that, The process of calculating the comprehensive environmental impact of ground environmental data to obtain the comprehensive environmental impact coefficient includes: Ground temperature is labeled as Tj, ground humidity as Qj, and pressure gradient as Yj, where j is the data label of the ground environmental data, and j = 1, 2, 3, ..., m, where m is the total number of ground environmental data. Using calculation formula The comprehensive environmental impact coefficient Hj was calculated. In the formula, T0 is the preset standard ground temperature coefficient, Q0 is the preset standard ground humidity coefficient, and Y0 is the preset standard pressure gradient coefficient; For the rate of temperature change, The rate of change of humidity. The pressure change rate is represented by w1, w2, and w3, which are preset proportional coefficients, and w1 + w2 + w3 = 1.

7. The earthquake monitoring and early warning method based on GNSS multi-source information fusion according to claim 6, characterized in that, The process of calculating the comprehensive earthquake probability assessment based on the comprehensive environmental impact coefficient and the earthquake fusion characteristic coefficient includes: Using formula The comprehensive earthquake probability score Pij is calculated. In the formula, α is the overall weight coefficient of ground features, and β is the overall characteristic coefficient of environmental impact.

8. The earthquake monitoring and early warning method based on GNSS multi-source information fusion according to claim 7, characterized in that, The process of determining the earthquake probability level based on the magnitude of the comprehensive earthquake probability score includes: Preset the upper and lower limits of earthquake probability safety [Pmin, Pmax]; Where Pmin is the lower limit of earthquake probability safety and Pmax is the upper limit of earthquake probability safety; The comprehensive earthquake probability score Pij is calculated by comparing it with the lower limit of earthquake probability safety Pmin and the upper limit of earthquake probability safety Pmax, and the earthquake probability level is determined based on the magnitude of the ratio.

9. The earthquake monitoring and early warning method based on GNSS multi-source information fusion according to claim 8, characterized in that, The process of determining the earthquake probability level based on the obtained ratio includes: Calculate the first ratio ; Calculate the second ratio ; Wherein, the first ratio is greater than the second ratio; When γ1≥1 and γ2<1, it is determined that the earthquake is of high probability level, an early warning is issued, and a high probability period is set as the monitoring period for earthquakes. When γ1 < 1 or γ1 ≥ 1 and γ2 ≥ 1, the low-probability period is set as the monitoring earthquake period.

10. An earthquake monitoring and early warning system based on GNSS multi-source information fusion, characterized in that, include: The data processing module is used to receive multi-source earthquake-related data, preprocess the multi-source earthquake-related data, and obtain processed multi-source earthquake-related data, wherein the multi-source earthquake-related data includes seismic wave signal data, surface deformation data, geological structure data, and acoustic wave data. The feature processing module is used to extract features from the processed multi-source earthquake-related data to obtain earthquake feature data, and to perform comprehensive feature fusion calculation on the earthquake feature data to obtain earthquake fusion feature coefficients. The earthquake feature data includes seismic wave features, surface deformation features, geological structure features, and acoustic wave features. The environmental impact processing module is used to receive ground environmental data, perform comprehensive environmental impact calculations on the ground environmental data, and obtain a comprehensive environmental impact coefficient. The ground environmental data includes ground temperature data, ground humidity data, and ground pressure data. The monitoring and early warning module is used to perform comprehensive earthquake probability assessment calculations based on the comprehensive environmental impact coefficient and earthquake fusion characteristic coefficient, obtain a comprehensive earthquake probability score, determine the earthquake probability level based on the magnitude of the comprehensive earthquake probability score, and perform earthquake monitoring and early warning based on the earthquake probability level.

Images