Earthquake geophysical data anomaly detection and early warning method based on big data analysis

Abstract

The invention belongs to the technical field of earthquake monitoring, and provides an earthquake geophysical data anomaly detection and early warning method based on big data analysis, which comprises the following steps: S1, acquiring earthquake geophysical observation data; s2, carrying out cleaning, integration and normalization processing on the collected data; s3, extracting characteristic parameters related to interference and abnormity from the preprocessed data; s4, performing anomaly detection on the extracted feature parameters by using a big data analysis technology; according to the method, various seismic geophysical data such as seismic wave data, geological structure data and underground fluid dynamics are collected, systematic cleaning, integration, normalization processing and feature extraction are carried out, anomaly detection is carried out by using a big data analysis technology, and anomaly early warning information is generated in combination with a pre-established anomaly early warning model. Accuracy and timeliness of earthquake monitoring are effectively improved, and powerful technical support is provided for prevention and response of earthquake disasters.

Description

Technical Field

[0001] The present invention belongs to the technical field of earthquake monitoring, and in particular to an earthquake geophysical data anomaly detection and early warning method based on big data analysis. Background Art

[0002] In the field of earthquake monitoring, traditional methods mainly rely on seismological theory and geological structure analysis. However, these methods are often limited by the incompleteness of data and the limitations of analytical methods, resulting in the accuracy and timeliness of prediction results being difficult to meet actual needs. With the rapid development of big data technology, more and more researchers have begun to explore how to use big data technology to conduct in-depth analysis and mining of earthquake geophysical data in order to improve the accuracy and reliability of earthquake monitoring.

[0003] Although some earthquake prediction methods based on big data analysis have been proposed, these methods still have many shortcomings. For example, some methods only focus on a single type of data (such as seismic wave data), while ignoring the impact of multi-dimensional data such as geological structure and underground fluid dynamics on observation data; some methods lack systematicity and comprehensiveness in data processing and feature extraction, resulting in the extracted feature parameters being insufficient to fully reflect the laws of interference and abnormal changes in observation data; and some methods rely on empirical rules and simple statistics in anomaly detection and warning generation, making it difficult to effectively identify complex and changeable interference and abnormal changes in observation data.

[0004] Therefore, how to integrate various earthquake geophysical data and use big data technology to conduct systematic and comprehensive analysis and early warning has become an urgent problem to be solved in the current earthquake monitoring field. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a seismic geophysical data anomaly detection and early warning method based on big data analysis, so as to solve the problems in the prior art that are often limited by the incompleteness of data and the limitations of analysis methods, resulting in the accuracy and timeliness of the prediction results being difficult to meet actual needs.

[0006] The seismic geophysical data anomaly detection and early warning method based on big data analysis includes:

[0007] S1. Collecting seismic geophysical observation data, including but not limited to geoelectric and geomagnetic data, deformation data, and underground fluid dynamic data;

[0008] S2. Clean, integrate and normalize the collected data to remove noise and outliers and improve data quality;

[0009] S3. Extracting characteristic parameters related to interference and abnormal changes in the observed data from the preprocessed data, wherein the characteristic parameters include but are not limited to information such as the frequency, trend, and change amplitude of the observed data curve;

[0010] S4. Use big data analysis technology to perform anomaly detection on the extracted feature parameters and identify abnormal data that does not match the normal observation data;

[0011] S5. Based on the results of anomaly detection and in combination with the pre-established interference and anomaly warning model, interference and anomaly warning information is generated, and the warning information is sent to relevant departments and personnel through a preset communication method.

[0012] Preferably, step S2 also includes performing dimensionality reduction processing on the data to reduce computational complexity and improve data processing efficiency.

[0013] Preferably, in step S3, a machine learning algorithm is used to perform feature selection and feature transformation on the seismic geophysical data to extract more representative feature parameters.

[0014] Preferably, in step S4, an anomaly detection algorithm based on Gaussian distribution is used to perform anomaly detection on the extracted feature parameters.

[0015] Preferably, in step S5, when establishing the interference and abnormality warning model, the model includes a prediction function and a loss function.

[0016] Preferably, in step S5, the interference and abnormal warning model is trained and optimized using a gradient descent algorithm in combination with geoelectric and geomagnetic data, deformation data, and underground fluid dynamic data to improve the accuracy of the warning.

[0017] Preferably, a data visualization step is also included to display the collected seismic geophysical data and anomaly detection results in an intuitive graphical manner, so that researchers can conduct more in-depth analysis and research on observation data interference and abnormal changes.

[0018] Big data analysis technology is a powerful tool that can deeply mine and analyze massive, multi-dimensional seismic geophysical data. In this method, the specific operation steps of using big data analysis technology to perform anomaly detection on the extracted characteristic parameters include: first, obtaining high-quality characteristic parameters through preprocessing steps; then, using big data analysis algorithms, such as anomaly detection algorithms based on Gaussian distribution, to deeply analyze the characteristic parameters, calculate their probability density and compare them with the preset threshold; finally, identify those abnormal data whose probability density is lower than the threshold and does not match the normal observation data, thereby providing a key basis for abnormal warning. This series of steps fully utilizes the advantages of big data analysis technology in processing complex data and mining potential laws.

[0019] The earthquake geophysical data anomaly detection and early warning system based on big data analysis uses the earthquake geophysical data anomaly detection and early warning method based on big data analysis, including:

[0020] Data acquisition module: collects seismic geophysical observation data, including but not limited to geoelectric and geomagnetic data, deformation data, and underground fluid dynamic data;

[0021] Data preprocessing module: cleans, integrates and normalizes the collected data to remove noise and outliers and improve data quality;

[0022] Feature extraction module: extracts characteristic parameters related to observed data interference and abnormal changes from preprocessed data, including but not limited to frequency, trend, change amplitude and other information of observed data curve;

[0023] Anomaly detection module: Use big data analysis technology to perform anomaly detection on the extracted feature parameters and identify abnormal data that does not match the normal observation data;

[0024] Warning generation module: Based on the results of anomaly detection and combined with the pre-established interference and anomaly warning models, it generates interference and anomaly warning information, and sends the warning information to relevant departments and personnel through the preset communication method.

[0025] A processor is configured to execute the above-mentioned earthquake geophysical data anomaly detection and early warning method based on big data analysis.

[0026] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned earthquake geophysical data anomaly detection and early warning method based on big data analysis.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention collects a variety of seismic geophysical data such as seismic wave data, geological structure data, underground fluid dynamics, etc., and performs cleaning, integration and normalization processing to effectively remove noise and outliers, improve the quality of data, and provide a reliable basis for subsequent analysis and early warning.

[0029] 2. The present invention uses a machine learning algorithm to perform feature selection and feature transformation on the preprocessed data, and extracts characteristic parameters such as frequency, trend, amplitude and abnormal change information of the observed data curve that are closely related to the interference and abnormal changes of the observed data. These characteristic parameters are more representative and can more comprehensively reflect the laws of interference and abnormal changes of the observed data.

[0030] 3. The present invention uses an anomaly detection algorithm based on Gaussian distribution to perform anomaly detection on the extracted feature parameters, which can accurately identify abnormal data that does not match normal observation data, thereby improving the accuracy of abnormal warning.

[0031] 4. The present invention combines geoelectric and geomagnetic data, deformation data, and underground fluid dynamic data, and uses a gradient descent algorithm to train and optimize the interference and abnormal warning model, thereby improving the predictive ability and timeliness of the warning model, so that the warning information can be sent to relevant departments and personnel more promptly.

[0032] 5. The present invention also includes a data visualization step, which displays the collected earthquake geophysical data and anomaly detection results in an intuitive graphical manner, making it easier for researchers to conduct more in-depth analysis and research on observation data interference and abnormal changes, and providing strong support for the field of earthquake monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of the earthquake geophysical data anomaly detection and early warning method based on big data analysis of the present invention;

[0034] Figure 2 This is a framework diagram of the earthquake geophysical data anomaly detection and early warning system based on big data analysis of the present invention. DETAILED DESCRIPTION

[0035] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0036] Embodiment: The present invention provides a method for detecting and warning anomalies in earthquake geophysical data based on big data analysis, such as Figure 1 As shown, including:

[0037] S1. Collecting seismic geophysical observation data, including but not limited to geoelectric and geomagnetic data, deformation data, and underground fluid dynamic data;

[0038] S2. Clean, integrate and normalize the collected data to remove noise and outliers and improve data quality;

[0039] S3. Extracting characteristic parameters related to interference and abnormal changes in the observed data from the preprocessed data, wherein the characteristic parameters include but are not limited to information such as the frequency, trend, and change amplitude of the observed data curve;

[0040] S4. Use big data analysis technology to perform anomaly detection on the extracted feature parameters and identify abnormal data that does not match the normal observation data;

[0041] S5. Based on the results of anomaly detection and in combination with the pre-established interference and anomaly warning model, interference and anomaly warning information is generated, and the warning information is sent to relevant departments and personnel through a preset communication method.

[0042] From the above, it can be seen that the present invention collects a variety of seismic geophysical data such as geoelectric and geomagnetic data, deformation data, underground fluid dynamic data, and performs systematic cleaning, integration, normalization and feature extraction, uses big data analysis technology to perform anomaly detection, and combines a pre-established anomaly warning model to generate anomaly warning information, thereby effectively improving the accuracy and timeliness of earthquake monitoring, and providing strong technical support for the prevention and response to earthquake disasters.

[0043] Furthermore, in step S2, the normalization formula includes:

[0044]

[0045] Among them, X is the original data, μ is the mean, and σ is the standard deviation;

[0046] It also includes dimensionality reduction of data to reduce computational complexity and improve data processing efficiency.

[0047] From the above, we can see that by normalizing and reducing the dimension of the data, we can not only effectively remove noise and outliers and improve the quality of the data, but also reduce the computational complexity and significantly improve the efficiency of data processing, providing a more streamlined and high-quality data foundation for subsequent feature extraction and anomaly detection, thereby further enhancing the accuracy and timeliness of anomaly warnings.

[0048] Furthermore, in step S3, a machine learning algorithm is used to perform feature selection and feature transformation on the seismic geophysical data to extract more representative feature parameters. The formula of the machine learning algorithm includes:

[0049]

[0050] Where I(X;Y) is the mutual information between X and Y, p(x,y) is the joint probability distribution of X and Y, and p(x) and p(y) are the marginal probability distributions of X and Y, respectively.

[0051] From the above, we can see that the use of machine learning algorithms to select and transform features of seismic geophysical data can accurately extract more representative characteristic parameters such as frequency, trend, and abnormal change information of the observed data curve that are closely related to the interference and abnormal changes of the observed data. These characteristic parameters can more comprehensively reflect the laws of interference and abnormal changes in observed data, and provide more reliable and effective data support for subsequent anomaly detection and early warning, thereby further improving the accuracy and reliability of abnormal early warning.

[0052] Furthermore, in step S4, an anomaly detection algorithm based on Gaussian distribution is used to perform anomaly detection on the extracted feature parameters, and the formula of the anomaly detection algorithm based on Gaussian distribution includes: if the data point x satisfies p′(x)<ε, it is regarded as an anomaly point, where p′(x) is the probability density function of the data point x under the Gaussian distribution, and ε is a preset threshold.

[0053] From the above, we can see that the use of anomaly detection algorithm based on Gaussian distribution to detect anomalies in the extracted feature parameters can accurately identify abnormal data that does not match normal observation data. This algorithm effectively distinguishes abnormal points from normal points by calculating the probability density of data points under Gaussian distribution and comparing them with the preset threshold. This method not only improves the accuracy of anomaly detection, but also provides a more reliable data basis for subsequent anomaly warnings, which helps relevant departments and personnel to take timely response measures and reduce the losses caused by earthquake disasters.

[0054] Furthermore, in step S5, when establishing the interference and abnormality warning model, the model includes a prediction function and a loss function, and the formula of the prediction function includes: The formula of the loss function includes: Among them, m is the number of samples, y (i) is the label of the i-th sample.

[0055] From the above, we can see that by constructing an interference and anomaly warning model including prediction function and loss function, we can make more accurate predictions and evaluations of observation data interference and abnormal changes based on anomaly detection results. The prediction function is used to predict the possibility of earthquake occurrence based on characteristic parameters, while the loss function is used to measure the difference between the prediction results and the actual observation data interference and abnormal changes, thereby guiding the optimization and improvement of the model. This model construction method not only improves the accuracy of anomaly warning, but also enhances the generalization ability of the model, enabling it to better adapt to the characteristics and laws of different observation data interference and abnormal changes, and provides more powerful support for the prevention and response to earthquake disasters.

[0056] Furthermore, in step S5, the interference and abnormal warning model is trained and optimized using a gradient descent algorithm in combination with geoelectric and geomagnetic data, deformation data, and underground fluid dynamic data to improve the accuracy of the warning. The formula of the gradient descent algorithm includes: Among them, α is the learning rate.

[0057] From the above, we can see that by combining geoelectric and geomagnetic data, deformation data, and underground fluid dynamic data, and using the gradient descent algorithm to train and optimize the interference and anomaly warning model, the prediction ability and accuracy of the warning model can be significantly improved. The gradient descent algorithm continuously adjusts the parameters of the model to minimize the loss function, thereby finding the optimal combination of model parameters. This method not only makes full use of the information of a variety of seismic geophysical data, but also continuously approaches the real observation data interference and abnormal change laws through iterative optimization, providing more reliable and accurate prediction results for abnormal warning, which helps relevant departments and personnel to respond in time and reduce the impact of earthquake disasters.

[0058] Furthermore, it also includes a data visualization step, which displays the collected seismic geophysical data and anomaly detection results in an intuitive graphical way, so that researchers can conduct more in-depth analysis and research on observation data interference and abnormal changes.

[0059] From the above, we can see that displaying the collected seismic geophysical data and anomaly detection results in an intuitive graphical way greatly facilitates researchers' in-depth analysis and research on observation data interference and abnormal changes. Through visualization, researchers can more intuitively understand the distribution and characteristics of data, discover potential laws and trends in the data, and thus provide more intuitive basis and inspiration for the improvement and optimization of earthquake monitoring models, further promoting the development and progress of earthquake monitoring technology.

[0060] Furthermore, the earthquake geophysical data anomaly detection and early warning method based on big data analysis of the embodiment is compared with the current traditional earthquake prediction method based on big data analysis (comparative example), and the following table is obtained:

[0061]

[0062]

[0063] By comparison, it can be seen that the earthquake geophysical data anomaly detection and early warning method based on big data analysis of the embodiment shows significant advantages in data acquisition range, data processing, feature extraction, anomaly detection, early warning model construction, early warning accuracy, timeliness and data visualization. Compared with the traditional earthquake prediction method based on big data analysis, its comprehensive effect is more outstanding and can better meet the actual needs of earthquake monitoring.

[0064] Earthquake geophysical data anomaly detection and early warning system based on big data analysis, such as Figure 2 As shown, the above-mentioned earthquake geophysical data anomaly detection and early warning method based on big data analysis includes:

[0065] Data acquisition module: collects seismic geophysical observation data, including but not limited to geoelectric and geomagnetic data, deformation data, and underground fluid dynamic data;

[0066] Data preprocessing module: cleans, integrates and normalizes the collected data to remove noise and outliers and improve data quality;

[0067] Feature extraction module: extracts characteristic parameters related to observed data interference and abnormal changes from preprocessed data, including but not limited to frequency, trend, change amplitude and other information of observed data curve;

[0068] Anomaly detection module: Use big data analysis technology to perform anomaly detection on the extracted feature parameters and identify abnormal data that does not match the normal observation data;

[0069] Warning generation module: Based on the results of anomaly detection and combined with the pre-established interference and anomaly warning models, it generates interference and anomaly warning information, and sends the warning information to relevant departments and personnel through the preset communication method.

[0070] Working principle: This method collects a variety of seismic geophysical data and processes them systematically, uses machine learning algorithms to extract characteristic parameters, adopts advanced anomaly detection algorithms to identify abnormal data, combines multiple data training and optimizes early warning models, and provides data visualization steps. It effectively improves the accuracy and timeliness of earthquake monitoring, provides comprehensive and reliable technical support for the prevention and response to earthquake disasters, and has important practical application value.

[0071] The embodiment of the present application provides an electronic device, which is applicable to the above-mentioned earthquake geophysical data anomaly detection and early warning method based on big data analysis, including:

[0072] Memory, used to protect computer programs and data;

[0073] Processor, used to run system programs.

[0074] The embodiment of the present application provides a computer storage medium, which is suitable for the above-mentioned earthquake geophysical data anomaly detection and early warning method based on big data analysis, and performs hierarchical confidentiality management on the above-mentioned system and data in accordance with confidentiality management requirements.

[0075] Those skilled in the art will appreciate that the embodiments of the present application may be provided as a system or a computer program product. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0076] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0077] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0079] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0080] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0081] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory media such as modulated data signals and carrier waves.

[0082] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, commodity or device including the elements.

[0083] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for detecting and warning anomalies in earthquake geophysical data based on big data analysis, characterized in that ,include: S1. Collect seismic geophysical observation data; S2, cleaning, integrating and normalizing the collected data; S3, extracting characteristic parameters related to interference and anomaly from the preprocessed data; S4. Use big data analysis technology to perform anomaly detection on the extracted feature parameters and identify abnormal data that does not match the normal observation data; S5. Based on the results of anomaly detection and in combination with the pre-established interference and anomaly warning model, interference and anomaly warning information is generated, and the warning information is sent to relevant departments and personnel through a preset communication method.

2. The method for detecting and warning anomalies of earthquake geophysical data based on big data analysis according to claim 1, characterized in that: In step S2, it also includes performing dimensionality reduction processing on the data.

3. The method for detecting and warning anomalies of earthquake geophysical data based on big data analysis according to claim 1, characterized in that: In step S3, a machine learning algorithm is used to perform feature selection and feature transformation on the seismic geophysical data.

4. The method for detecting and warning anomalies of earthquake geophysical data based on big data analysis according to claim 1, characterized in that: In step S4, an anomaly detection algorithm based on Gaussian distribution is used to perform anomaly detection on the extracted feature parameters.

5. The method for detecting and warning anomalies of earthquake geophysical data based on big data analysis according to claim 1, characterized in that: In step S5, when establishing the interference and abnormality warning model, the model includes a prediction function and a loss function.

6. The method for detecting and warning anomalies of earthquake geophysical data based on big data analysis according to claim 1, characterized in that: In step S5, the interference and abnormal warning model is trained and optimized by combining geoelectric and geomagnetic data, deformation data, and underground fluid dynamic data using a gradient descent algorithm.

7. The method for detecting and warning anomalies of earthquake geophysical data based on big data analysis according to claim 1, characterized in that: It also includes a data visualization step to display the collected seismic geophysical data and anomaly detection results in an intuitive graphical manner.

8. Earthquake geophysical data anomaly detection and early warning system based on big data analysis, characterized by: The method for detecting and warning anomalies of seismic geophysical data based on big data analysis according to any one of claims 1 to 7 comprises: Data acquisition module: collects seismic geophysical observation data, including but not limited to geoelectric and geomagnetic data, deformation data, and underground fluid dynamic data; Data preprocessing module: cleans, integrates and normalizes the collected data to remove noise and outliers and improve data quality; Feature extraction module: extracts characteristic parameters related to interference and anomalies from the preprocessed data, including but not limited to the frequency, trend, and change amplitude of the observed data curve; Anomaly detection module: Use big data analysis technology to perform anomaly detection on the extracted feature parameters and identify abnormal data that does not conform to the normal observation data pattern; Warning generation module: Based on the results of anomaly detection and combined with the pre-established interference and anomaly warning models, it generates interference and anomaly warning information, and sends the warning information to relevant departments and personnel through the preset communication method.

9. A processor, characterized in that: The method is configured to execute the earthquake geophysical data anomaly detection and early warning method based on big data analysis according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the earthquake geophysical data anomaly detection and early warning method based on big data analysis described in any one of claims 1 to 7 is implemented.

Images