Prediction model training method and device, earthquake prediction method and device and electronic equipment

Abstract

The invention provides a prediction model training method, an earthquake prediction method and device and electronic equipment, and relates to the technical field of earthquake monitoring and earthquake prediction. The training method comprises the steps that multiple pieces of aftershock data in historical seismic waveform data of a target area are synthesized with preset noise data, and an earthquake precursor data set is obtained; intercepting a plurality of continuous waveform data containing small seismic group events from the historical seismic waveform data to obtain a random event data set; determining a noise data set by generating a white noise sequence or selecting waveform data of a plurality of noise segments of which the magnitude is below a preset seismic magnitude from historical seismic waveform data; and training the neural network by using the earthquake precursor data set, the random event data set and the noise data set to obtain an earthquake prediction model. According to the invention, the recognition precision of earthquake precursor anomalies is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of earthquake monitoring and earthquake prediction, and more specifically, to a prediction model training method, an earthquake prediction method, a device and an electronic device. Background Art

[0002] Earthquakes are caused by sudden changes in the structure of the medium in a certain local area of ​​the earth's interior, triggered by the instantaneous rupture of the underground rock structure. In terms of earthquake prevention and disaster reduction, earthquake prediction is particularly important. The basis for earthquake prediction is to understand the physical process of earthquake breeding and the changes in the physical properties and mechanical state of the crustal rock during this process. Due to the complexity of the earthquake breeding mechanism, the limitations of observation methods, and the multi-solution nature of geophysical problems, the problem of earthquake prediction cannot be solved well. Precursor phenomena provide a certain degree of feasibility for earthquake prediction, but due to the complexity of precursor phenomena, many abnormal phenomena are often not necessarily caused by earthquakes. Common earthquake precursor phenomena include: abnormal seismic activity, changes in seismic wave velocity, crustal deformation, abnormal changes in groundwater, changes in radon gas content or other chemical components in groundwater, changes in ground stress, geoelectric changes, geomagnetic changes, gravity anomalies, animal anomalies, ground sound, ground light, ground temperature anomalies, etc. Earthquake prediction has always been a global problem, especially earthquake prediction. With the development of science and technology, people have more and more means of observation data and the amount of data is increasing, but there is still a lack of an effective and stable earthquake prediction method. At present, classic earthquakes that have been successfully predicted include the Haicheng earthquake in 1975 and the Xiuyan earthquake in 1999. Earthquake waveform records contain rich information about the source, underground structure, and underground structure changes. According to the study of the successfully predicted Haicheng and Xiuyan earthquakes, an abnormal earthquake pattern of small earthquakes first slowly increased and then suddenly decreased appeared 2 to 3 days before the two major earthquakes. There are many precursors to earthquakes. One of them may be a concentration of small earthquakes in a short period of time. The number of small earthquakes first slowly increases to a certain peak value, and large-magnitude earthquakes are also distributed near the peak value. Then the seismic activity suddenly decreases, the number of small earthquakes decreases, and the magnitude decreases, followed by a large earthquake. This precursor pattern may also behave differently under different geological backgrounds. Some precursor small earthquakes have a large magnitude, such as the Haicheng earthquake and the Xiuyan earthquake foreshocks are very obvious; some precursor small earthquakes have a small magnitude, which is partially or completely submerged in the noise and difficult to identify.

[0003] Deep learning technology is not only used in knowledge-based systems, but also widely promoted in many fields such as natural language understanding, non-monotonic reasoning, machine vision, pattern recognition, data mining, etc. In addition, deep learning is also widely used in geophysics, and some even exceed traditional geophysical methods, such as the deep learning method to pick the first arrival and the traditional STA / LTA method. Therefore, a method for earthquake prediction using deep learning is urgently needed. Summary of the invention

[0004] In view of this, the present disclosure provides a prediction model training method, an earthquake prediction method, an apparatus and an electronic device.

[0005] One aspect of the present disclosure provides an earthquake prediction model training method, comprising:

[0006] Synthesizing a plurality of aftershock data in the historical earthquake waveform data of the target area with preset noise data respectively to obtain a plurality of earthquake precursor data samples with a fixed data length, and using the plurality of earthquake precursor data samples as an earthquake precursor data set;

[0007] Extracting a plurality of continuous waveform data containing small earthquake swarm events from the historical earthquake waveform data to obtain a plurality of random event samples of the fixed data length, and using the plurality of random event samples as a random event data set;

[0008] Determine a plurality of noise data samples of the fixed data length by generating a white noise sequence or selecting a plurality of noise segment waveform data with a magnitude below a preset earthquake magnitude from the historical earthquake waveform data, and use the plurality of noise data samples as a noise data set;

[0009] The earthquake precursor data set, the random event data set and the noise data set are used to train a neural network to obtain an earthquake prediction model.

[0010] According to an embodiment of the present disclosure, the training method further includes:

[0011] Performing a dimensionality reduction operation on each sample in the earthquake precursor data set, the random event data set, and the noise data set to obtain a dimensionality reduction data set;

[0012] The step of applying the earthquake precursor data set, the random event data set and the noise data set to train a neural network to obtain an earthquake prediction model includes:

[0013] The dimensionality reduction data set is used to train the neural network to obtain the earthquake prediction model.

[0014] According to an embodiment of the present disclosure, the magnitude difference between the maximum magnitude and the minimum magnitude of each earthquake precursor data sample in the earthquake precursor data set is greater than a preset magnitude.

[0015] Another aspect of the present disclosure provides an earthquake prediction method based on deep learning, comprising:

[0016] The seismic waveform data of the target area at the current moment is input into the earthquake prediction model to obtain a prediction result; the prediction result is the probability that the seismic waveform data at the current moment is an earthquake precursor, wherein the earthquake prediction model is trained using the above-mentioned earthquake prediction model training method.

[0017] According to an embodiment of the present disclosure, the prediction method further includes:

[0018] Performing a preprocessing operation on the seismic waveform data at the current moment to obtain target seismic waveform data;

[0019] The step of inputting the earthquake waveform data of the target area at the current moment into the earthquake prediction model to obtain the prediction result includes:

[0020] The target earthquake waveform data is input into the earthquake prediction model to obtain the prediction result.

[0021] According to an embodiment of the present disclosure, the preprocessing operation is performed on the seismic waveform data at the current moment to obtain the target seismic waveform data, specifically including:

[0022] Performing a de-instrumentation response operation on the seismic waveform data at the current moment;

[0023] De-noising the seismic waveform data after removing the instrument response;

[0024] The denoised seismic waveform data is subjected to dimension reduction to obtain target seismic waveform data.

[0025] Another aspect of the present disclosure provides an earthquake prediction model training device, which applies the above earthquake prediction model training method, including:

[0026] An earthquake precursor data set determination module is used to synthesize multiple aftershock data in the historical earthquake waveform data of the target area with preset noise data respectively to obtain multiple earthquake precursor data samples with fixed data length, and use the multiple earthquake precursor data samples as the earthquake precursor data set;

[0027] A random event data set determination module is used to intercept a plurality of continuous waveform data containing small earthquake group events from the historical earthquake waveform data, obtain a plurality of random event samples of the fixed data length, and use the plurality of random event samples as the random event data set;

[0028] A noise data set determination module, configured to determine a plurality of noise data samples of the fixed data length by generating a white noise sequence or selecting a plurality of noise segment waveform data with a magnitude below a preset earthquake magnitude from the historical earthquake waveform data, and use the plurality of noise data samples as the noise data set;

[0029] The training module is used to train the neural network using the earthquake precursor data set, the random event data set and the noise data set to obtain an earthquake prediction model.

[0030] Another aspect of the present disclosure provides an earthquake prediction device based on deep learning, which applies the above-mentioned earthquake prediction method based on deep learning, including:

[0031] The prediction module is used to input the earthquake waveform data of the target area at the current moment into the earthquake prediction model to obtain a prediction result; the prediction result is the probability that the earthquake waveform data at the current moment is an earthquake precursor.

[0032] Another aspect of the present disclosure provides an electronic device, comprising:

[0033] one or more processors;

[0034] a memory for storing one or more programs,

[0035] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0036] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0037] Another aspect of the present disclosure provides a computer program product, which includes computer executable instructions, and when the instructions are executed, are used to implement the method as described above.

[0038] According to the embodiments of the present disclosure, an earthquake precursor data set is obtained by synthesizing multiple aftershock data in historical earthquake waveform data with preset noise data, and multiple continuous waveform data containing small earthquake group events are intercepted from the historical earthquake waveform data to obtain a random event data set. A noise data set is obtained by generating a white noise sequence or selecting multiple noise segment waveform data with a magnitude below the preset earthquake magnitude from the historical earthquake waveform data, and a training set for training a neural network model is constructed. The earthquake prediction model obtained by training the neural network model with the training set is capable of identifying earthquake anomaly patterns in background noise, thereby at least partially overcoming the technical problem that some precursor small earthquakes have a small magnitude and are partially or completely submerged in the noise and are difficult to identify, thereby achieving the technical effect of improving the recognition accuracy of earthquake precursor anomalies. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0040] Figure 1 An exemplary system architecture to which a prediction model training method and / or an earthquake prediction method based on deep learning can be applied according to an embodiment of the present disclosure is schematically shown;

[0041] Figure 2 A flowchart of an earthquake prediction model training method according to an embodiment of the present disclosure is schematically shown;

[0042] Figure 3 A flowchart of an earthquake prediction method based on deep learning according to an embodiment of the present disclosure is schematically shown;

[0043] Figure 4 A flowchart of a preprocessing method according to an embodiment of the present disclosure is schematically shown;

[0044] Figure 5 A block diagram of an earthquake prediction model training device according to an embodiment of the present disclosure is schematically shown;

[0045] Figure 6 A block diagram of an earthquake prediction device based on deep learning according to an embodiment of the present disclosure is schematically shown;

[0046] Fig. 7A Schematically shows a schematic diagram of the east-west vibration component in the three-component seismic image data according to an embodiment of the present disclosure;

[0047] Figure 7B A schematic diagram of north-south vibration components in three-component seismic data according to an embodiment of the present disclosure is schematically shown;

[0048] Figure 7C A schematic diagram of a vertical vibration component in three-component seismic image data according to an embodiment of the present disclosure is schematically shown;

[0049] Fig. 8A Schematically shows a magnitude time diagram of an earthquake with obvious earthquake precursors according to an embodiment of the present disclosure;

[0050] Figure 8B Schematically showing a magnitude time diagram in which an earthquake precursor is drowned by noise according to an embodiment of the present disclosure;

[0051] Figure 8C Schematically showing a magnitude time diagram of an earthquake without earthquake precursors or with precursors of other modes according to an embodiment of the present disclosure;

[0052] Fig. 9A schematic block diagram of an earthquake prediction system for identifying abnormal patterns of large earthquakes in background noise based on deep learning according to an embodiment of the present disclosure is schematically shown;

[0053] Fig. 10A A schematic diagram showing the distribution of earthquake quantity and time according to an embodiment of the present disclosure is shown;

[0054] Fig. 10B A schematic diagram showing that the distribution of the number and magnitude of earthquakes according to an embodiment of the present disclosure satisfies the Gutenberg-Richter law;

[0055] Fig. 10C A schematic diagram of a small event signal according to an embodiment of the present disclosure is schematically shown;

[0056] Fig. 10D A schematic diagram of noise for synthesizing precursors according to an embodiment of the present disclosure is schematically shown;

[0057] Fig.10E Schematically illustrates a schematic diagram of a synthetic precursor according to an embodiment of the present disclosure;

[0058] Fig.11A A schematic diagram of a characteristic value curve of earthquake precursor data samples after being processed by principal component analysis according to an embodiment of the present disclosure is schematically shown;

[0059] Fig. 11B A schematic diagram of a compressed data sample after dimensionality reduction of a noise data sample according to an embodiment of the present disclosure is schematically shown;

[0060] Fig. 11C A schematic diagram of a compressed data sample after dimensionality reduction of a random event data sample according to an embodiment of the present disclosure is schematically shown;

[0061] Fig.11D A schematic diagram of compressed data samples after dimension reduction of earthquake precursor data samples according to an embodiment of the present disclosure is schematically shown;

[0062] Fig.12 The schematic diagram of the structure of the convolutional neural network according to the embodiment of the present disclosure is shown;

[0063] Fig.13A A schematic diagram of a validation set loss function curve in a model training process according to an embodiment of the present disclosure is schematically shown;

[0064] Fig. 13B A schematic diagram of a confusion matrix of a test set according to an embodiment of the present disclosure is schematically shown;

[0065] Fig.14 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0066] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0067] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0068] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0069] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0070] In the embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security, and national security.

[0071] In the embodiments of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0072] Embodiments of the present disclosure provide a prediction model training method, an earthquake prediction method, an apparatus, and an electronic device.

[0073] Figure 1The exemplary system architecture 100 to which the prediction model training method and / or the earthquake prediction method based on deep learning can be applied according to an embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0074] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0075] The user may use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only for example).

[0076] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0077] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0078] It should be noted that the prediction model training method and / or the earthquake prediction method based on deep learning provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the prediction model training system and / or the earthquake prediction system based on deep learning provided in the embodiment of the present disclosure can generally be set in the server 105. The prediction model training method and / or the earthquake prediction method based on deep learning provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Correspondingly, the prediction model training system and / or the earthquake prediction system based on deep learning provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Alternatively, the prediction model training method and / or the earthquake prediction method based on deep learning provided in the embodiments of the present disclosure may also be performed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or may also be performed by other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Accordingly, the prediction model training system and / or the earthquake prediction system based on deep learning provided in the embodiments of the present disclosure may also be provided in the first terminal device 101, the second terminal device 102, or the third terminal device 103, or may be provided in other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0079] For example, the historical seismic waveform data and / or the seismic waveform data at the current moment may be originally stored in any one of the first terminal device 101, the second terminal device 102 or the third terminal device 103 (for example, the first terminal device 101, but not limited thereto), or stored on an external storage device and may be imported into the first terminal device 101. Then, the first terminal device 101 may locally execute the prediction model training method and / or the earthquake prediction method based on deep learning provided in the embodiments of the present disclosure, or send the historical seismic waveform data and / or the seismic waveform data at the current moment to other terminal devices, servers, or server clusters, and the prediction model training method and / or the earthquake prediction method based on deep learning provided in the embodiments of the present disclosure may be executed by other terminal devices, servers, or server clusters that receive the historical seismic waveform data and / or the seismic waveform data at the current moment.

[0080] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0081] Figure 2 The flowchart of the earthquake prediction model training method according to the embodiment of the present disclosure is schematically shown.

[0082] like Figure 2 As shown, the training method 200 includes operations S201-S204:

[0083] In operation S201, a plurality of aftershock data in the historical earthquake waveform data of the target area are synthesized with preset noise data respectively to obtain a plurality of earthquake precursor data samples with a fixed data length, and the plurality of earthquake precursor data samples are used as an earthquake precursor data set.

[0084] In operation S202, a plurality of continuous waveform data containing small earthquake swarm events are intercepted from the historical earthquake waveform data to obtain a plurality of random event samples with a fixed data length, and the plurality of random event samples are used as a random event data set.

[0085] In operation S203, a plurality of noise data samples with a fixed data length are determined by generating a white noise sequence or selecting a plurality of noise segment waveform data with a magnitude below a preset earthquake magnitude from historical earthquake waveform data, and the plurality of noise data samples are used as a noise data set.

[0086] In operation S204, the earthquake precursor data set, the random event data set, and the noise data set are used to train a neural network to obtain an earthquake prediction model.

[0087] The area where earthquake precursor prediction is desired can be used as the target area, and the historical earthquake waveform data of the target area can be used to construct an earthquake precursor data set, a random event data set, and a noise data set. The earthquake precursor data set, the random event data set, and the noise data set can be used to train the neural network, thereby obtaining an earthquake prediction model for earthquake precursor prediction for the target area. For example, when predicting earthquake precursors for another area, it is necessary to use the historical earthquake waveform data of another area to construct an earthquake precursor data set, a random event data set, and a noise data set for the area, and train the neural network, thereby obtaining an earthquake prediction model for earthquake precursor prediction for the area.

[0088] When training the neural network, the training data set including the earthquake precursor data set, the random event data set and the noise data set can be divided into a training set, a validation set and a test set, and the training set, the validation set and the test set are divided according to a preset ratio, and optionally, the preset ratio can be divided according to 8:1:1, etc. Then, the accuracy and / or recall rate of the trained neural network can be calculated by inputting the test set into the trained neural network according to the output of the trained neural network. When the accuracy and / or recall rate of the trained neural network meets the preset requirements, the trained neural network that meets the preset requirements is used as an earthquake prediction model. For example, when the accuracy rate reaches more than 90%, it is considered that the trained neural network can be used as an earthquake prediction model.

[0089] Before training the neural network, the earthquake precursor data set, the random event data set and the noise data set can be preprocessed, for example, each sample in the earthquake precursor data set, the random event data set and the noise data set can be subjected to dimensionality reduction operation to obtain a dimensionality reduction data set. Then the dimensionality reduction data set is applied to train the neural network. Since the data dimension of the dimensionality reduction data set is reduced relative to the earthquake precursor data set, the random event data set and the noise data set, the calculation speed of the neural network training is accelerated, and the features contained in the dimensionality reduction data set are more prominent, thereby improving the prediction accuracy of the trained neural network for earthquake precursors.

[0090] When reducing the dimension of earthquake precursor data sets, random event data sets and noise data sets, the principal component analysis method can be used, so that the dimension-reduced data sets can contain more features. For the data in earthquake precursor data sets, random event data sets and noise data sets, multiple data formats can be adopted, such as single-station single component, single-station three-component, multi-station single component, multi-station three-component, etc.

[0091] Other methods can also be used to improve the prediction accuracy of the neural network model, for example, the magnitude difference between the maximum magnitude and the minimum magnitude of each earthquake precursor data sample in the earthquake precursor data set is set to be greater than the preset magnitude, or the relationship between the earthquake precursor data sample and time can be described by the Chi-squared distribution. Taking the setting of the preset magnitude as an example, the preset magnitude can be selected according to the actual situation, and the preset magnitude can be selected as 2, the magnitude range is 0 to 3, -1 to 2, divided according to the span of 3, or the preset magnitude is set to 3. This setting method makes the data size in the earthquake precursor data sample change significantly, which is conducive to the neural network to better learn the characteristics of earthquake precursors during the training process, thereby improving the prediction accuracy of the trained neural network for earthquake precursors.

[0092] In the process of obtaining the random event data set, small earthquake group events and data with frequent small earthquakes but no large earthquakes in a period of time can be selected as random event samples. In the process of determining the noise data set, the noise data sample can be selected from the noise or white noise in the seismic waveform data of the study area, or a combination of noise and white noise. For example, the noise data sample in the seismic waveform data selects the noise level magnitude below ML1. A broad random event data set, noise data set, and earthquake precursor data set can generalize the ability of the earthquake prediction model to identify earthquake precursors.

[0093] The fixed data length values ​​of earthquake precursor data samples, random event samples and noise data samples can be set according to actual needs. For example, the fixed data length can be one day, several hours, or several days.

[0094] The disclosed embodiments can use neural networks to search for the learned probability of earthquake precursors after obtaining input earthquake data, and predict the probability of a major earthquake in the next few days. This can be applied to the prediction of natural earthquakes and induced earthquakes. Combined with existing ground stress, hydrological information, etc., it can have certain guiding significance for deciding whether to issue an earthquake warning.

[0095] Figure 3 A flowchart of an earthquake prediction method based on deep learning according to an embodiment of the present disclosure is schematically shown.

[0096] like Figure 3 As shown, the prediction method 300 includes operation S301:

[0097] In operation S301, the seismic waveform data of the target area at the current moment is input into the earthquake prediction model to obtain a prediction result; the prediction result is the probability that the seismic waveform data at the current moment is an earthquake precursor, wherein the earthquake prediction model is trained using the earthquake prediction model training method of the embodiment of the present disclosure.

[0098] Optionally, the seismic waveform data at the current moment is preprocessed to obtain target seismic waveform data, so that when earthquake precursor prediction is performed on the seismic waveform data at the current moment, the target seismic waveform data is input into an earthquake prediction model to obtain a prediction result.

[0099] Figure 4 The flowchart of the preprocessing method according to the embodiment of the present disclosure is schematically shown.

[0100] like Figure 4 As shown, according to an embodiment of the present disclosure, a preprocessing method 210 for performing a preprocessing operation on the seismic waveform data at the current moment to obtain target seismic waveform data includes operations S211-S213:

[0101] In operation S211, the seismic waveform data at the current moment is subjected to an instrument response removal operation.

[0102] In operation S212, the seismic waveform data after removing the instrument response is denoised.

[0103] In operation S213, the denoised seismic waveform data is subjected to dimension reduction to obtain target seismic waveform data.

[0104] There are many ways to perform preprocessing operations. You can choose to perform any one or more of the preprocessing operations such as instrument response removal, denoising, and data dimension reduction on the seismic waveform data at the current moment. You can also perform denoising first, then instrument response removal, and finally data dimension reduction. By removing the instrument response operation, the defect of the deviation of the prediction results caused by the different acquisition instruments between the seismic waveform data at the current moment and the training data set of the seismic prediction model can be overcome; by the denoising operation, the problem of inaccurate prediction results caused by the mixed noise of the seismic waveform data at the current moment can be overcome; by the data dimension reduction operation, the calculation time of the seismic prediction model is reduced, and the efficiency of the seismic prediction model in outputting the prediction results is improved.

[0105] Figure 5 A block diagram of an earthquake prediction model training device according to an embodiment of the present disclosure is schematically shown.

[0106] like Figure 5 As shown, the training device 400 includes an earthquake precursor data set determination module 401, a random event data set determination module 402, a noise data set determination module 403 and a training module 404.

[0107] The earthquake precursor data set determination module 401 is used to synthesize multiple aftershock data in the historical earthquake waveform data of the target area with preset noise data respectively to obtain multiple earthquake precursor data samples with fixed data length, and use the multiple earthquake precursor data samples as the earthquake precursor data set.

[0108] The random event data set determination module 402 is used to extract a plurality of continuous waveform data containing small earthquake swarm events from the historical earthquake waveform data, obtain a plurality of random event samples with a fixed data length, and use the plurality of random event samples as the random event data set.

[0109] The noise data set determination module 403 is used to determine multiple noise data samples with fixed data length by generating a white noise sequence or selecting multiple noise segment waveform data with magnitude below a preset earthquake magnitude from historical earthquake waveform data, and use the multiple noise data samples as the noise data set.

[0110] The training module 404 is used to train the neural network using the earthquake precursor data set, the random event data set and the noise data set to obtain an earthquake prediction model.

[0111] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging circuits, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0112] For example, any multiple of the earthquake precursor data set determination module 401, the random event data set determination module 402, the noise data set determination module 403, and the training module 404 can be combined in one module / unit / subunit for implementation, or any one of the modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functions of one or more of these modules / units / subunits can be combined with at least part of the functions of other modules / units / subunits and implemented in one module / unit / subunit. According to an embodiment of the present disclosure, at least one of the earthquake precursor data set determination module 401, the random event data set determination module 402, the noise data set determination module 403, and the training module 404 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware, and firmware, or by a suitable combination of any of them. Alternatively, at least one of the earthquake precursor dataset determination module 401, the random event dataset determination module 402, the noise dataset determination module 403 and the training module 404 can be at least partially implemented as a computer program module, which can perform corresponding functions when executed.

[0113] Figure 6 A block diagram of an earthquake prediction device based on deep learning according to an embodiment of the present disclosure is schematically shown.

[0114] like Figure 6 As shown, the prediction device 500 includes a prediction module 501 .

[0115] The prediction module 501 is used to input the earthquake waveform data of the target area at the current moment into the earthquake prediction model to obtain a prediction result; the prediction result is the probability that the earthquake waveform data at the current moment is an earthquake precursor.

[0116] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging circuits, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0117] For example, the prediction module 501 can be implemented in one module / unit / subunit, or one of the modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functions of one or more of these modules / units / subunits can be combined with at least part of the functions of other modules / units / subunits and implemented in one module / unit / subunit. According to an embodiment of the present disclosure, the prediction module 501 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, the prediction module 501 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0118] It should be noted that the earthquake prediction model training device part in the embodiments of the present disclosure corresponds to the earthquake prediction model training method part in the embodiments of the present disclosure, and the description of the earthquake prediction model training device part specifically refers to the earthquake prediction model training method part. In addition, the earthquake prediction device part based on deep learning in the embodiments of the present disclosure corresponds to the earthquake prediction method part based on deep learning in the embodiments of the present disclosure, and the description of the earthquake prediction device part based on deep learning specifically refers to the earthquake prediction method part based on deep learning, which will not be repeated here.

[0119] Fig. 7A Schematically shows a schematic diagram of the east-west vibration component in the three-component seismic image data according to an embodiment of the present disclosure; Figure 7B A schematic diagram of north-south vibration components in three-component seismic data according to an embodiment of the present disclosure is schematically shown; Figure 7C A schematic diagram of the vertical vibration component in the three-component seismic data according to an embodiment of the present disclosure is shown; Fig. 7A , Figure 7B and Figure 7C In the figure, the horizontal axis is relative time (seconds), the vertical axis is the speed of the earth medium vibration at the location of the seismograph, the station location is 31.48°N, 103.60°E, the waveform length is 2 minutes, Fig. 7A In the above figure, BHE stands for Broadband High-Gain E-component waveform, which refers to the broadband high-gain eastward component waveform; Figure 7B In the above, BHN stands for Broadband High-Gain N-component waveform, which refers to the broadband high-gain north component waveform; Figure 7C In the figure, BHZ stands for Broadband High-Gain Z-component waveform, which refers to the broadband high-gain Z-component waveform.

[0120] Fig. 8A Schematically shows a magnitude time diagram of an earthquake with obvious earthquake precursors according to an embodiment of the present disclosure; Figure 8B Schematically showing a magnitude time diagram in which an earthquake precursor is drowned by noise according to an embodiment of the present disclosure; Figure 8C The schematic diagram shows the magnitude time diagram of earthquakes without earthquake precursors or with other precursors according to the embodiment of the present disclosure; there are three states of earthquake precursors: obvious earthquake precursors, earthquake precursors drowned in noise, no earthquake precursors or other unidentified earthquake precursors. Fig. 8A As shown in Figure 2, the magnitude signal is significantly higher than the noise, which is a clear sign of an earthquake. Figure 8BAs shown in Figure 2, affected by different geological backgrounds, the precursor signals of some earthquakes are weak, and the effective precursors are submerged in the noise, that is, the magnitude signal is lower than the noise signal; Figure 8C Situations where there are no earthquake precursors or where there are earthquake precursors that have never been identified are shown.

[0121] Fig. 9 The schematic block diagram of an earthquake prediction system for identifying abnormal patterns of large earthquakes in background noise based on deep learning, which is composed of an earthquake prediction model training device 400 and an earthquake prediction device 500 based on deep learning according to an embodiment of the present disclosure, is schematically shown; the system 900 includes: a training part and a working part. The training part includes: a seismic map data set 910, which is used to construct an earthquake precursor data set, a random event data set and a noise data set; a data compression device 930, which is used to pre-process the seismic map data set 910, reduce the amount of data while retaining the main information of the data; the neural network model 940 is trained using the dimension reduction data set output by the data compression device 930, and the trained network model can be distributed on a remote server or distributed storage. The working part includes: the input device 920 can be a data interface, for example, it can be connected to the output device or communication interface of a single or multiple seismic monitoring stations to receive seismic map records of seismic events generated from a single or multiple seismic monitoring stations. The input device 120 can also include a user interface such as a keyboard, a touch screen, etc., and the user or operator can input system settings, predetermined conditions, etc. through the input device 120 to control and manage the operation of the system. The input device 120 may be implemented in any appropriate structure or form. The input device 120 is used to input the seismic waveform data of the station obtained in real time from the seismic network data stream, and the seismic waveform data may contain earthquake precursors, random events or noise, etc.; the seismic waveform data is input into the data compression device 930 to obtain the target seismic waveform data, and the target seismic waveform data is input into the trained neural network model 940 to obtain the probability that the target seismic waveform data belongs to an earthquake precursor.

[0122] System 900 may also include a decision device (not shown) that can comprehensively evaluate the possibility of a destructive earthquake occurring in the near future based on seismic waveform data by comparing other recent earthquake monitoring parameters, such as stress changes, velocity changes, etc.

[0123] Fig. 10A A schematic diagram showing the distribution of earthquake quantity and time according to an embodiment of the present disclosure is shown; Fig. 10B A schematic diagram showing that the distribution of the number and magnitude of earthquakes according to an embodiment of the present disclosure satisfies the Gutenberg-Richter law; Fig. 10C A schematic diagram of a small event signal according to an embodiment of the present disclosure is schematically shown; Fig. 10D A schematic diagram of noise for synthesizing precursors according to an embodiment of the present disclosure is schematically shown; Fig.10E A schematic diagram of a synthetic precursor according to an embodiment of the present disclosure is schematically shown. Fig. 10A , Fig. 10B , Fig. 10C , Fig. 10D and Fig.10E The process of synthesizing earthquake precursor datasets is demonstrated. The constructed earthquake precursor datasets, random event datasets, and noise datasets conform to the Gutenberg-Richter law of magnitude distribution and the Chi-squared law of earthquake quantity distribution. The length of the synthesized data can be 1 to 15 days, and a data sample can contain data of three components from multiple stations at the same time. Fig. 10A The number and time of earthquakes are Chi-squared distributed. Fig. 10B The number and magnitude of earthquakes satisfy the Gutenberg-Richter law distribution. The description of unrecognized earthquake precursors is not limited to the Chi-squared distribution. Given the time range, magnitude range, noise level and other parameters of earthquake precursor data synthesis, an earthquake precursor data set can be obtained. Fig. 10D The noise shown is similar to that of the filter. Fig. 10C The earthquake waveform data shown in the figure are superimposed according to the synthesized earthquake precursor catalog to obtain a Fig.10E The earthquake precursor signal shown is used to obtain an earthquake precursor data set by transforming the parameters and data values ​​of the earthquake precursor signal.

[0124] Fig.11A A schematic diagram of a characteristic value curve of earthquake precursor data samples after being processed by principal component analysis according to an embodiment of the present disclosure is schematically shown; Fig. 11B A schematic diagram of a compressed data sample after dimensionality reduction of a noise data sample according to an embodiment of the present disclosure is schematically shown; Fig. 11C A schematic diagram of a compressed data sample after dimensionality reduction of a random event data sample according to an embodiment of the present disclosure is schematically shown; Fig.11D Schematically shows a schematic diagram of compressed data samples after dimension reduction of earthquake precursor data samples according to an embodiment of the present disclosure; Fig.11A , Fig. 11B , Fig. 11C and Fig.11D The figure shows the schematic diagram after different preprocessing operations are performed on the earthquake precursor dataset, random event dataset and noise dataset.

[0125] Fig.12 The structure diagram of the convolutional neural network according to the embodiment of the present disclosure is schematically shown; Fig.12 As shown in the figure, the convolutional neural network has three convolutional layers, four fully connected layers and a pooling layer, among which the convolution kernel size is selected as 5×5.

[0126] Fig.13AA schematic diagram of a validation set loss function curve in a model training process according to an embodiment of the present disclosure is schematically shown; Fig. 13B The confusion matrix diagram of the test set according to the embodiment of the present disclosure is schematically shown. Fig.13A and Fig. 13B As shown in the figure, the neural network constructed by training the training set data is continuously adjusted according to the test results of the validation set to optimize the parameters of the network structure and other parameters of the model. The trained neural network is tested with the data of the test set. From the confusion matrix, it can be seen that the recall rate and accuracy of each indicator have reached a certain level. The feasibility of this method for synthetic data is verified.

[0127] Fig.14 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Fig.14 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0128] like Fig.14 As shown, the electronic device 1400 according to an embodiment of the present disclosure includes a processor 1401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1402 or a program loaded from a storage part 1408 to a random access memory (RAM) 1403. The processor 1401 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1401 may also include an onboard memory for caching purposes. The processor 1401 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0129] In RAM 1403, various programs and data required for the operation of electronic device 1400 are stored. Processor 1401, ROM 1402 and RAM 1403 are connected to each other through bus 1404. Processor 1401 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 1402 and / or RAM 1403. It should be noted that the program can also be stored in one or more memories other than ROM 1402 and RAM 1403. Processor 1401 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0130] According to an embodiment of the present disclosure, the electronic device 1400 may further include an input / output (I / O) interface 1405, which is also connected to the bus 1404. The electronic device 1400 may further include one or more of the following components connected to the input / output (I / O) interface 1405: an input portion 1406 including a keyboard, a mouse, etc.; an output portion 1407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 1408 including a hard disk, etc.; and a communication portion 1409 including a network interface card such as a LAN card, a modem, etc. The communication portion 1409 performs communication processing via a network such as the Internet. A drive 1410 is also connected to the input / output (I / O) interface 1405 as needed. A removable medium 1411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1410 as needed, so that a computer program read therefrom is installed into the storage portion 1408 as needed.

[0131] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1409, and / or installed from the removable medium 1411. When the computer program is executed by the processor 1401, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0132] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0133] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0134] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 1402 and / or the RAM 1403 described above and / or one or more memories other than the ROM 1402 and the RAM 1403 .

[0135] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, which contains program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the earthquake prediction model training method and / or the earthquake prediction method based on deep learning provided by the embodiment of the present disclosure.

[0136] When the computer program is executed by the processor 1401, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0137] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 1409, and / or installed from the removable medium 1411. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0138] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0139] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0140] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for training an earthquake prediction model, characterized in that: The training method comprises: Synthesizing a plurality of aftershock data in the historical earthquake waveform data of the target area with preset noise data respectively to obtain a plurality of earthquake precursor data samples with a fixed data length, and using the plurality of earthquake precursor data samples as an earthquake precursor data set; Extracting a plurality of continuous waveform data containing small earthquake swarm events from the historical earthquake waveform data to obtain a plurality of random event samples of the fixed data length, and using the plurality of random event samples as a random event data set; Determine a plurality of noise data samples of the fixed data length by generating a white noise sequence or selecting a plurality of noise segment waveform data with a magnitude below a preset earthquake magnitude from the historical earthquake waveform data, and use the plurality of noise data samples as a noise data set; The earthquake precursor data set, the random event data set and the noise data set are used to train a neural network to obtain an earthquake prediction model.

2. The earthquake prediction model training method according to claim 1, characterized in that: The training method further comprises: performing a dimensionality reduction operation on each sample in the earthquake precursor data set, the random event data set and the noise data set to obtain a dimensionality reduction data set; The step of applying the earthquake precursor data set, the random event data set and the noise data set to train a neural network to obtain an earthquake prediction model includes: The dimensionality reduction data set is used to train the neural network to obtain the earthquake prediction model.

3. The earthquake prediction model training method according to claim 1, characterized in that: The magnitude difference between the maximum magnitude and the minimum magnitude of each earthquake precursor data sample in the earthquake precursor data set is greater than a preset magnitude.

4. A method for earthquake prediction based on deep learning, characterized in that: The earthquake prediction method comprises: The seismic waveform data of the target area at the current moment is input into the earthquake prediction model to obtain a prediction result; the prediction result is the probability that the seismic waveform data at the current moment is an earthquake precursor, wherein the earthquake prediction model is trained using the earthquake prediction model training method according to any one of claims 1 to 3.

5. The earthquake prediction method based on deep learning according to claim 4, characterized in that: The prediction method further comprises: Performing a preprocessing operation on the seismic waveform data at the current moment to obtain target seismic waveform data; The step of inputting the earthquake waveform data of the target area at the current moment into the earthquake prediction model to obtain the prediction result includes: The target earthquake waveform data is input into the earthquake prediction model to obtain the prediction result.

6. The earthquake prediction method based on deep learning according to claim 5, characterized in that: The preprocessing operation is performed on the seismic waveform data at the current moment to obtain target seismic waveform data, specifically including: Performing a de-instrumentation response operation on the seismic waveform data at the current moment; De-noising the seismic waveform data after removing the instrument response; The denoised seismic waveform data is subjected to dimension reduction to obtain target seismic waveform data.

7. An earthquake prediction model training device, characterized in that: The earthquake prediction model training method according to any one of claims 1 to 3 is applied, wherein the training device comprises: An earthquake precursor data set determination module is used to synthesize multiple aftershock data in the historical earthquake waveform data of the target area with preset noise data respectively to obtain multiple earthquake precursor data samples with fixed data length, and use the multiple earthquake precursor data samples as the earthquake precursor data set; A random event data set determination module is used to intercept a plurality of continuous waveform data containing small earthquake group events from the historical earthquake waveform data, obtain a plurality of random event samples of the fixed data length, and use the plurality of random event samples as the random event data set; A noise data set determination module, configured to determine a plurality of noise data samples of the fixed data length by generating a white noise sequence or selecting a plurality of noise segment waveform data with a magnitude below a preset earthquake magnitude from the historical earthquake waveform data, and use the plurality of noise data samples as the noise data set; The training module is used to train the neural network using the earthquake precursor data set, the random event data set and the noise data set to obtain an earthquake prediction model.

8. An earthquake prediction device based on deep learning, characterized in that: The earthquake prediction method based on deep learning according to any one of claims 4 to 6 is applied, wherein the earthquake prediction device comprises: The prediction module is used to input the earthquake waveform data of the target area at the current moment into the earthquake prediction model to obtain a prediction result; the prediction result is the probability that the earthquake waveform data at the current moment is an earthquake precursor.

9. An electronic device, comprising: one or more processors; a memory for storing one or more programs, Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any one of claims 1 to 3 and / or claims 4 to 6.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the method according to any one of claims 1 to 3 and / or claims 4 to 6.

Images