Spatial positioning method and device based on seismic waves and acoustic waves

Abstract

The present invention provides a method and device for spatial positioning based on seismic waves and sound waves, wherein the method comprises: obtaining a seismic trace data set and a sound wave data set composed of continuous data, dividing them respectively and inputting them into a first sub-model and a second sub-model for training, thereby obtaining an earthquake spatial positioning prediction model, and using the earthquake spatial positioning prediction model to predict current data to obtain spatial positioning information of the current earthquake. Beneficial effects of the present invention: Since the earthquake spatial positioning prediction model combines seismic wave and sound wave data and uses advanced machine learning models for training and prediction, it can achieve accurate spatial positioning of earthquakes and provide strong support for earthquake monitoring and early warning. It can improve the accuracy and reliability of earthquake positioning and contribute to reducing the impact of earthquake disasters.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a spatial positioning method and device based on seismic waves and sound waves. Background Art

[0002] Earthquakes are common disasters in nature. They are often extremely destructive and pose a serious threat to human society. In order to mitigate the impact of earthquake disasters, earthquake monitoring and early warning technologies are particularly important. Traditional earthquake monitoring mainly relies on the collection and analysis of seismic wave data, and infers the occurrence, location and scale of earthquakes through the propagation characteristics of seismic waves. However, a single seismic wave data may not provide enough information in some cases, especially in areas with complex geological structures. The propagation path and speed of seismic waves may be affected by many factors, resulting in limited positioning accuracy.

[0003] In recent years, with the continuous development of acoustic wave monitoring technology, people have begun to try to combine acoustic wave data with seismic wave data to locate earthquakes. The propagation characteristics of acoustic waves in underground media are different from those of seismic waves, and they can provide supplementary information that seismic waves cannot obtain. By collecting seismic wave and acoustic wave data at the same time and conducting joint analysis, it is expected to improve the accuracy and reliability of earthquake location. At present, there is no method to combine seismic wave and acoustic wave data for earthquake location. Summary of the invention

[0004] The main purpose of the present invention is to provide a spatial positioning method and device based on seismic waves and acoustic waves, aiming to solve the problem that single seismic wave data may not provide sufficient information in some cases.

[0005] The present invention provides a spatial positioning method based on seismic waves and acoustic waves, comprising:

[0006] S1: Acquire the seismic trace data set and acoustic wave data set composed of continuous data within a period of time, as well as the corresponding spatial positioning information;

[0007] S2: matching the seismic trace data set and the acoustic wave data set in time order, and dividing the seismic trace data set into n seismic trace data subsets and the acoustic wave data set into n acoustic wave data subsets according to a preset segmentation method;

[0008] S3: inputting the n seismic trace data subsets and the n acoustic wave data subsets into the first sub-model and the second sub-model of the preset earthquake spatial positioning prediction model respectively, and inputting the spatial positioning information into the output layer of the preset earthquake spatial positioning prediction model for training; wherein the preset earthquake prediction model comprises a first sub-model, a second sub-model and an output layer, the neurons of the respective intermediate layers of the first sub-model and the second sub-model are cross-connected in sequence, and the first sub-model and the second sub-model are connected to the output layer respectively;

[0009] S4: Acquire multiple sets of seismic trace data sets and acoustic wave data sets, as well as corresponding spatial positioning information, and repeat steps S2-S3 to obtain a trained earthquake spatial positioning prediction model;

[0010] S5: Acquire a real-time seismic trace data set and a real-time acoustic wave data set consisting of continuous data in the current time period;

[0011] S6: dividing the real-time seismic trace data set and the real-time acoustic wave data set into n real-time seismic trace data subsets and n real-time acoustic wave data subsets according to a preset division method;

[0012] S7: Input the n real-time seismic trace data subsets and the n real-time acoustic wave data subsets into the earthquake spatial positioning prediction model to obtain the spatial positioning information of the current earthquake.

[0013] Further, the step S4 of acquiring multiple sets of seismic trace data sets and acoustic wave data sets, and corresponding spatial positioning information, and repeating steps S2-S3 to obtain a trained earthquake spatial positioning prediction model includes:

[0014] S401: Obtaining the relationship function between the seismic trace data set and the acoustic wave data set in the neurons of the first sub-model and the second sub-model to obtain the first relationship function f(x) corresponding to each neuron in the first sub-model and the second relationship function g(x) corresponding to each neuron in the second sub-model;

[0015] S402: According to each of the first relationship functions, each of the second relationship functions and the corresponding spatial positioning information, the first sub-model and the second sub-model are trained by supervised learning to obtain the trained first sub-model and the second sub-model, and then to obtain the trained earthquake spatial positioning prediction model.

[0016] Furthermore, the step S401 of obtaining the relationship function between the seismic trace data set and the acoustic wave data set in the neurons of the first sub-model and the second sub-model to obtain the first relationship function f(x) corresponding to each neuron in the first sub-model and the second relationship function g(x) corresponding to each neuron in the second sub-model includes:

[0017] S4021: The first sub-model is obtained by formula , the first relationship function f(x) corresponding to the seismic data subset and the acoustic wave data subset is obtained, and the second sub-model is obtained by formula , the second relationship function g(x) corresponding to the seismic trace data subset and the acoustic wave data subset is obtained; where, , , represents a calculation function based on parameter x, represents a calculation function based on parameter x, represents the hth seismic trace data subset, represents the kth acoustic wave data subset, represents the seismic trace data subset in the h+ith temporary data set, represents the seismic trace data subset in the h+i+1th temporary data set, represents the h+i-1th seismic trace data subset, represents the k+jth subset of acoustic wave data, represents the k+j+1th acoustic wave data subset, Represents the k+j-1th acoustic wave data subset.

[0018] Furthermore, in the step S1 of acquiring a seismic trace data set and an acoustic wave data set composed of continuous data within a period of time, and corresponding spatial positioning information, the step of acquiring the seismic trace data set includes:

[0019] S101: Obtain the original data set of seismic gathers;

[0020] S102: Performing data consistency processing and anisotropy correction processing on the original data set of the seismic trace gather to obtain the seismic trace data set.

[0021] Furthermore, in the step S1 of acquiring a seismic trace data set and an acoustic wave data set composed of continuous data within a period of time, and corresponding spatial positioning information, the step of acquiring the seismic trace data set includes:

[0022] S111: Get the original data set of seismic gathers;

[0023] S112: Determine whether there are seismic trace data collected in multiple directions in the original data set of the seismic trace gather;

[0024] S113: If there are seismic trace data collected in multiple directions and orientations, obtain a preset weight for each orientation;

[0025] S114: performing weighted processing on each seismic trace data according to the preset weight to obtain a weighted seismic trace data set.

[0026] The present invention also provides a spatial positioning device based on seismic waves and acoustic waves, comprising:

[0027] A first acquisition module is used to instruct the implementation of step S1: acquiring a seismic trace data set and an acoustic wave data set composed of continuous data within a period of time, and corresponding spatial positioning information;

[0028] A matching module, used for instructing to implement step S2: matching the seismic trace data set and the acoustic wave data set in time order, and dividing the seismic trace data set into n seismic trace data subsets and the acoustic wave data set into n acoustic wave data subsets according to a preset segmentation method;

[0029] The first input module is used to instruct the implementation of step S3: inputting the n seismic trace data subsets and the n acoustic wave data subsets into the first sub-model and the second sub-model of the preset earthquake spatial positioning prediction model respectively, and inputting the spatial positioning information into the output layer of the preset earthquake spatial positioning prediction model for training; wherein the preset earthquake prediction model includes a first sub-model, a second sub-model and an output layer, the neurons of the respective intermediate layers of the first sub-model and the second sub-model are cross-connected in sequence, and the first sub-model and the second sub-model are connected to the output layer respectively;

[0030] The second acquisition module is used to instruct the implementation of step S4: acquiring multiple sets of seismic trace data sets and acoustic wave data sets, as well as corresponding spatial positioning information, and repeating steps S2-S3 to obtain a trained earthquake spatial positioning prediction model;

[0031] A third acquisition module is used to instruct the implementation of step S5: acquiring a real-time seismic trace data set and a real-time acoustic wave data set composed of continuous data in a current time period;

[0032] A segmentation module, used for instructing to implement step S6: segmenting the real-time seismic trace data set and the real-time acoustic wave data set into n real-time seismic trace data subsets and n real-time acoustic wave data subsets according to a preset segmentation method;

[0033] The second input module is used to instruct the implementation of step S7: inputting the n real-time seismic trace data subsets and the n real-time acoustic wave data subsets into the earthquake spatial positioning prediction model to obtain the spatial positioning information of the current earthquake.

[0034] Furthermore, the second acquisition module includes:

[0035] A calculation submodule, used for instructing to implement step S401: obtaining the relationship function between the seismic trace data set and the acoustic wave data set in the neurons of the first submodel and the second submodel, and obtaining the first relationship function f(x) corresponding to each neuron in the first submodel and the second relationship function g(x) corresponding to each neuron in the second submodel;

[0036] The training submodule is used to instruct the implementation step S402: the first sub-model and the second sub-model are trained in a supervised learning manner according to each of the first relationship functions, each of the second relationship functions and the corresponding spatial positioning information, so as to obtain the trained first sub-model and the second sub-model, and then obtain the trained earthquake spatial positioning prediction model.

[0037] Furthermore, the calculation submodule includes:

[0038] A calculation unit is used to instruct the implementation of step S4021: the first sub-model is calculated by formula , the first relationship function f(x) corresponding to the seismic data subset and the acoustic wave data subset is obtained, and the second sub-model is obtained by formula , the second relationship function g(x) corresponding to the seismic trace data subset and the acoustic wave data subset is obtained; where, , , represents a calculation function based on parameter x, represents a calculation function based on parameter x, represents the hth seismic trace data subset, represents the kth acoustic wave data subset, represents the seismic trace data subset in the h+ith temporary data set, represents the seismic trace data subset in the h+i+1th temporary data set, represents the h+i-1th seismic trace data subset, represents the k+jth subset of acoustic wave data, represents the k+j+1th acoustic wave data subset, Represents the k+j-1th geoacoustic wave data subset.

[0039] Furthermore, the first acquisition module includes:

[0040] The seismic gather original data set acquisition submodule is used to instruct the implementation of step S101: acquiring the seismic gather original data set;

[0041] The seismic trace gather original data set processing submodule is used to instruct the implementation of step S102: performing data consistency processing and anisotropy correction processing on the seismic trace gather original data set to obtain the seismic trace data set.

[0042] Furthermore, the first acquisition module includes:

[0043] The original data set acquisition submodule is used to instruct the implementation of step S111: acquiring the original data set of the seismic gather;

[0044] The original data set judgment submodule is used to instruct the implementation of step S112: judging whether there are seismic trace data collected in multiple directions in the original data set of the seismic trace gather;

[0045] The weight acquisition submodule is used to instruct the implementation of step S113: if there are seismic trace data collected in multiple directions and orientations, then the preset weight of each orientation is obtained;

[0046] The weighted processing submodule is used to instruct the implementation of step S114: weighted processing is performed on each seismic trace data according to the preset weight to obtain a weighted seismic trace data set.

[0047] The beneficial effects of the present invention are as follows: by acquiring a seismic trace data set and an acoustic wave data set composed of continuous data, the data sets are divided and input into the first sub-model and the second sub-model for training, an earthquake spatial positioning prediction model is obtained, and the earthquake spatial positioning prediction model is used to predict the current data to obtain the spatial positioning information of the current earthquake. Since the earthquake spatial positioning prediction model combines seismic wave and acoustic wave data and uses advanced machine learning models for training and prediction, it can realize the precise spatial positioning of earthquakes and provide strong support for earthquake monitoring and early warning. The accuracy and reliability of earthquake positioning can be improved, and contributions can be made to reducing the impact of earthquake disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic flow chart of a spatial positioning method based on seismic waves and acoustic waves according to an embodiment of the present invention;

[0049] Figure 2 It is a schematic block diagram of the structure of a spatial positioning device based on seismic waves and acoustic waves according to an embodiment of the present invention;

[0050] Figure 3 A schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0051] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly. The connection can be a direct connection or an indirect connection.

[0054] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone.

[0055] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0056] Reference Figure 1 The present invention proposes a spatial positioning method based on seismic waves and acoustic waves, comprising:

[0057] S1: Acquire the seismic trace data set and acoustic wave data set composed of continuous data within a period of time, as well as the corresponding spatial positioning information;

[0058] S2: matching the seismic trace data set and the acoustic wave data set in time order, and dividing the seismic trace data set into n seismic trace data subsets and the acoustic wave data set into n acoustic wave data subsets according to a preset segmentation method;

[0059] S3: inputting the n seismic trace data subsets and the n acoustic wave data subsets into the first sub-model and the second sub-model of the preset earthquake spatial positioning prediction model respectively, and inputting the spatial positioning information into the output layer of the preset earthquake spatial positioning prediction model for training; wherein the preset earthquake prediction model comprises a first sub-model, a second sub-model and an output layer, the neurons of the respective intermediate layers of the first sub-model and the second sub-model are cross-connected in sequence, and the first sub-model and the second sub-model are connected to the output layer respectively;

[0060] S4: Acquire multiple sets of seismic trace data sets and acoustic wave data sets, as well as corresponding spatial positioning information, and repeat steps S2-S3 to obtain a trained earthquake spatial positioning prediction model;

[0061] S5: Acquire a real-time seismic trace data set and a real-time acoustic wave data set consisting of continuous data in the current time period;

[0062] S6: dividing the real-time seismic trace data set and the real-time acoustic wave data set into n real-time seismic trace data subsets and n real-time acoustic wave data subsets according to a preset division method;

[0063] S7: Input the n real-time seismic trace data subsets and the n real-time acoustic wave data subsets into the earthquake spatial positioning prediction model to obtain the spatial positioning information of the current earthquake.

[0064] As described in the above step S1, a seismic trace data set and an acoustic wave data set consisting of continuous data within a period of time, and corresponding spatial positioning information are obtained, wherein the seismic trace data and the acoustic wave data can be collected by preset sensors, and the sensor for collecting the seismic trace data can be a seismic detector, specifically a three-component detector (capable of simultaneously detecting seismic waves in the vertical direction, along the survey line direction and perpendicular to the survey line direction), and the sensor for collecting the acoustic wave data can be one or more of an acoustic wave sensor, an ultrasonic sensor and a distributed optical fiber acoustic wave sensor. Specifically, within a period of time, multiple collection time points can be set to obtain seismic trace data and acoustic wave data at each time point, and the seismic trace data at each time point includes three-dimensional seismic sub-data.

[0065] As described in the above step S2, the seismic trace data set and the acoustic wave data set are matched in time order, and the seismic trace data set is divided into n seismic trace data subsets and the acoustic wave data set is divided into n acoustic wave data subsets according to a preset segmentation method. It should be noted that the n divided subsets need to correspond to the neurons of the subsequent sub-models, that is, the first sub-model and the second sub-model both have n neurons. As for the segmentation method, the data can be split or merged, that is, if the number of data is greater than n, the data can be merged. If the number of data is less than n, the two adjacent data can be averaged and the new data obtained can be filled to make the final number n.

[0066] As described in step S3 above, the n seismic trace data subsets and the n acoustic wave data subsets are respectively input into the first sub-model and the second sub-model in the preset earthquake spatial positioning prediction model, and the spatial positioning information is input into the output layer of the preset earthquake spatial positioning prediction model for training; wherein the preset earthquake prediction model includes the first sub-model, the second sub-model and the output layer, the neurons of the respective intermediate layers of the first sub-model and the second sub-model are cross-connected in sequence, and the first sub-model and the second sub-model are respectively connected to the output layer. That is, a sample data is generated for training the first sub-model and the second sub-model. It should be noted that the neurons of the first sub-model are connected in sequence, the number of neurons in the first sub-model is the same as the number of neurons in the second sub-model, the neurons in the second verification sub-module are connected in sequence, and the neurons of the first sub-model are connected to the neurons of the second sub-model in reverse order. For example, assuming that there are 5 neurons in the first sub-model and the second sub-model respectively, the first neuron of the first sub-model is connected to its second neuron, and is also connected to the fifth neuron of the second sub-model. This is for the subsequent training in a supervised manner, that is, the data in the first neuron of the first sub-model is supervised by the data of the fifth neuron of the second sub-model. Of course, the second neuron of the first sub-model can be jointly supervised and trained by the first neuron of the first sub-model and the fourth neuron of the second sub-model.

[0067] As described in step S4 above, multiple sets of seismic trace data sets and acoustic wave data sets, as well as corresponding spatial positioning information, are obtained, and steps S2-S3 are repeated to obtain a trained earthquake spatial positioning prediction model. After multiple sample training, the relationship between the seismic trace data and the acoustic wave data can be obtained, and supervised training is performed based on the relationship and spatial positioning information, so that the trained earthquake spatial positioning prediction model can predict spatial positioning based on the combination of seismic trace data and acoustic wave data, thereby improving the accuracy of the prediction.

[0068] As described in the above steps S6-S7, the real-time seismic trace data set and the real-time acoustic wave data set are segmented into n real-time seismic trace data subsets and n real-time acoustic wave data subsets according to a preset segmentation method, and the n real-time seismic trace data subsets and the n real-time acoustic wave data subsets are input into the earthquake spatial positioning prediction model to obtain the spatial positioning information of the current earthquake. Since the earthquake spatial positioning prediction model combines seismic waves and acoustic wave data, and uses advanced machine learning models for training and prediction, it can achieve accurate spatial positioning of earthquakes and provide strong support for earthquake monitoring and early warning. The accuracy and reliability of earthquake positioning can be improved, and contributions can be made to reducing the impact of earthquake disasters.

[0069] In one embodiment, the step S4 of acquiring multiple sets of seismic trace data sets and acoustic wave data sets, and corresponding spatial positioning information, and repeating steps S2-S3 to obtain a trained earthquake spatial positioning prediction model includes:

[0070] S401: Obtaining the relationship function between the seismic trace data set and the acoustic wave data set in the neurons of the first sub-model and the second sub-model to obtain the first relationship function f(x) corresponding to each neuron in the first sub-model and the second relationship function g(x) corresponding to each neuron in the second sub-model;

[0071] S402: According to each of the first relationship functions, each of the second relationship functions and the corresponding spatial positioning information, the first sub-model and the second sub-model are trained by supervised learning to obtain the trained first sub-model and the second sub-model, and then to obtain the trained earthquake spatial positioning prediction model.

[0072] As described in the above steps S401-S402, the first sub-model and the second sub-model are trained by using a supervised learning method. Since the first relationship function f(x) and the second relationship function g(x) are inverse functions of each other, this characteristic can be used to perform supervised training on both the first sub-model and the second sub-model, which can further improve the accuracy and reliability of the earthquake spatial positioning prediction model.

[0073] In one embodiment, the step S401 of obtaining the relationship function between the seismic trace data set and the acoustic wave data set in the neurons of the first sub-model and the second sub-model to obtain the first relationship function f(x) corresponding to each neuron in the first sub-model and the second relationship function g(x) corresponding to each neuron in the second sub-model includes:

[0074] S4021: The first sub-model is obtained by formula , the first relationship function f(x) corresponding to the seismic data subset and the acoustic wave data subset is obtained, and the second sub-model is obtained by formula , the second relationship function g(x) corresponding to the seismic trace data subset and the acoustic wave data subset is obtained; where, , , represents a calculation function based on parameter x, represents a calculation function based on parameter x, represents the hth seismic trace data subset, represents the kth acoustic wave data subset, represents the seismic trace data subset in the h+ith temporary data set, represents the seismic trace data subset in the h+i+1th temporary data set, represents the h+i-1th seismic trace data subset, represents the k+jth subset of acoustic wave data, represents the k+j+1th acoustic wave data subset, Represents the k+j-1th acoustic wave data subset.

[0075] As described in step S4021 above, it should be noted that the superscript T is a calculation symbol, which is the transpose of the vector, while the non-superscript T is a calculation function. and are the first relationship function f(x) and the second relationship function to be obtained, and their corresponding relationship functions can be any one of a logarithmic function, a multi-time function, a linear function, a quadratic function, and an exponential function.

[0076] In one embodiment, in the step S1 of acquiring a seismic trace data set and an acoustic wave data set composed of continuous data within a period of time, and corresponding spatial positioning information, the step of acquiring the seismic trace data set includes:

[0077] S101: Obtain the original data set of seismic gathers;

[0078] S102: Performing data consistency processing and anisotropy correction processing on the original data set of the seismic trace gather to obtain the seismic trace data set.

[0079] As described in the above steps S101-S102, seismic wave data, i.e., seismic trace data, can be recorded by seismic detectors (or seismographs). These detectors may be located on the ground, on the seabed, or in a well, depending on the specific exploration needs. In order to eliminate data inconsistencies caused by instrument differences, environmental factors, or improper operation. Specifically, steps such as data standardization, denoising, and time calibration are included to ensure that all data sets are compared and analyzed under the same standards. Differences in seismic wave propagation caused by the anisotropy of underground media (i.e., different physical properties of the medium in different directions). Specifically, mathematical models or physical simulations can be used to estimate and correct such differences to improve the accuracy and reliability of the data. Similarly, the acoustic wave data can also be preprocessed, and the preprocessing method is not limited, and can be processed with reference to the existing method of processing acoustic wave data.

[0080] In one embodiment, in the step S1 of acquiring a seismic trace data set and an acoustic wave data set composed of continuous data within a period of time, and corresponding spatial positioning information, the step of acquiring the seismic trace data set includes:

[0081] S111: Obtain the original data set of seismic gathers;

[0082] S112: Determine whether there are seismic trace data collected in multiple directions in the original data set of the seismic trace gather;

[0083] S113: If there are seismic trace data collected in multiple directions and orientations, obtain a preset weight for each orientation;

[0084] S114: performing weighted processing on each seismic trace data according to the preset weight to obtain a weighted seismic trace data set.

[0085] As described in the above steps S111-S114, the preset weights for each orientation are obtained, that is, preset weights are set for each orientation in advance, and the preset weights are related to the size of the seismic data. For example, if the original data set of the seismic data set contains data from due north and due east, the preset weights can be set according to the size of the data, or the weights can be set in proportion. The data of each seismic data set is weighted according to the preset weights to obtain a weighted original data set of the seismic data set, which is used to input into the generation model of the preset model. Similarly, if the acoustic wave data also contains data from multiple orientations, the same processing method can be used for processing, which will not be described in detail in this application.

[0086] Reference Figure 2 The present invention also provides a spatial positioning device based on seismic waves and acoustic waves, comprising:

[0087] The first acquisition module 10 is used to instruct the implementation of step S1: acquiring a seismic trace data set and an acoustic wave data set composed of continuous data within a period of time, and corresponding spatial positioning information;

[0088] The matching module 20 is used to instruct the implementation of step S2: matching the seismic trace data set and the acoustic wave data set in time order, and dividing the seismic trace data set into n seismic trace data subsets and the acoustic wave data set into n acoustic wave data subsets according to a preset segmentation method;

[0089] The first input module 30 is used to instruct the implementation of step S3: inputting the n seismic trace data subsets and the n acoustic wave data subsets into the first sub-model and the second sub-model of the preset earthquake spatial positioning prediction model respectively, and inputting the spatial positioning information into the output layer of the preset earthquake spatial positioning prediction model for training; wherein the preset earthquake prediction model includes a first sub-model, a second sub-model and an output layer, the neurons of the respective intermediate layers of the first sub-model and the second sub-model are cross-connected in sequence, and the first sub-model and the second sub-model are connected to the output layer respectively;

[0090] The second acquisition module 40 is used to instruct the implementation of step S4: acquiring multiple sets of seismic trace data sets and acoustic wave data sets, as well as corresponding spatial positioning information, and repeating steps S2-S3 to obtain a trained earthquake spatial positioning prediction model;

[0091] The third acquisition module 50 is used to instruct the implementation of step S5: acquiring a real-time seismic trace data set and a real-time acoustic wave data set composed of continuous data in a current time period;

[0092] The segmentation module 60 is used to instruct the implementation of step S6: segmenting the real-time seismic trace data set and the real-time acoustic wave data set into n real-time seismic trace data subsets and n real-time acoustic wave data subsets according to a preset segmentation method;

[0093] The second input module 70 is used to instruct the implementation of step S7: inputting the n real-time seismic trace data subsets and the n real-time acoustic wave data subsets into the earthquake spatial positioning prediction model to obtain the spatial positioning information of the current earthquake.

[0094] In one embodiment, the second acquisition module 40 includes:

[0095] A calculation submodule, used for instructing to implement step S401: obtaining the relationship function between the seismic trace data set and the acoustic wave data set in the neurons of the first submodel and the second submodel, and obtaining the first relationship function f(x) corresponding to each neuron in the first submodel and the second relationship function g(x) corresponding to each neuron in the second submodel;

[0096] The training submodule is used to instruct the implementation step S402: the first sub-model and the second sub-model are trained in a supervised learning manner according to each of the first relationship functions, each of the second relationship functions and the corresponding spatial positioning information, so as to obtain the trained first sub-model and the second sub-model, and then obtain the trained earthquake spatial positioning prediction model.

[0097] In one embodiment, the computing submodule includes:

[0098] A calculation unit is used to instruct the implementation of step S4021: the first sub-model is calculated by formula , the first relationship function f(x) corresponding to the seismic data subset and the acoustic wave data subset is obtained, and the second sub-model is obtained by formula , the second relationship function g(x) corresponding to the seismic trace data subset and the acoustic wave data subset is obtained; where, , , represents a calculation function based on parameter x, represents a calculation function based on parameter x, represents the hth seismic trace data subset, represents the kth acoustic wave data subset, represents the seismic trace data subset in the h+ith temporary data set, represents the seismic trace data subset in the h+i+1th temporary data set, represents the h+i-1th seismic trace data subset, represents the k+jth subset of acoustic wave data, represents the k+j+1th acoustic wave data subset, Represents the k+j-1th acoustic wave data subset.

[0099] In one embodiment, the first acquisition module 10 includes:

[0100] The seismic gather original data set acquisition submodule is used to instruct the implementation of step S101: acquiring the seismic gather original data set;

[0101] The seismic trace gather original data set processing submodule is used to instruct the implementation of step S102: performing data consistency processing and anisotropy correction processing on the seismic trace gather original data set to obtain the seismic trace data set.

[0102] In one embodiment, the first acquisition module 10 includes:

[0103] The original data set acquisition submodule is used to instruct the implementation of step S111: acquiring the original data set of the seismic gather;

[0104] The original data set judgment submodule is used to instruct the implementation of step S112: judging whether there are seismic trace data collected in multiple directions in the original data set of the seismic trace gather;

[0105] The weight acquisition submodule is used to instruct the implementation of step S113: if there are seismic trace data collected in multiple directions and orientations, then the preset weight of each orientation is obtained;

[0106] The weighted processing submodule is used to instruct the implementation of step S114: weighted processing is performed on each seismic trace data according to the preset weight to obtain a weighted seismic trace data set.

[0107] The beneficial effects of the present invention are as follows: by acquiring a seismic trace data set and an acoustic wave data set composed of continuous data, the data sets are divided and input into the first sub-model and the second sub-model for training, an earthquake spatial positioning prediction model is obtained, and the earthquake spatial positioning prediction model is used to predict the current data to obtain the spatial positioning information of the current earthquake. Since the earthquake spatial positioning prediction model combines seismic wave and acoustic wave data and uses advanced machine learning models for training and prediction, it can realize the precise spatial positioning of earthquakes and provide strong support for earthquake monitoring and early warning. The accuracy and reliability of earthquake positioning can be improved, and contributions can be made to reducing the impact of earthquake disasters.

[0108] Reference Figure 3 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store various seismic trace data and acoustic wave data, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the spatial positioning method based on seismic waves and acoustic waves described in any of the above embodiments can be implemented.

[0109] Those skilled in the art will understand that Figure 3 The structure shown in is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied.

[0110] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the spatial positioning method based on seismic waves and sound waves described in any of the above embodiments can be implemented.

[0111] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0112] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method 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, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.

[0113] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0114] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0115] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the claims of the present invention.

Claims

1. A spatial positioning method based on seismic waves and acoustic waves, characterized in that: include: S1: Acquire the seismic trace data set and acoustic wave data set consisting of continuous data within a period of time, as well as the corresponding spatial positioning information; S2: matching the seismic trace data set and the acoustic wave data set in time order, and dividing the seismic trace data set into n seismic trace data subsets and the acoustic wave data set into n acoustic wave data subsets according to a preset segmentation method; S3: inputting the n seismic trace data subsets and the n acoustic wave data subsets into the first sub-model and the second sub-model of the preset seismic spatial positioning prediction model respectively, and inputting the spatial positioning information into the output layer of the preset seismic spatial positioning prediction model for training; The preset earthquake prediction model includes a first sub-model, a second sub-model and an output layer, the neurons in the intermediate layers of the first sub-model and the second sub-model are cross-connected in sequence, and the first sub-model and the second sub-model are connected to the output layer respectively; S4: Acquire multiple sets of seismic trace data sets and acoustic wave data sets, as well as corresponding spatial positioning information, and repeat steps S2-S3 to obtain a trained earthquake spatial positioning prediction model; S5: Acquire a real-time seismic trace data set and a real-time acoustic wave data set consisting of continuous data in the current time period; S6: dividing the real-time seismic trace data set and the real-time acoustic wave data set into n real-time seismic trace data subsets and n real-time acoustic wave data subsets according to a preset division method; S7: inputting the n real-time seismic trace data subsets and the n real-time acoustic wave data subsets into the earthquake spatial positioning prediction model to obtain the spatial positioning information of the current earthquake; The step S4 of acquiring multiple sets of seismic trace data sets and acoustic wave data sets, and corresponding spatial positioning information, and repeating steps S2-S3 to obtain a trained earthquake spatial positioning prediction model includes: S401: Obtaining the relationship function between the seismic trace data set and the acoustic wave data set in the neurons of the first sub-model and the second sub-model to obtain the first relationship function f(x) corresponding to each neuron in the first sub-model and the second relationship function g(x) corresponding to each neuron in the second sub-model; S402: According to each of the first relationship functions, each of the second relationship functions and the corresponding spatial positioning information, the first sub-model and the second sub-model are trained by supervised learning to obtain the trained first sub-model and the second sub-model, and then to obtain the trained earthquake spatial positioning prediction model.

2. The spatial positioning method based on seismic waves and acoustic waves as claimed in claim 1, characterized in that: The step S401 of obtaining the relationship function between the seismic trace data set and the acoustic wave data set in the neurons of the first sub-model and the second sub-model to obtain the first relationship function f(x) corresponding to each neuron in the first sub-model and the second relationship function g(x) corresponding to each neuron in the second sub-model includes: S4021: The first sub-model is obtained by formula , the first relationship function f(x) corresponding to the seismic data subset and the acoustic wave data subset is obtained, and the second sub-model is obtained by formula , the second relationship function g(x) corresponding to the seismic trace data subset and the acoustic wave data subset is obtained; where, , , represents a calculation function based on parameter x, represents a calculation function based on parameter x, represents the hth seismic trace data subset, represents the kth acoustic wave data subset, represents the seismic trace data subset in the h+ith temporary data set, represents the seismic trace data subset in the h+i+1th temporary data set, represents the h+i-1th seismic trace data subset, represents the k+jth subset of acoustic wave data, represents the k+j+1th acoustic wave data subset, Represents the k+j-1th acoustic wave data subset.

3. The spatial positioning method based on seismic waves and acoustic waves as claimed in claim 1, characterized in that: In the step S1 of acquiring a seismic trace data set and an acoustic wave data set composed of continuous data within a period of time, and corresponding spatial positioning information, the step of acquiring the seismic trace data set includes: S101: Obtain the original data set of seismic gathers; S102: Performing data consistency processing and anisotropy correction processing on the original data set of the seismic trace gather to obtain the seismic trace data set.

4. The spatial positioning method based on seismic waves and acoustic waves as claimed in claim 1, characterized in that: In the step S1 of acquiring a seismic trace data set and an acoustic wave data set composed of continuous data within a period of time, and corresponding spatial positioning information, the step of acquiring the seismic trace data set includes: S111: Get the original data set of seismic gathers; S112: Determine whether there are seismic trace data collected in multiple directions in the original data set of the seismic trace gather; S113: If there are seismic trace data collected in multiple directions and orientations, obtain a preset weight for each orientation; S114: performing weighted processing on each seismic trace data according to the preset weight to obtain a weighted seismic trace data set.

5. A spatial positioning device based on seismic waves and sound waves, characterized in that: include: A first acquisition module is used to instruct the implementation of step S1: acquiring a seismic trace data set and an acoustic wave data set composed of continuous data within a period of time, and corresponding spatial positioning information; A matching module, used for instructing to implement step S2: matching the seismic trace data set and the acoustic wave data set in time order, and dividing the seismic trace data set into n seismic trace data subsets and the acoustic wave data set into n acoustic wave data subsets according to a preset segmentation method; A first input module is used to instruct the implementation of step S3: inputting the n seismic trace data subsets and the n acoustic wave data subsets into the first sub-model and the second sub-model of the preset seismic spatial positioning prediction model respectively, and inputting the spatial positioning information into the output layer of the preset seismic spatial positioning prediction model for training; The preset earthquake prediction model includes a first sub-model, a second sub-model and an output layer, the neurons in the intermediate layers of the first sub-model and the second sub-model are cross-connected in sequence, and the first sub-model and the second sub-model are connected to the output layer respectively; The second acquisition module is used to instruct the implementation of step S4: acquiring multiple sets of seismic trace data sets and acoustic wave data sets, as well as corresponding spatial positioning information, and repeating steps S2-S3 to obtain a trained earthquake spatial positioning prediction model; A third acquisition module is used to instruct the implementation of step S5: acquiring a real-time seismic trace data set and a real-time acoustic wave data set composed of continuous data in a current time period; A segmentation module, used for instructing to implement step S6: segmenting the real-time seismic trace data set and the real-time acoustic wave data set into n real-time seismic trace data subsets and n real-time acoustic wave data subsets according to a preset segmentation method; The second input module is used to instruct the implementation of step S7: inputting the n real-time seismic trace data subsets and the n real-time acoustic wave data subsets into the earthquake spatial positioning prediction model to obtain the spatial positioning information of the current earthquake; The second acquisition module includes: A calculation submodule, used for instructing to implement step S401: obtaining the relationship function between the seismic trace data set and the acoustic wave data set in the neurons of the first submodel and the second submodel, and obtaining the first relationship function f(x) corresponding to each neuron in the first submodel and the second relationship function g(x) corresponding to each neuron in the second submodel; The training submodule is used to instruct the implementation step S402: the first sub-model and the second sub-model are trained in a supervised learning manner according to each of the first relationship functions, each of the second relationship functions and the corresponding spatial positioning information, so as to obtain the trained first sub-model and the second sub-model, and then obtain the trained earthquake spatial positioning prediction model.

6. The spatial positioning device based on seismic waves and acoustic waves as claimed in claim 5, characterized in that: The computing submodule comprises: A calculation unit, used to instruct to implement step S4021: the first sub-model is calculated by formula , the first relationship function f(x) corresponding to the seismic data subset and the acoustic wave data subset is obtained, and the second sub-model is obtained by formula , the second relationship function g(x) corresponding to the seismic trace data subset and the acoustic wave data subset is obtained; where, , , represents a calculation function based on parameter x, represents a calculation function based on parameter x, represents the hth seismic trace data subset, represents the kth acoustic wave data subset, represents the seismic trace data subset in the h+ith temporary data set, represents the seismic trace data subset in the h+i+1th temporary data set, represents the h+i-1th seismic trace data subset, represents the k+jth subset of acoustic wave data, represents the k+j+1th acoustic wave data subset, Represents the k+j-1th acoustic wave data subset.

7. The spatial positioning device based on seismic waves and acoustic waves as claimed in claim 5, characterized in that: The first acquisition module includes: The seismic gather original data set acquisition submodule is used to instruct the implementation of step S101: acquiring the seismic gather original data set; The seismic trace gather original data set processing submodule is used to instruct the implementation of step S102: performing data consistency processing and anisotropy correction processing on the seismic trace gather original data set to obtain the seismic trace data set.

8. The spatial positioning device based on seismic waves and acoustic waves as claimed in claim 5, characterized in that: The first acquisition module includes: The original data set acquisition submodule is used to instruct the implementation of step S111: acquiring the original data set of the seismic gather; The original data set judgment submodule is used to instruct the implementation of step S112: judging whether there are seismic trace data collected in multiple directions in the original data set of the seismic trace gather; The weight acquisition submodule is used to instruct the implementation of step S113: if there are seismic trace data collected in multiple directions and orientations, then the preset weight of each orientation is obtained; The weighted processing submodule is used to instruct the implementation of step S114: weighted processing is performed on each seismic trace data according to the preset weight to obtain a weighted seismic trace data set.

Images