A surface Q field establishment method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a method and device for establishing a surface Q field, electronic equipment and a storage medium. The method for establishing a surface Q field comprises: obtaining first feature data of a plurality of surface Q value prediction points of a target work area; wherein the first feature data at least includes the east coordinate, north coordinate and surface velocity of the surface Q value prediction points; obtaining a plurality of groups of prediction input data according to the first feature data of the plurality of surface Q value prediction points; obtaining the predicted value of the surface Q value of the plurality of surface Q value prediction points by using a surface Q value neural network prediction model according to the plurality of groups of prediction input data; and establishing the surface Q field of the target work area according to the predicted value of the surface Q value of the plurality of surface Q value prediction points and the surface Q value of a plurality of surface Q value survey points of the target work area.

Description

Technical Field

[0001] This application relates to the field of petroleum geophysical exploration, and in particular to a method, apparatus, electronic device and storage medium for establishing a surface Q field. Background Technology

[0002] The surface Q-value (hereinafter referred to as the surface Q-value) is an important parameter for quantitatively describing the absorption and attenuation of seismic waves. Compared with deeper media, the surface layer experiences more severe absorption and attenuation of seismic waves. Accurately establishing the surface Q-field and effectively compensating for it in seismic data is of great significance for improving the resolution of seismic data.

[0003] In related technologies, there are various schemes for establishing the surface Q field, such as the surface Q value survey method, fitting method, and empirical formula method.

[0004] The surface Q-value survey method mainly utilizes dual-well micrologging and single-well micrologging methods to investigate the surface Q-value of the target work area and obtain the true surface Q-value of the survey points. However, the surface Q-value survey is costly, and the number of surface Q-value survey points carried out in the actual target work area is relatively small, resulting in a limited control range and failing to meet the requirements for accurately establishing the surface Q-field.

[0005] Establishing a surface Q-field using fitting methods typically involves fitting the relationship between the true surface Q-value and surface velocity at surveyed surface Q-value points, establishing a formula for the true surface Q-value and surface velocity. Then, the surface velocity at predicted surface Q-value points, obtained from first-arrival seismic artillery data or previous small-refraction and micro-logging data of the target area, is substituted into the formula for the true surface Q-value and surface velocity to obtain the true surface Q-value at the predicted surface Q-value points. However, the process of establishing the formulas for the true surface Q-value and surface velocity is highly susceptible to human intervention, and it is often difficult to establish accurate formulas, leading to a decrease in the accuracy of the established surface Q-field.

[0006] Establishing a surface Q-field using empirical formulas typically involves substituting the surface velocity from surface Q-value survey points and predicted surface Q-value points obtained from initial seismic artillery strikes or previous small refraction / micrologging data of the target area into an empirical formula relating surface Q-values ​​and surface velocities. This yields the relative surface Q-values ​​between the survey points and the predicted points. Then, the actual surface Q-values ​​of the survey points are used to calibrate their relative surface Q-values, resulting in calibration coefficients that convert the relative surface Q-values ​​to the actual surface Q-values. These calibration coefficients are then used to convert the relative surface Q-values ​​of the predicted points back to their actual surface Q-values, thus establishing the surface Q-field. However, establishing a surface Q-field using empirical formulas is complex, often making it difficult to obtain widely applicable calibration coefficients, and the determination of these coefficients is highly susceptible to human error.

[0007] Therefore, how to accurately and conveniently establish the surface Q field is a technical problem that urgently needs to be solved. Summary of the Invention

[0008] This application provides a method, apparatus, electronic device, and storage medium for establishing a surface Q-field, which can accurately and conveniently establish a surface Q-field.

[0009] One embodiment of this application provides a method for establishing a surface Q-field. The method includes: acquiring first feature data of multiple surface Q-value prediction points in a target work area; wherein the first feature data includes at least the east coordinate, north coordinate, and surface velocity of the surface Q-value prediction points; obtaining multiple sets of prediction input data based on the first feature data of the multiple surface Q-value prediction points; obtaining predicted values ​​of the surface Q-values ​​of the multiple surface Q-value prediction points using a surface Q-value neural network prediction model based on the multiple sets of prediction input data; and establishing a surface Q-field in the target work area based on the predicted values ​​of the surface Q-values ​​of the multiple surface Q-value prediction points and the surface Q-values ​​of multiple surface Q-value survey points in the target work area.

[0010] In some embodiments, the first feature data further includes surface velocity fitting features; wherein the surface velocity fitting features are obtained by calculating the surface velocity in the first feature data by taking the square root of the power of 2.2; the step of obtaining multiple sets of prediction input data based on the first feature data of the plurality of surface Q-value prediction points includes: for each of the first feature data of the surface Q-value prediction points, performing the following processing: normalizing the first feature data; and using the normalized first feature data as a set of prediction input data.

[0011] In some embodiments, obtaining the predicted values ​​of the surface Q-values ​​of the plurality of surface Q-value prediction points using a surface Q-value neural network prediction model based on the plurality of sets of predicted input data includes: for each surface Q-value prediction point, performing the following processing: inputting the predicted input data of the surface Q-value prediction point into the surface Q-value neural network prediction model to obtain a first predicted value; performing inverse normalization processing on the first predicted value to obtain the predicted value of the surface Q-value of the surface Q-value prediction point.

[0012] In some embodiments, establishing the surface Q-field of the target work area based on the predicted surface Q-values ​​of the plurality of surface Q-value prediction points and the surface Q-values ​​of the plurality of surface Q-value survey points of the target work area includes: obtaining the surface Q-values ​​of the remaining locations of the target work area using a spatial interpolation algorithm based on the predicted surface Q-values ​​of the plurality of surface Q-value prediction points and the surface Q-values ​​of the plurality of surface Q-value survey points of the target work area; and establishing the surface Q-field of the target work area using the surface Q-values ​​of all locations of the target work area.

[0013] In some embodiments, the surface Q-value neural network prediction model is a BP neural network model; the surface Q-value neural network prediction model is trained by: obtaining a training dataset; using the training dataset, training the initial BP neural network model to obtain the surface Q-value neural network prediction model.

[0014] In some embodiments, the training dataset includes multiple sets of training data and labels for each set of training data; obtaining the training dataset includes: obtaining second feature data of multiple surface Q-value survey points in the target work area and surface Q-values ​​obtained using exploration data; wherein, the second feature data includes at least the east coordinate, north coordinate, and surface velocity of the surface Q-value survey points; for each surface Q-value survey point, the following operations are performed: the second feature data of the surface Q-value survey point is normalized and used as a set of sample data; the surface Q-values ​​of the surface Q-value survey points obtained using exploration data are normalized and used as labels for the sample data.

[0015] In some embodiments, obtaining the second feature data of multiple surface Q-value survey points in the target work area includes: obtaining a set of basic data for all surface Q-value survey points in the target work area; wherein the basic data includes at least the east coordinate, north coordinate, and surface velocity of the surface Q-value survey points; sorting the surface velocities in the set of basic data in descending order to form a velocity distribution interval, and removing the basic data corresponding to the surface velocities within a preset range at the beginning and end of the velocity distribution interval from the set of basic data; and performing the following operations on the basic data of each surface Q-value survey point in the set of basic data: calculating the 2.2 power root of the surface velocity in the basic data to obtain the surface velocity fitting feature of the surface Q-value survey point; and obtaining the second feature data of multiple surface Q-value survey points in the target work area based on the basic data of all surface Q-value survey points in the set of basic data and the surface velocity fitting feature.

[0016] In some embodiments, training an initial BP neural network model using the training dataset to obtain the surface Q-value neural network prediction model includes: using the initial BP neural network model to process sample data in the training dataset; adjusting the parameters of the initial BP neural network model according to the difference between the output value of the initial BP neural network model and the label of the sample data until the convergence condition of the model is met, thereby obtaining the surface Q-value neural network prediction model.

[0017] One embodiment of this application provides a surface Q-field establishment device, the device comprising: a first acquisition module, configured to acquire first feature data of multiple surface Q-value prediction points in a target work area; wherein the first feature data includes at least the east coordinate, north coordinate, and surface velocity of the surface Q-value prediction points; a second acquisition module, configured to obtain multiple sets of prediction input data based on the first feature data of the multiple surface Q-value prediction points; a third acquisition module, configured to obtain predicted values ​​of the surface Q-values ​​of the multiple surface Q-value prediction points using a surface Q-value neural network prediction model based on the multiple sets of prediction input data; and an establishment module, configured to establish the surface Q-field of the target work area based on the predicted values ​​of the surface Q-values ​​of the multiple surface Q-value prediction points and the surface Q-values ​​of multiple surface Q-value survey points in the target work area.

[0018] This application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the method described above when running the program.

[0019] This application provides a storage medium for storing a computer-readable program, which, when run, performs the method described above.

[0020] The technical solutions provided in this application have at least the following advantages compared with the prior art:

[0021] In the embodiments provided in this application, first feature data of multiple surface Q-value prediction points in the target work area are obtained; multiple sets of prediction input data are obtained based on the first feature data of the multiple surface Q-value prediction points; based on the multiple sets of prediction input data, a surface Q-value neural network prediction model is used to obtain the predicted values ​​of the surface Q-values ​​of the multiple surface Q-value prediction points; based on the predicted values ​​of the surface Q-values ​​of the multiple surface Q-value prediction points and the surface Q-values ​​of multiple surface Q-value survey points in the target work area, a surface Q-field of the target work area is established. This allows for the accurate and convenient establishment of the surface Q-field. Attached Figure Description

[0022] This application will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0023] Figure 1 This is an exemplary flowchart of a surface Q-field establishment method according to some embodiments of this application;

[0024] Figure 2 This is an exemplary flowchart of a training method for a surface Q-value neural network prediction model according to some embodiments of this application;

[0025] Figure 3This is an exemplary schematic diagram of the structure of a surface Q-value neural network prediction model according to some embodiments of this application;

[0026] Figure 4A This is an exemplary schematic diagram showing a comparison between surface Q values ​​obtained using the methods provided in this application and surface Q values ​​obtained using exploration data, according to some embodiments of this application.

[0027] Figure 4B This is yet another exemplary schematic diagram showing a comparison between surface Q values ​​obtained using the methods provided in this application and surface Q values ​​obtained using exploration data, according to some embodiments of this application.

[0028] Figure 5A This is an exemplary schematic diagram comparing the surface Q value obtained based on relevant technologies with the surface Q value obtained using exploration data;

[0029] Figure 5B This is yet another exemplary schematic diagram comparing the surface Q value obtained according to relevant technologies with the surface Q value obtained using exploration data;

[0030] Figure 6A This is an exemplary schematic diagram of the surface Q-value plane distribution of control points according to some embodiments of this application;

[0031] Figure 6B This is yet another exemplary schematic diagram of a control point surface Q-value planar distribution map according to some embodiments of this application;

[0032] Figure 7A This is an exemplary schematic diagram of a Q-field map obtained using a spatial interpolation algorithm according to some embodiments of this application;

[0033] Figure 7B This is yet another exemplary schematic diagram of a Q-field map obtained using a spatial interpolation algorithm according to some embodiments of this application;

[0034] Figure 8 These are ground seismic profiles before and after surface Q-value compensation, as shown in some embodiments of this application.

[0035] Figure 9A These are comparison diagrams of surface seismic profiles before and after surface Q-value compensation, as shown in some embodiments of this application.

[0036] Figure 9B This is yet another comparison diagram of the surface seismic profile spectrum before and after surface Q-value compensation according to some embodiments of this application;

[0037] Figure 10 This is an exemplary schematic diagram of a surface Q-field establishment apparatus according to some embodiments of this application;

[0038] Figure 11 This is an exemplary structural diagram of an electronic device according to some embodiments of this application. Detailed Implementation

[0039] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0040] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other words can achieve the same purpose, they may be replaced by other expressions.

[0041] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0042] Flowcharts are used in this application to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0043] For ease of understanding, the technical solution of this application is described below with reference to the accompanying drawings and embodiments.

[0044] Figure 1 This is an exemplary flowchart of a surface Q-field establishment method according to some embodiments of this application.

[0045] like Figure 1 As shown, the method for establishing the surface Q-field includes the following steps:

[0046] Step S110: Obtain the first feature data of multiple surface Q-value prediction points of the target work area.

[0047] The first feature data is data related to the surface Q-value, which includes at least the east and north coordinates of the surface Q-value prediction point and the surface velocity.

[0048] In some embodiments, to obtain more accurate prediction results, the first feature data further includes surface velocity fitting features. The surface velocity fitting features have a linear relationship with the surface Q-value and can be obtained by calculating the surface velocity in the first feature data using the power of 2.2.

[0049] In the specific implementation process, the first feature data of the surface Q-value prediction points corresponds one-to-one with the second feature data input into the surface Q-value neural network prediction model during training. For a detailed description of the surface Q-value neural network prediction model, please refer to the relevant content in step S130, which will not be repeated here. For a detailed description of the second feature data of the surface Q-value neural network prediction model obtained through training, please refer to... Figure 2 The relevant content will not be repeated here.

[0050] In the specific implementation process, multiple surface Q-value prediction points can be selected in various ways. For example, test location points can be selected based on the distribution of surface Q-value survey points in the target work area, so that the surface Q-value prediction points and surface Q-value survey points are located relatively evenly in the target work area.

[0051] Step S120: Based on the first feature data of multiple surface Q-value prediction points, obtain multiple sets of prediction input data.

[0052] In the specific implementation process, the first feature data of multiple surface Q-value prediction points can be preprocessed, and the preprocessed first feature data can be used as multiple sets of prediction input data.

[0053] In some embodiments, the following processing can be performed on the first feature data of each surface Q-value prediction point:

[0054] The first feature data is normalized; the normalized first feature data is then used as a set of prediction input data.

[0055] As an example only, the following describes the detailed process of normalizing the first feature data.

[0056] 1) The first feature data of the obtained surface Q-value prediction points include the east coordinate x′[i], the north coordinate y′[i], the surface elevation z′[i], the surface velocity v′[i], and the surface velocity fitting feature v′. 2.2 [i], surface thickness h′[i], and seismic wave propagation time t′[i] in the surface layer.

[0057] 2) Utilize Figure 2 The normalization parameters of the features in the training dataset (see detailed description) Figure 2(Related content) Normalizes the features of surface Q-value prediction points. First, the east coordinates of the surface Q-value prediction points are normalized, as shown in the following formula.

[0058]

[0059] Where x′[i] is the original value of the east coordinate of the i-th surface Q-value prediction point, and x′[i]1 is the normalized feature of the east coordinate of the i-th surface Q-value prediction point.

[0060] Similarly, complete the calculation of the north coordinate y′[i], surface elevation z′[i], surface velocity v′[i], and surface velocity fitting feature v′ of the predicted surface Q value points. 2.2 Normalization of [i], surface thickness h′[i], and seismic wave propagation time t′[i] in the surface layer yields the normalized features y′[i]1, z′[i]1, v′[i]1, and v′[i]1 of the surface layer Q-value prediction points. 2.2 [i]1、h′[i]1、t′[i]1.

[0061] Step S130: Based on multiple sets of predicted input data, the predicted values ​​of the surface Q-values ​​at multiple surface Q-value prediction points are obtained using a surface Q-value neural network prediction model.

[0062] In practical implementation, various machine learning models can be used to establish a surface Q-value neural network prediction model, including but not limited to: convolutional neural network models, random forest models, etc. In some embodiments, the surface Q-value neural network prediction model is a BP neural network model. The number of neurons in the input layer of the BP neural network model is consistent with the number of features in the predicted input data; the number of hidden layers n and the number of neurons in each hidden layer m are set as hyperparameters; the output layer has only one neuron.

[0063] For example only, such as Figure 3 As shown, the dimension of the first feature data is 6, so the number of neurons in the input layer of the surface Q-value neural network prediction model is also 6; the number of hidden layers is set to 2, where the number of neurons in the first hidden layer is set to 9 and the number of neurons in the second hidden layer is set to 5.

[0064] The activation function used in each hidden layer is the sigmoid function, which is shown below:

[0065]

[0066] In some embodiments, the predicted input data is normalized in step S120, and the following processing can be performed for each surface Q-value prediction point: the predicted input data of the surface Q-value prediction point is input into the surface Q-value neural network prediction model, and the output layer of the surface Q-value neural network prediction model outputs a first predicted value; the first predicted value is subjected to inverse normalization processing to obtain the predicted value of the surface Q-value of the surface Q-value prediction point.

[0067] As an example only, the first feature data x′[i]1, y′[i]1, z′[i]1, v′[i]1, v′[i]1, v′[i]1, and v′[i]1 can be normalized from the surface Q-value prediction points in step S120. 2.2 The parameters [i]1, h′[i]1, and t′[i]1 are input into the trained surface Q-value neural network prediction model to obtain the first predicted value q′[i] output by the surface Q-value neural network prediction model. Then, the parameters that are normalized to the labels of the training dataset (see details in the documentation) are used. Figure 2 (The relevant content in the text) performs inverse normalization on the data output by the neural network. The inverse normalization formula is:

[0068] Q′[i]=q′[i]*(q max -q min )+q min (3)

[0069] Where, q max and q min The maximum and minimum values ​​of the surface Q-values ​​in the training dataset are used; the denormalized data Q′[i] is the predicted value of the surface Q-value at the i-th surface Q-value prediction point.

[0070] Step S140: Based on the predicted values ​​of surface Q values ​​at multiple surface Q value prediction points and the surface Q values ​​at multiple surface Q value survey points in the target work area, establish the surface Q field of the target work area.

[0071] In practice, exploration data can be used to obtain surface Q-values ​​at multiple surface Q-value survey points in the target work area. As an example, dual-well micrologging or single-well micrologging can be used to conduct surface Q-value surveys in the target area, obtaining surface Q-values ​​at multiple survey points. However, due to the high cost of surface Q-value surveys, the number of surface Q-values ​​obtained through the above methods is relatively small, making it difficult to establish the surface Q-field of the target work area solely based on the surface Q-values ​​of these survey points.

[0072] In some embodiments, the predicted surface Q-values ​​of multiple surface Q-value prediction points and the surface Q-values ​​of multiple surface Q-value survey points can be used as surface Q-value control points for the target work area. A spatial interpolation algorithm can then be used to obtain the surface Q-values ​​at the remaining locations within the target work area. The spatial interpolation algorithm can be inverse distance interpolation, Kriging interpolation, etc.

[0073] Finally, the surface Q-field of the target work area can be established using the surface Q-values ​​of all locations in the target work area obtained by the above method.

[0074] The technical effects of the embodiments provided in this application are described below.

[0075] Figure 4A and Figure 4B It uses a trained surface Q-value neural network prediction model to predict the test dataset. To prevent model overfitting, the root mean square error of the prediction results for the test dataset is 1.1117, and the trend of the prediction results is basically consistent with the actual value, which can meet the requirements for establishing the surface Q field.

[0076] Figure 5A and Figure 5B The prediction results for the test dataset are obtained using existing technology. The root mean square error of the prediction results for the test dataset is 1.2513, which is larger than the surface Q-value prediction error based on the neural network algorithm proposed in this application, and the trend of the prediction results is basically inconsistent with the actual value.

[0077] Figure 6A and Figure 6B It is a planar distribution map of surface Q-value control points, composed of the surface Q-values ​​of the predicted surface Q-value points and the surface Q-values ​​of the surveyed surface Q-value points, calculated using the method provided in this application.

[0078] Figure 7A and Figure 7B Based on Figure 5A and Figure 5B The surface Q-value control points shown are used to obtain the surface Q-field using a spatial interpolation algorithm. This surface Q-field is then used to perform surface Q-compensation on the ground seismic profile. The ground seismic profiles before and after compensation are shown in the figure. Figure 8 As can be seen, the phase axes of the seismic profile are more continuous and the signal-to-noise ratio is higher after Q-compensation at the surface (white arrow position). Figure 9A and Figure 9B The spectrum of the ground seismic profile before and after surface Q-value compensation shows that the high-frequency end of the ground seismic profile expanded from 48Hz to 66Hz after surface Q-value compensation, proving the effectiveness of the surface Q-field establishment method based on neural network algorithm in this application.

[0079] Figure 2 This is an exemplary flowchart of a training method for a surface Q-value neural network prediction model according to some embodiments of this application.

[0080] In this embodiment, the surface Q-value neural network prediction model is constructed based on the BP neural network model, and can be trained to obtain the surface Q-value neural network prediction model through the following steps:

[0081] Step S210: Obtain the training dataset.

[0082] The training dataset includes multiple sets of training data and labels for each set of training data.

[0083] In some embodiments, second feature data of multiple surface Q-value survey points in the target work area and surface Q-values ​​obtained using exploration data can be acquired; wherein, the second feature data includes at least the east coordinate, north coordinate, and surface velocity of the surface Q-value survey points.

[0084] In some embodiments, a set of basic data for all surface Q-value survey points in the target work area can be obtained. The basic data for the surface Q-value survey points may include the east and north coordinates, surface elevation, surface velocity, surface thickness, seismic wave propagation time in the surface, and surface Q-values ​​obtained using exploration data.

[0085] The aforementioned set of basic data may contain inaccurate surface velocities (e.g., erroneous data obtained due to measurement errors or recording mistakes). In some embodiments, the surface velocities in the set of basic data can be sorted in descending order to form a velocity distribution interval, and the basic data corresponding to the surface velocities within a preset range (e.g., 3% of the velocity distribution interval) at the beginning and end of the velocity distribution interval can be removed from the set of basic data, thereby removing abnormal data from the set of basic data.

[0086] Because there is a non-linear relationship between surface Q-value and surface velocity, in order to enable the surface Q-value neural network prediction model to learn this non-linear relationship and improve the accuracy of model prediction, in some embodiments, the training data may include surface velocity fitting features. In specific implementation, for each surface Q-value survey point in the basic dataset, the following operation can be performed: the surface velocity in the basic data is calculated by taking the square root of the power of 2.2 to obtain the surface velocity fitting features for the surface Q-value survey point.

[0087] In some embodiments, second feature data for multiple surface Q-value survey points in the target work area can be obtained based on the basic data of all surface Q-value survey points in the basic data set and the surface velocity fitting characteristics. The surface Q-value obtained using exploration data is used as the label for the corresponding second feature data.

[0088] In the specific implementation process, the collected basic data needs to be checked and processed. This check determines whether any basic data is missing. For cases where basic data has missing values, the missing data can be supplemented in various ways. As an example, the average of data from multiple (e.g., 5) surface Q-value survey points near the missing value can be calculated, and this average can be used to replace the missing value. For instance, if the north coordinate feature of the 9th surface Q-value survey point is missing, the average of the north coordinates of the 5 surface Q-value survey points closest to the 9th surface Q-value survey point can be used as the north coordinate feature of the 9th surface Q-value survey point.

[0089] In some embodiments, the following operations can be performed for each surface Q-value survey point:

[0090] The second characteristic data of the surface Q-value survey points were normalized and used as a set of sample data; the surface Q-values ​​obtained from the exploration data of the surface Q-value survey points were normalized and used as the labels of the sample data.

[0091] In the specific implementation process, the data obtained from all surface Q-value survey points can be normalized and then divided into a training dataset and a test dataset in an 8:2 ratio. The training dataset is used to train the surface Q-value neural network prediction model. The test dataset is used to test the trained surface Q-value neural network prediction model to determine its prediction accuracy. The trained model that can accurately predict surface Q-values ​​is then used as the surface Q-value neural network prediction model.

[0092] As an example only, the following details the specific methods for normalizing data obtained from surface Q-value survey points.

[0093] 1) Normalize the data and labels in the training dataset.

[0094] First, the eastern coordinate feature x[i] in the training dataset of the surface Q-value survey points is normalized. Then, the minimum value x of the eastern coordinate feature x[i] in the training dataset is found. min and maximum value x max , will x min x max This is called the normalization parameter for the east coordinate features of the training dataset. Then, the normalized data x[i]1 of the east coordinate features in the training dataset is calculated using the following formula:

[0095]

[0096] Where x[i] is the original value of the east coordinate feature of the i-th surface Q-value survey point in the training dataset, x minTo find the minimum value of the coordinate feature of the training dataset, x max x[i]1 represents the maximum value of the east coordinate feature of the training dataset, and x[i]1 represents the normalized feature of the east coordinate feature of the i-th surface Q-value survey point in the training dataset.

[0097] Similarly, find the north coordinate y[i], surface elevation z[i], surface velocity v[i], and surface velocity fitting feature v in the training dataset. 2.2 The minimum and maximum values ​​of [i], layer thickness h[i], seismic wave propagation time t[i] in the surface layer, and the label q[i] in the training dataset are used to obtain the north coordinate y[i], surface elevation z[i], surface velocity v[i], and surface velocity fitting feature v[i] in the training dataset. 2.2 Data y of the minimum and maximum values ​​of [i], surface thickness h[i], and seismic wave propagation time t[i] in the surface layer. min y max z min z max v min v max v 2.2min v 2.2max h min h max t min t max And obtain the minimum and maximum values ​​of the training dataset label q[i]. min q max .

[0098] Following formula (4), the features y[i], z[i], v[i], and v[i] of all training datasets are sequentially calculated. 2.2 Normalization of [i], h[i], t[i] and label q[i] yields the normalized features y[i]1, z[i]1, v ... 2.2 [i]1, h[i]1, t[i]1 and the normalized label q[i]1.

[0099] 2) Normalize the data and labels in the test dataset.

[0100] First, use the east coordinate normalization parameter x from the training dataset. min x max The east coordinate feature X[i] in the test dataset is normalized using the normalization formula shown below. The normalization formula is:

[0101]

[0102] Where X[i] is the original value of the east coordinate feature of the i-th surface Q-value survey point in the test dataset, and X[i]1 is the normalized feature of the east coordinate feature of the i-th surface Q-value survey point in the test dataset.

[0103] Similarly, following formula (5), the features Y[i], Z[i], V[i], and V[i] of all test datasets are sequentially completed. 2.2 Normalization of [i], H[i], T[i] and label Q[i] yields the normalized features Y[i]1, Z[i]1, V ... 2.2 [i]1, H[i]1, T[i]1 and the normalized label Q[i]1.

[0104] Step S220: Using the training dataset, train the initial BP neural network model to obtain the surface Q-value neural network prediction model.

[0105] In some embodiments, an initial BP neural network model can be used to process the sample data in the training dataset; the parameters of the initial BP neural network model are adjusted according to the difference between the output value of the initial BP neural network model and the label of the sample data until the convergence condition of the model is met, thus obtaining the surface Q-value neural network prediction model.

[0106] The convergence condition of the model can be that the loss function decreases below a set value, for example, less than 1e-6.

[0107] Figure 10 This is an exemplary schematic diagram of a surface Q-field establishment apparatus according to some embodiments of this application.

[0108] like Figure 10 As shown, the surface Q-field establishment device includes: a first acquisition module 1010, a second acquisition module 1020, a third acquisition module 1030, and an establishment module 1040.

[0109] The first acquisition module 1010 is used to acquire first feature data of multiple surface Q-value prediction points in the target work area; wherein, the first feature data includes at least the east coordinate, north coordinate, and surface velocity of the surface Q-value prediction points.

[0110] The second acquisition module 1020 is used to obtain multiple sets of prediction input data based on the first feature data of the multiple surface Q-value prediction points.

[0111] The third acquisition module 1030 is used to obtain the predicted values ​​of the surface Q values ​​of the multiple surface Q value prediction points based on the multiple sets of predicted input data and using a surface Q value neural network prediction model.

[0112] The module 1040 is used to establish the surface Q field of the target work area based on the predicted values ​​of the surface Q values ​​of the multiple surface Q value prediction points and the surface Q values ​​of the multiple surface Q value survey points of the target work area.

[0113] In the embodiments of the above-mentioned surface Q-field establishment device, the specific processing of each module and the technical effects it brings can be referred to the relevant descriptions in the corresponding method embodiments, and will not be repeated here.

[0114] Figure 11 This is an exemplary structural diagram of an electronic device according to some embodiments of this application.

[0115] like Figure 11 As shown, the electronic device includes: at least one processor 1101, at least one communication interface 1102, at least one memory 1103, and at least one communication bus 1104. Optionally, the communication interface 1102 can be an interface of a communication module, such as the interface of a GSM module. The processor 1101 may be a CPU, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The memory 1103 may include high-speed RAM and may also include non-volatile memory, such as at least one disk storage device. The memory 1103 stores a program, and the processor 1101 calls the program stored in the memory 1103 to execute some or all of the above-described method embodiments.

[0116] This application relates to a storage medium for storing a computer-readable program, which, when run, performs some or all of the above-described method embodiments.

[0117] Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0118] Based on the same inventive concept, this application also provides a computer program product, including a computer program that, when executed by a processor, implements some or all of the above-described method embodiments.

[0119] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0120] Furthermore, this application uses specific terms to describe its embodiments. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this application do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application can be appropriately combined.

[0121] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this application are not intended to limit the order of the processes and methods of this application. Although the foregoing disclosure has discussed some currently considered useful embodiments of the invention through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the substance and scope of the embodiments of this application. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely through software solutions, such as installing the described system on existing servers or mobile devices.

[0122] Similarly, it should be noted that, in order to simplify the description of the present application and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of the embodiments of the present application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of the application requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

[0123] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of scope in some embodiments of this application are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0124] For each patent, patent application, patent application publication, and other material such as articles, books, specifications, publications, and documents referenced in this application, the entire contents of that patent are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this application, as well as documents that limit the broadest scope of the claims in this application (currently or subsequently appended to this application). It should be noted that if there are any inconsistencies or conflicts between the descriptions, definitions, and / or terminology used in the supplementary materials of this application and the content of this application, the descriptions, definitions, and / or terminology used in this application shall prevail.

[0125] Finally, it should be understood that the embodiments described in this application are merely illustrative of the principles of the embodiments of this application. Other modifications may also fall within the scope of this application. Therefore, alternative configurations of the embodiments of this application are considered as examples and not limitations, and are regarded as consistent with the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly described and illustrated in this application.

Claims

1. A method for establishing a surface Q-field, characterized in that, The method includes: First feature data of multiple surface Q-value prediction points in the target work area are obtained; wherein, the first feature data includes at least the east coordinate, north coordinate, surface velocity, and surface velocity fitting feature of the surface Q-value prediction points; the surface velocity fitting feature is obtained by calculating the surface velocity in the first feature data by taking the power of 2.

2. Based on the first feature data of the plurality of surface Q-value prediction points, multiple sets of prediction input data are obtained, including: for each of the first feature data of the surface Q-value prediction points, the following processing is performed: normalizing the first feature data; and using the normalized first feature data as a set of prediction input data. Based on the multiple sets of predicted input data, a surface Q-value neural network prediction model is used to obtain the predicted values ​​of the surface Q-values ​​at the multiple surface Q-value prediction points. This includes: for each surface Q-value prediction point, performing the following processing: inputting the predicted input data of the surface Q-value prediction point into the surface Q-value neural network prediction model to obtain a first predicted value; performing inverse normalization processing on the first predicted value to obtain the predicted value of the surface Q-value at the surface Q-value prediction point. Based on the predicted surface Q values ​​of the multiple surface Q value prediction points and the surface Q values ​​of the multiple surface Q value survey points in the target work area, a surface Q field for the target work area is established, including: using a spatial interpolation algorithm to obtain the surface Q values ​​of the remaining locations in the target work area based on the predicted surface Q values ​​of the multiple surface Q value prediction points and the surface Q values ​​of the multiple surface Q value survey points in the target work area; and using the surface Q values ​​of all locations in the target work area, a surface Q field for the target work area is established.

2. The method according to claim 1, characterized in that, The surface Q-value neural network prediction model is a BP neural network model; The surface Q-value neural network prediction model was trained using the following method: Obtain the training dataset; Using the training dataset, the initial BP neural network model is trained to obtain the surface Q-value neural network prediction model.

3. The method according to claim 2, characterized in that, The training dataset includes multiple sets of training data and labels for each set of training data; The acquisition of the training dataset includes: Acquire the second characteristic data of multiple surface Q-value survey points in the target work area and the surface Q-value obtained using exploration data; For each of the surface Q-value survey points, the following operations are performed: After normalizing the second characteristic data of the surface Q-value survey points, it is used as a set of sample data. The surface Q-values ​​obtained from the exploration data at the surface Q-value survey points are normalized and used as labels for the sample data.

4. The method according to claim 3, characterized in that, The acquisition of the second feature data of multiple surface Q-value survey points in the target work area includes: Obtain a set of basic data for all surface Q-value survey points in the target work area; wherein, the basic data includes at least the east coordinate, north coordinate, and surface velocity of the surface Q-value survey points; The surface velocities in the set of basic data are sorted in descending order to form velocity distribution intervals, and the basic data corresponding to the surface velocities within the preset ranges at both ends of the velocity distribution intervals are removed from the set of basic data; and For the basic data of each surface Q-value survey point in the aforementioned basic dataset, perform the following operations: The surface velocity in the basic data is calculated by taking the 2nd power square root to obtain the surface velocity fitting characteristics of the surface Q value survey points; Based on the basic data of all surface Q-value survey points in the basic data set and the surface velocity fitting characteristics, the second feature data of multiple surface Q-value survey points in the target work area are obtained.

5. A surface Q-field establishment device, characterized in that, The device includes: The first acquisition module is used to acquire first feature data of multiple surface Q-value prediction points in the target work area; wherein, the first feature data includes at least the east coordinate, north coordinate, surface velocity, and surface velocity fitting feature of the surface Q-value prediction points; the surface velocity fitting feature is obtained by calculating the surface velocity in the first feature data by taking the power of 2.

2. The second acquisition module is used to obtain multiple sets of prediction input data based on the first feature data of the multiple surface Q-value prediction points, including: for each of the first feature data of the surface Q-value prediction points, performing the following processing: normalizing the first feature data; and using the normalized first feature data as a set of prediction input data. The third acquisition module is used to obtain the predicted values ​​of the surface Q values ​​of the plurality of surface Q value prediction points based on the plurality of sets of predicted input data and using a surface Q-value neural network prediction model, including: for each surface Q value prediction point, performing the following processing: inputting the predicted input data of the surface Q value prediction point into the surface Q value neural network prediction model to obtain a first predicted value; performing inverse normalization processing on the first predicted value to obtain the predicted value of the surface Q value of the surface Q value prediction point; A module is established to establish the surface Q-field of the target work area based on the predicted surface Q-values ​​of the multiple surface Q-value prediction points and the surface Q-values ​​of the multiple surface Q-value survey points of the target work area. This includes: using a spatial interpolation algorithm to obtain the surface Q-values ​​of the remaining locations in the target work area based on the predicted surface Q-values ​​of the multiple surface Q-value prediction points and the surface Q-values ​​of the multiple surface Q-value survey points of the target work area; and using the surface Q-values ​​of all locations in the target work area to establish the surface Q-field of the target work area.

6. An electronic device comprising a memory and a processor, the memory storing a computer program, the processor executing the method as described in any one of claims 1 to 5 when running the program.

7. A storage medium for storing a computer-readable program, which, when executed, performs the method as described in any one of claims 1 to 5.

Images