Elastic parameter determination method and device, electronic equipment and storage medium

Abstract

The invention discloses an elastic parameter determination method and device, electronic equipment and a storage medium. The method comprises the steps that first seismic data and first initial priori knowledge in a target area are acquired, the first seismic data are seismic data obtained by conducting seismic detection on the target area, and the first initial priori knowledge is initial cognitive information of geological features in the target area; constructing a first prestack angle gather in the target area based on the first seismic data; according to a first relation, a first prestack angle gather and first initial prior knowledge which are constructed in advance, a first elastic parameter set corresponding to the target area is determined, the first relation is a nonlinear mapping relation between the prestack angle gather and the elastic parameter set, and the elastic parameter set comprises the longitudinal wave speed, the transverse wave speed and the geological density. By adopting the technical scheme of the invention, the first elastic parameter group corresponding to the finally determined target area has good stability and uniqueness.

Description

Technical Field

[0001] This invention relates to the field of energy exploration technology, and in particular to a method, apparatus, electronic device, and storage medium for determining elastic parameters. Background Technology

[0002] Accurate measurement of earthquake elastic parameters, such as P-wave velocity, S-wave velocity, and density, is crucial for a deeper understanding of geological structures, interpretation of seismic data, and precise description of reservoir characteristics.

[0003] AVO inversion technology is used to estimate the elastic parameters of geophysical properties. Transforming real pre-stack data into meaningful elastic parameter representations is a complex inverse problem. However, limited bandwidth, incomplete data coverage, and noise interference introduce uncertainties into the inversion process, leading to insufficient stability and uniqueness of seismic inversion results. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for determining elastic parameters to address the problems of insufficient stability and uniqueness of seismic inversion results.

[0005] According to one aspect of the present invention, a method for determining elastic parameters is provided, the method comprising:

[0006] Acquire the first seismic data and the first initial prior knowledge within the target area. The first seismic data is the seismic data obtained by seismic detection in the target area, and the first initial prior knowledge is the initial cognitive information about the geological features within the target area.

[0007] Based on the first seismic data, construct the first pre-stack angle gather within the target area;

[0008] Based on the pre-structured first relation, the first pre-stack angle gather, and the first initial prior knowledge, the first set of elastic parameters corresponding to the target area is determined. The first relation is a nonlinear mapping relationship between the pre-stack angle gather and the set of elastic parameters. The set of elastic parameters includes P-wave velocity, S-wave velocity, and geological density.

[0009] According to another aspect of the present invention, an elastic parameter determining device is provided, the device comprising:

[0010] The earthquake data acquisition module is used to acquire the first earthquake data and the first initial prior knowledge within the target area. The first earthquake data is the earthquake data obtained by earthquake detection in the target area, and the first initial prior knowledge is the initial cognitive information on the geological features within the target area.

[0011] The corner gather determination module is used to construct the first pre-stack corner gather within the target area based on the first seismic data;

[0012] The elastic parameter acquisition module is used to determine the first set of elastic parameters corresponding to the target area based on the pre-structured first relationship, the first pre-stack angle gather, and the first initial prior knowledge. The first relationship is a nonlinear mapping relationship between the pre-stack angle gather and the elastic parameter set. The elastic parameter set includes P-wave velocity, S-wave velocity, and geological density.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory that is communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the elastic parameter determination method of any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the elastic parameter determination method of any embodiment of the present invention.

[0018] The technical solution of this invention involves acquiring first seismic data and first initial prior knowledge within a target area; constructing a first pre-stack angle gather within the target area based on the first seismic data; and determining a first set of elastic parameters corresponding to the target area according to a pre-structured first relationship, the first pre-stack angle gather, and the first initial prior knowledge. The first relationship is a nonlinear mapping relationship between the pre-stack angle gather and the elastic parameter set, which includes P-wave velocity, S-wave velocity, and geological density. This ensures that the final first set of elastic parameters better matches the actual situation within the target area, thereby giving the final determined first set of elastic parameters corresponding to the target area good stability and uniqueness.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1This is a flowchart of a method for determining elastic parameters according to Embodiment 1 of the present invention;

[0022] Figure 2 This is a schematic diagram of the pre-stack angle gather at a first angle according to Embodiment 1 of the present invention;

[0023] Figure 3 This is a schematic diagram of the pre-stack angle gather at the second angle according to Embodiment 1 of the present invention;

[0024] Figure 4 This is a schematic diagram of the pre-stack angle gather at the third angle according to Embodiment 1 of the present invention;

[0025] Figure 5 This is a flowchart of another method for determining elastic parameters provided in Embodiment 2 of the present invention;

[0026] Figure 6 This is a schematic diagram of an elastic parameter determining device according to Embodiment 3 of the present invention;

[0027] Figure 7 This is a schematic diagram of the structure of an electronic device that implements the elastic parameter determination method of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Example 1

[0031] Figure 1This is a flowchart of a method for determining elastic parameters according to Embodiment 1 of the present invention. This embodiment is applicable to situations where a group of elastic parameters needs to be determined. This method can be executed by an elastic parameter determining device, which can be implemented in hardware and / or software. This device can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0032] S110. Obtain the first earthquake data and the first initial prior knowledge within the target area. The first earthquake data is the earthquake data obtained by earthquake detection in the target area, and the first initial prior knowledge is the initial cognitive information on the geological features within the target area.

[0033] Seismic data can be information on seismic activity within a target area obtained through various seismic monitoring methods. Initial prior knowledge, in this application, can be understood as initial cognitive information about the geological features of a certain area.

[0034] The determination of the first seismic data and the first initial prior knowledge within the target area can be obtained by reviewing previous exploration records of the target area or conducting seismic tests on the target area, and this application does not impose any restrictions on this.

[0035] S120. Based on the first seismic data, construct the first pre-stack angle gather within the target area.

[0036] A pre-stack angle gather can be a dataset composed of multiple seismic traces arranged according to different incident angles or offsets. The first pre-stack angle gather can be synthesized from the first seismic data.

[0037] Accurate measurement of seismic elastic parameters, such as P-wave velocity, S-wave velocity, and density, is crucial for a deep understanding of geological structure, interpretation of seismic data, and precise description of reservoir characteristics. AVO inversion technology is used to estimate the elastic parameters of geophysical properties; transforming real pre-stack data into a meaningful representation of elastic parameters is a complex inverse problem. Therefore, the inversion of pre-stack corner gathers often requires the prediction of elastic parameters using these gathers. This necessitates the synthesis of the first pre-stack corner gathers using the first seismic data.

[0038] S130. Based on the pre-structured first relationship, the first pre-stack angle gather, and the first initial prior knowledge, determine the first set of elastic parameters corresponding to the target area. The first relationship is the nonlinear mapping relationship between the pre-stack angle gather and the set of elastic parameters. The set of elastic parameters includes P-wave velocity, S-wave velocity, and geological density.

[0039] The first relationship can be a predetermined nonlinear mapping between the elastic parameter set and the pre-stack angle gather.

[0040] By using the first pre-stack angle gather and the first relation, the elastic parameter set corresponding to the target region can be initially determined. Then, by using the first initial prior knowledge to optimize the elastic parameter set, the first elastic parameter set corresponding to the target region can be obtained.

[0041] By using the pre-structured first relation, the first pre-stack angle gather, and the first initial prior knowledge, the first set of elastic parameters corresponding to the target region is determined, so that the final first set of elastic parameters can better match the actual situation in the target region, thereby making the final determined first set of elastic parameters corresponding to the target region have good stability and uniqueness.

[0042] Optionally, the first relationship can be determined using a feature-based model.

[0043] In one alternative approach, the process of determining the first relationship may include steps A1-A5:

[0044] Step A1: Determine the second earthquake data, the second initial prior knowledge, and the second set of elastic parameters. The second earthquake data is the earthquake data within the sample area, the second set of elastic parameters is the set of elastic parameters for the sample area, the sample area is the area where the earthquake data and the set of elastic parameters have been determined, and the second initial prior knowledge is the initial prior knowledge for the sample area.

[0045] Step A2: Based on the second seismic data, determine the pre-stack angle gathers within the sample area.

[0046] Step A3: Determine the residual hybrid convolutional blocks in the model through feature determination, perform convolution and nonlinear transformation on the pre-stack corner gathers of the samples, and send the processing results to the next residual hybrid convolutional block for convolution and nonlinear transformation processing until the number of nonlinear transformation processing reaches a preset number to obtain the features of the first sample data. The number of residual hybrid convolutional blocks in the feature determination model is a preset number, and the residual hybrid convolutional blocks are connected in series. The output of the previous residual hybrid convolutional block is the input of the last residual hybrid convolutional block.

[0047] Step A4: Combine the second initial prior knowledge with the features of the first sample data to obtain the second relationship. The second relationship is the nonlinear mapping relationship between the sample pre-stack angle gather and the elastic parameter set determined when the feature determination model is trained.

[0048] Step A5: Based on the second set of elastic parameters and the pre-stack angle gather of the samples, adjust the initial second relation to obtain the first relation.

[0049] The second set of seismic data can be seismic data within the sample area. The second set of elastic parameters is the set of elastic parameters for the sample area, which is an area where seismic data and elastic parameter sets are already known. The second set of initial prior knowledge is the initial prior knowledge for the sample area.

[0050] After obtaining the second earthquake data, a sample pre-stack corner gather corresponding to the second earthquake data is generated. The sample pre-stack corner gather is then convolved using residual hybrid convolutional blocks in the feature determination model, thereby determining the corresponding first sample data features from the sample pre-stack corner gather.

[0051] To determine the first sample data feature from the pre-stack corner gather, it needs to be processed by at least one residual hybrid convolutional block. Each residual hybrid convolutional block performs convolution and non-linear transformations on the input data. These residual hybrid convolutional blocks are connected in series; that is, the output of one residual hybrid convolutional block serves as the input to the next. The pre-stack corner gather serves as the input to the first residual hybrid convolutional block, and after processing by at least one residual hybrid convolutional block, the first sample data feature is generated.

[0052] Since the second initial prior knowledge is the initial prior knowledge of the sample region, it can be combined with the features of the first sample data. Thus, when determining the data features, the initial prior knowledge can be obtained simultaneously, thereby obtaining the second relation.

[0053] To ensure the accuracy of the second relation, after obtaining the second relation, the initial second relation is adjusted using the second elastic parameter set and the sample pre-stack angle gather to obtain the final first relation.

[0054] By determining the second set of seismic data, the second set of initial prior knowledge, and the second set of elastic parameters, and based on the second set of seismic data, the pre-stack corner gathers within the sample area are determined. The sample pre-stack corner gathers are then convolved and nonlinearly transformed using residual hybrid convolutional blocks in the feature determination model. The processing results are then sent to the next residual hybrid convolutional block for further convolution and nonlinear transformation until the number of nonlinear transformations reaches a preset number, thus obtaining the first set of sample data features. The second set of initial prior knowledge is combined with the first set of sample data features to obtain the second relation. Finally, based on the second set of elastic parameters and the sample pre-stack corner gathers, the initial second relation is adjusted to obtain the first relation. This ensures that the final determined first relation is more accurate and better reflects the actual situation within the target area, thereby improving the stability and uniqueness of the final determined set of elastic parameters.

[0055] In one alternative approach, determining the pre-stack angle gathers within the sample area based on the second seismic data may include steps B1-B2:

[0056] Step B1: Based on the second earthquake data, determine the seismic wavelet and the seismic wavelet reflectivity at various angles.

[0057] Step B2: Based on the seismic wavelet and the seismic wavelet reflectivity at various angles, determine the pre-stack angle gathers within the sample area.

[0058] For pre-stack seismic inversion, the method to solve the inversion problem is to predict the elastic parameter set using pre-stack angle gathers. The forward modeling process for pre-stack seismic inversion is as follows:

[0059] d = g(m) + n;

[0060] In the formula, g represents the forward modeling operator; n represents the noise component; m represents the set of elastic parameters, namely the P-wave velocity, S-wave velocity, and density; and d represents the pre-stack angle gather.

[0061] See Figure 2 , Figure 3 as well as Figure 4 The figure shows schematic diagrams of pre-stack angle gathers at the first, second, and third angles, respectively. It should be noted that pre-stack angle gathers are not limited to only three angles; these are used as examples. In the forward modeling operator g, the exact Zoeppritz equations are used to establish the relationship between the seismic wavelet reflectivity and the elastic parameter set at each angle, and the synthetic data are simulated. Therefore, the pre-stack angle gather d(θ) can be expressed as:

[0062] d(θ)=W(r)*R(m,θ)+n(θ);

[0063] Where W(r) represents the seismic wavelet; * represents the convolution operation; and R(m, θ) represents the seismic wavelet reflectivity related to the angle θ.

[0064] The exact Zoeppritz equation can be used to describe the reflection and transmission coefficients of seismic waves at the interface between two different media.

[0065] By using the second seismic data, the seismic wavelet and the seismic wavelet reflectivity at various angles are determined. Based on the seismic wavelet and the seismic wavelet reflectivity at various angles, the pre-stack angle gathers of the sample area are determined, making the final pre-stack angle gathers of the sample area more accurate. This avoids the problem that a large error in the pre-stack angle gathers of the sample leads to a large error in the final determination of the first relation.

[0066] From given pre-stack data, based on the inversion operator Estimating the objective function l of the elastic parameter set inv for:

[0067]

[0068] Furthermore, by introducing a second initial prior knowledge, constraints can be imposed on the objective function, thereby obtaining an updated objective function:

[0069]

[0070] In the formula, m0 represents the second initial prior knowledge.

[0071] In one alternative approach, combining the second initial prior knowledge with the features of the first sample data to obtain the second relation may include steps C1-C4:

[0072] Step C1: Determine the patch embedding layer in the model through feature determination, perform position encoding on the features of the first sample data, and obtain at least one sample encoding result.

[0073] Step C2: Determine the seismic data feature extraction block in the model through feature identification, extract features from the coding results of each sample, and obtain the second sample data features.

[0074] Step C3: Determine the normalization layer in the model through features, and normalize the features of the second sample data to obtain the normalization result.

[0075] Step C4: Combine the normalization result with the second initial prior knowledge to obtain the second relation.

[0076] After obtaining the features of the first sample data, the patch embedding layer in the feature determination model will be used to encode the location of the features of the first sample data. In this process, the features of the first sample data will be divided into multiple sub-samples. Each sub-sample will carry location information and will be added to the patch embedding layer for encoding, thereby obtaining at least one sample encoding result.

[0077] The seismic data feature extraction block extracts key information from the sample encoding results and performs layer normalization to reduce error accumulation caused by covariate shifting. The seismic data feature extraction block includes a multi-head attention block, composed of multiple self-attention blocks, which allows for greater focus on the embedded vector. Then, a random depth dropout layer from the seismic data feature extraction block is used to mask the random tensor to prevent overfitting, ultimately generating the second sample data features.

[0078] The generated second sample data features are input into the normalization layer in the feature determination model to normalize the second sample data features, thereby improving the convergence speed of the model and obtaining the normalization result. Finally, the normalization result is combined with the second initial prior knowledge to obtain the second relation.

[0079] By using the patch embedding layer in the feature determination model, the features of the first sample data are positionally encoded to obtain at least one sample encoding result. Then, through the seismic data feature extraction block in the feature determination model, features are extracted from each sample encoding result to obtain the features of the second sample data. Finally, through the normalization layer in the feature determination model, the features of the second sample data are normalized to obtain a normalized result. This normalized result is then combined with the second initial prior knowledge to obtain a second relation, thereby improving the accuracy of the final obtained second relation and thus enhancing the computational precision of the system.

[0080] In one alternative approach, residual hybrid convolutional blocks in the model are determined by feature identification, and the sample pre-stack corner gathers are convolved and nonlinearly transformed, which may include D1-D3:

[0081] Step D1: Perform convolution processing on the sample pre-stack corner gather through the one-dimensional convolution layer in the residual hybrid convolution block to obtain the sample convolution result.

[0082] Step D2: Integrate the sample convolution results through the residual connection mechanism to obtain the sample integration result.

[0083] Step D3: Perform nonlinear transformation on the sample integration result through the nonlinear transformation function layer of Gaussian error linear unit in the residual mixing convolution block.

[0084] The residual connection mechanism, also known as the residual connection mechanism, is based on the idea of ​​adding a direct connection to the neural network, which connects the input directly to the subsequent layers, making it easier for the network to learn the residual mapping between the input and the output.

[0085] Traditional neural networks transmit information and extract features by stacking layers. However, as network depth increases, problems such as vanishing or exploding gradients may occur, making the network difficult to train. Residual connections, by directly passing input information to subsequent layers, can effectively alleviate the vanishing gradient problem, enabling the network to learn deeper feature representations more easily.

[0086] After the sample pre-stack corner gathers are input into the residual hybrid convolutional block, the sample pre-stack corner gathers are convolved by a one-dimensional convolutional layer in the residual hybrid convolutional block to obtain the sample convolution result. Information is effectively integrated through the residual connection mechanism. Compared with traditional convolution operations, this method can better capture global features and effectively reduce the risk of overfitting. Furthermore, the residual hybrid convolutional block utilizes a Gaussian error linear unit activation function layer to transform the linear representation into a non-linear representation, further enhancing the feature representation capability.

[0087] This embodiment establishes a complex nonlinear mapping relationship from pre-stack angle gathers to various elastic parameters. During training, this mapping relationship is continuously optimized by minimizing the error between each estimated elastic parameter and its corresponding label. To efficiently and accurately invert P-wave velocity, S-wave velocity, and density, this invention designs a hybrid loss function in the inversion branch, including a function with L1 norm and mean squared error (MSE), which can be expressed as:

[0088]

[0089] k is a constant, M is the number of training samples, and y and y' are the target and estimated elasticity parameter sets, respectively.

[0090] In this embodiment, synthetic data is simulated based on the characteristic distribution of actual data, and the model trained from the synthetic data can be successfully transferred to actual data. This reduces the dependence on well data and improves the accuracy of elastic parameter inversion.

[0091] According to the technical solution of the present invention, first seismic data and first initial prior knowledge within the target area are acquired; based on the first seismic data, a first pre-stack angle gather within the target area is constructed; according to the pre-structured first relationship, the first pre-stack angle gather, and the first initial prior knowledge, a first set of elastic parameters corresponding to the target area is determined. The first relationship is a nonlinear mapping relationship between the pre-stack angle gather and the elastic parameter set. The elastic parameter set includes P-wave velocity, S-wave velocity, and geological density, so that the final first set of elastic parameters can better conform to the actual situation within the target area, thereby making the final determined first set of elastic parameters corresponding to the target area have good stability and uniqueness.

[0092] Example 2

[0093] Figure 5 This invention provides a flowchart of another method for determining elastic parameters. This embodiment further optimizes the process of constructing the first pre-stack angle gather within the target area based on the first seismic data in the aforementioned embodiments. This embodiment can be combined with various optional schemes in one or more of the above embodiments. Figure 5 As shown, the method for determining the elastic parameters in this embodiment may include the following steps:

[0094] S210, Obtain the first seismic data and the first initial prior knowledge within the target area.

[0095] Optionally, the process for determining the first initial prior knowledge includes:

[0096] By performing differential logging of geological structures in the target area, the first initial prior knowledge is obtained.

[0097] Geological structure directional logging difference refers to the difference data calculated by measuring and comparing different logging parameters during the geological structure directional logging process. These differences can reflect the characteristics and changes of underground geological structures.

[0098] Therefore, the initial prior knowledge can be obtained by performing geological structure-guided logging difference processing on the target area.

[0099] By performing geological structure-guided logging differential processing on the target area, the first initial prior knowledge can be obtained, which can make the final first initial prior knowledge more consistent with the actual situation in the target area, thereby reducing systematic calculation errors.

[0100] S220. Using the first earthquake data, determine the seismic wavelet of the target area and the seismic wavelet reflectivity at different angles.

[0101] S230. Based on the seismic wavelet of the target area and the seismic wavelet reflectivity at different angles, determine the first pre-stack angle gather.

[0102] S240. Based on the pre-structured first relationship, the first pre-stack angle gather, and the first initial prior knowledge, determine the first set of elastic parameters corresponding to the target area. The first relationship is the nonlinear mapping relationship between the pre-stack angle gather and the set of elastic parameters. The set of elastic parameters includes P-wave velocity, S-wave velocity, and geological density.

[0103] According to the technical solution of the present invention, the first seismic data and the first initial prior knowledge within the target area are acquired; the first pre-stack angle gather is determined based on the seismic wavelet of the target area and the seismic wavelet reflectivity at different angles; the first pre-stack angle gather is determined based on the seismic wavelet of the target area and the seismic wavelet reflectivity at different angles; and finally, the first elastic parameter set corresponding to the target area is determined according to the pre-structured first relationship, the first pre-stack angle gather, and the first initial prior knowledge, so that the finally determined first elastic parameter set can be more accurate.

[0104] Example 3

[0105] Figure 6 This invention provides a structural block diagram of an elastic parameter determination device, applicable to situations requiring the determination of a set of elastic parameters. This elastic parameter determination device can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 6 As shown, the elastic parameter determination device of this embodiment may include: a seismic data acquisition module 310, an angle gather determination module 320, and an elastic parameter acquisition module 330. Wherein:

[0106] The earthquake data acquisition module 310 is used to acquire the first earthquake data and the first initial prior knowledge within the target area. The first earthquake data is the earthquake data obtained by earthquake detection in the target area, and the first initial prior knowledge is the initial cognitive information on the geological features within the target area.

[0107] The corner gather determination module 320 is used to construct the first pre-stack corner gather within the target area based on the first seismic data;

[0108] The elastic parameter acquisition module 330 is used to determine the first set of elastic parameters corresponding to the target area based on the pre-structured first relationship, the first pre-stack angle gather, and the first initial prior knowledge. The first relationship is a nonlinear mapping relationship between the pre-stack angle gather and the elastic parameter set. The elastic parameter set includes P-wave velocity, S-wave velocity, and geological density.

[0109] Based on the above embodiments, optionally, the angle gather determination module 320 includes:

[0110] Using the first seismic data, the seismic wavelet of the target area and the seismic wavelet reflectivity at different angles were determined;

[0111] Based on the seismic wavelet of the target area and the seismic wavelet reflectivity at different angles, the first pre-stack angle gather is determined.

[0112] Based on the above embodiments, optionally, the first relationship can be determined using a feature determination model;

[0113] Correspondingly, the process of determining the first relation includes:

[0114] The second earthquake data, the second initial prior knowledge, and the second set of elastic parameters are determined. The second earthquake data are earthquake data within the sample area, the second set of elastic parameters are the elastic parameter set of the sample area, the sample area is the area where the earthquake data and elastic parameter set have been determined, and the second initial prior knowledge is the initial prior knowledge of the sample area.

[0115] Based on the second earthquake data, the pre-stack angle gathers of the samples within the sample area were determined;

[0116] The residual hybrid convolutional blocks in the feature determination model are convolved and nonlinearly transformed on the pre-stack corner gathers of the samples. The processing results are then sent to the next residual hybrid convolutional block for convolution and nonlinear transformation, until the number of nonlinear transformations reaches a preset number, thus obtaining the features of the first sample data. The number of residual hybrid convolutional blocks in the feature determination model is a preset number. The residual hybrid convolutional blocks are connected in series, and the output of the previous residual hybrid convolutional block is the input of the last residual hybrid convolutional block.

[0117] The second initial prior knowledge is combined with the features of the first sample data to obtain the second relationship. The second relationship is the nonlinear mapping relationship between the sample pre-stack angle gather and the elastic parameter set determined when the feature determination model is trained.

[0118] Based on the second set of elastic parameters and the pre-stack angle gather of the samples, the initial second relation is adjusted to obtain the first relation.

[0119] Based on the above embodiments, optionally, based on the second seismic data, the pre-stack angle gathers within the sample area are determined, including:

[0120] Based on the second earthquake data, the seismic wavelet and the seismic wavelet reflectivity at various angles were determined;

[0121] Based on the seismic wavelet and the seismic wavelet reflectivity at various angles, the pre-stack angle gathers of the sample area are determined.

[0122] Based on the above embodiments, optionally, the second initial prior knowledge is combined with the features of the first sample data to obtain a second relationship, including:

[0123] By determining the patch embedding layer in the feature determination model, the features of the first sample data are positionally encoded to obtain at least one sample encoding result;

[0124] By identifying the seismic data feature extraction blocks in the feature determination model, feature extraction is performed on the coding results of each sample to obtain the second sample data features;

[0125] By determining the normalization layer in the feature-based model, the features of the second sample data are normalized to obtain the normalization result.

[0126] The normalization result is combined with the second initial prior knowledge to obtain the second relation.

[0127] Based on the above embodiments, optionally, residual hybrid convolutional blocks in the model are determined by feature identification, and convolution and nonlinear transformation processing is performed on the pre-stack corner gathers of the samples, including:

[0128] The sample pre-stack corner gather is convolved by a one-dimensional convolutional layer in the residual hybrid convolutional block to obtain the sample convolution result.

[0129] By using the residual connection mechanism, the sample convolution results are integrated to obtain the sample integration result;

[0130] The nonlinear transformation of the sample integration result is performed through the nonlinear transformation function layer of Gaussian error linear unit in the residual mixing convolution block.

[0131] Based on the above embodiments, optionally, the process for determining the first initial prior knowledge includes:

[0132] By performing differential logging of geological structures in the target area, the first initial prior knowledge is obtained.

[0133] The elastic parameter determination device provided in the embodiments of the present invention can execute the elastic parameter determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0134] Example 4

[0135] Figure 7 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0136] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0137] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0138] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the elastic parameter determination method.

[0139] In some embodiments, the resilience parameter determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the resilience parameter determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the resilience parameter determination method by any other suitable means (e.g., by means of firmware).

[0140] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0142] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0143] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0144] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0145] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0146] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0147] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining elastic parameters, characterized in that, include: Acquire first seismic data and first initial prior knowledge within the target area. The first seismic data is seismic data obtained by seismic detection of the target area, and the first initial prior knowledge is initial cognitive information about the geological features within the target area. Based on the first seismic data, a first pre-stack angle gather is constructed within the target area; Based on the pre-structured first relationship, the first pre-stack angle gather, and the first initial prior knowledge, the first set of elastic parameters corresponding to the target region is determined. The first relationship is a nonlinear mapping relationship between the pre-stack angle gather and the set of elastic parameters, which includes P-wave velocity, S-wave velocity, and geological density.

2. The method according to claim 1, characterized in that, Based on the first seismic data, a first pre-stack angle gather is constructed within the target area, including: Using the first seismic data, the seismic wavelet of the target area and the seismic wavelet reflectivity at different angles are determined; Based on the seismic wavelet of the target area and the seismic wavelet reflectivity at different angles, the first pre-stack angle gather is determined.

3. The method according to claim 1, characterized in that, The first relationship is determined using a feature-based model; Accordingly, the process of determining the first relationship includes: Determine the second earthquake data, the second initial prior knowledge, and the second set of elastic parameters. The second earthquake data is the earthquake data within the sample area, the second set of elastic parameters is the set of elastic parameters for the sample area, the sample area is the area where the earthquake data and the set of elastic parameters have been determined, and the second initial prior knowledge is the initial prior knowledge for the sample area. Based on the second seismic data, determine the pre-stack angle gathers within the sample area; The residual hybrid convolutional blocks in the model are determined by the features. Convolution and nonlinear transformation are performed on the pre-stack corner gathers of the samples. The processing results are sent to the next residual hybrid convolutional block for convolution and nonlinear transformation, until the number of nonlinear transformations reaches a preset number, and the first sample data features are obtained. The number of residual hybrid convolutional blocks in the model determined by the features is a preset number. The residual hybrid convolutional blocks are connected in series, and the output of the previous residual hybrid convolutional block is the input of the last residual hybrid convolutional block. The second initial prior knowledge is combined with the features of the first sample data to obtain a second relationship. The second relationship is a nonlinear mapping relationship between the sample pre-stack angle gather and the elastic parameter set, which is determined when the feature determination model is trained. Based on the second set of elastic parameters and the sample pre-stack angle gather, the initial second relation is adjusted to obtain the first relation.

4. The method according to claim 3, characterized in that, Based on the second seismic data, the pre-stack angle gathers within the sample area are determined, including: Based on the second seismic data, the seismic wavelet and the seismic wavelet reflectivity at various angles are determined; Based on the seismic wavelet and the seismic wavelet reflectivity at various angles, the pre-stack angle gathers of the samples within the sample area are determined.

5. The method according to claim 3, characterized in that, The second initial prior knowledge is combined with the features of the first sample data to obtain the second relationship, including: The patch embedding layer in the model is determined by the features, and the first sample data features are positionally encoded to obtain at least one sample encoding result. By determining the seismic data feature extraction block in the model based on the aforementioned features, feature extraction is performed on the encoding results of each sample to obtain the second sample data features; The normalization layer in the model is determined by the aforementioned features, and the features of the second sample data are normalized to obtain the normalization result. The normalization result is combined with the second initial prior knowledge to obtain the second relationship.

6. The method according to claim 3, characterized in that, The residual hybrid convolutional blocks in the model are determined based on the aforementioned features. Convolution and nonlinear transformation are then performed on the pre-stack corner gathers of the samples, including: The sample pre-stack corner gather is convolved by a one-dimensional convolutional layer in the residual hybrid convolutional block to obtain the sample convolution result; The sample convolution results are integrated using the residual connection mechanism to obtain the sample integration result; The sample integration result is nonlinearly transformed by the nonlinear transformation function layer of the Gaussian error linear unit in the residual hybrid convolution block.

7. The method according to claim 1, characterized in that, The process of determining the first initial prior knowledge includes: The first initial prior knowledge is obtained by performing geological structure-guided logging difference processing on the target area.

8. A device for determining elastic parameters, characterized in that, include: The earthquake data acquisition module is used to acquire first earthquake data and first initial prior knowledge within a target area. The first earthquake data is earthquake data obtained by earthquake detection in the target area, and the first initial prior knowledge is initial cognitive information about the geological features within the target area. An angle gather determination module is used to construct a first pre-stack angle gather within the target area based on the first seismic data; The elastic parameter acquisition module is used to determine the first set of elastic parameters corresponding to the target area based on the pre-structured first relationship, the first pre-stack angle gather, and the first initial prior knowledge. The first relationship is a nonlinear mapping relationship between the pre-stack angle gather and the elastic parameter set, which includes P-wave velocity, S-wave velocity, and geological density.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the elastic parameter determination method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the elastic parameter determination method according to any one of claims 1-7.

Images