Seismic stratigraphic interpretation method, system and equipment for stratigraphic tip-out problem

Abstract

The invention belongs to the field of data analysis, particularly relates to a seismic stratum interpretation method, system and equipment for a stratum pinching problem, and aims to solve the problem of insufficient stratum prediction accuracy caused by neglecting multiple possibilities of stratum pinching in an area where the stratum pinching problem possibly occurs. The method comprises the steps of determining phase attribute jump point coordinates in three-dimensional seismic data, determining the number of overlapped jump points at each horizontal position, determining a three-dimensional seismic data block according to different numbers of the jump points, performing three-dimensional transformation on the three-dimensional seismic data block, clustering seismic channel data points after the three-dimensional transformation, and obtaining a clustering result; and determining a proximity relationship of different clustering clusters, determining a connection mode between clustering results of all different blocks based on the proximity relationship, and obtaining a plurality of explanation results of strata with probabilities to exist based on the connection mode. According to the method, multiple stratum interpretation results with the probability of existence can be determined, and the accuracy of stratum interpretation is improved.

Description

Background Art

[0002] In the related art, a horizontal layered data set of strata is pre-established, and the seismic attribute characteristics of the layer categories in the seismic data are learned by training a neural network to predict the structure and morphology of the strata. However, since the forward algorithm of this method requires the pre-design of the horizontal layered strata, and then the information such as folds and faults is added, it is impossible to synthesize a large amount of three-dimensional pinch-out strata information. In other words, it is impossible to determine whether there is a pinch-out stratum during the design of the horizontal layered strata, that is, it is difficult to create pinch-out stratum data of the meeting strata, resulting in the inability to accurately identify the pinch-out strata, which in turn leads to insufficient accuracy of the determined predicted strata.

[0003] Furthermore, in areas where formation pinch-out problems may occur, the existence of multiple possibilities for formation pinch-out is ignored, resulting in insufficient accuracy in formation prediction. Summary of the invention

[0004] In order to solve the above-mentioned problem in the prior art, i.e., ignoring the multiple possibilities of formation pinch-out and the problem of insufficient formation prediction accuracy, the present invention provides a seismic formation interpretation method for the formation pinch-out problem, the method comprising:

[0005] Determine the coordinates of phase attribute jump points in three-dimensional seismic data, wherein the jump points are used to mark seismic reflection events, and the seismic reflection events reflect the distribution of strata;

[0006] Determine the number of overlapping jump points at each horizontal position, and confirm the three-dimensional seismic data block according to the different numbers of the jump points, wherein the number of jump points in the same three-dimensional seismic data block is the same;

[0007] Perform three-dimensional transformation on three-dimensional seismic data blocks;

[0008] Clustering the seismic trace data points after three-dimensional transformation;

[0009] Based on the data points of the clustering results of all different blocks, project the data points of the same cluster cluster onto the same XY plane, find the first edge point on each XY plane of the block, and back-project the first edge point into the second edge point of the cluster cluster;

[0010] Based on the second edge points, determining a proximity relationship of the second edge points between clustering results of different blocks, wherein the proximity relationship represents the possibility that two stratigraphic sublayers corresponding to two clusters are continuous;

[0011] Based on the proximity relationship, confirm the connection mode between the clustering results of all different blocks;

[0012] Based on the connection method, a variety of possible formation interpretation results are obtained.

[0013] In some preferred embodiments, the first edge point of each cluster is determined by the following method:

[0014] In the clustering results of each block, the data points that do not have four adjacent data points at the same time are taken as the first edge points.

[0015] In some preferred embodiments, the proximity relationship of the second edge point is determined by the following method:

[0016] For the second edge point of each cluster, calculate the Euclidean distance between the second edge point of each other cluster, and calculate the Euclidean distance between the data points in the same cluster;

[0017] For each pairwise combination of clusters, select a set number of data point pairs with the shortest Euclidean distance;

[0018] If the Euclidean distance between the data point pair is less than a set multiple of the maximum value of the Euclidean distance between data points in the same cluster, the proximity relationship of the second edge point is considered to be probabilistic proximity, otherwise the proximity relationship is considered to be non-proximal.

[0019] In some preferred implementations, the step of confirming the connection between the clustering results of all different blocks based on the proximity relationship includes:

[0020] The continuous states between all the stratigraphic clustering results with probabilistic proximity are expressed as continuous and discontinuous respectively;

[0021] The continuous state between the clustering results of all different blocks and the stratigraphic interpretation results under all permutations and combinations are obtained, and multiple stratigraphic interpretation results with a high probability of existence are obtained.

[0022] In some preferred implementations, after clustering the three-dimensionally transformed seismic trace data points, the method further includes:

[0023] Based on the clustering results, for each layer category, determine whether there are different scattered points at the same position on the XY plane;

[0024] If there are no different scattered points at the same position on the XY plane, it is determined that the pinch-out stratum is effectively identified, and a step-by-step division result of the first stratum is obtained, wherein the pinch-out stratum is effectively identified, indicating that the three-dimensional scattered point coordinates of the transformed marker point and the stratum category division result of the stratum marker point are credible;

[0025] If there are different scattered points at the same position on the XY plane, according to the clustering result, each cluster cluster in each clustering result with different scattered points at the same position on the XY plane is traversed, and the stratigraphic landmark points corresponding to each cluster cluster are re-transformed into three-dimensional coordinates, and the first stratigraphic level-by-level division result of each cluster cluster is obtained through the adjusted clustering parameters until the second cluster clusters of the first stratigraphic level-by-level division results of all cluster clusters do not have different scattered points at the same position on the XY plane.

[0026] In some preferred embodiments, a three-dimensional transformation is performed on a three-dimensional seismic data block by using a PCA method.

[0027] In a second aspect of the present invention, a seismic interpretation system for the formation pinch-out problem is proposed, the system comprising: a jump point determination module, used to determine the coordinates of the phase attribute jump point in the three-dimensional seismic data, wherein the jump point is used to mark the seismic reflection event axis, and the seismic reflection event axis reflects the distribution of the formation;

[0028] A block division module is used to determine the number of overlapping jump points at each horizontal position, and confirm the three-dimensional seismic data block according to the different numbers of the jump points, wherein the number of jump points in the same three-dimensional seismic data block is the same;

[0029] A three-dimensional transformation module is used to perform three-dimensional transformation on three-dimensional seismic data blocks;

[0030] A clustering module is used to cluster the seismic trace data points after three-dimensional transformation;

[0031] A splicing module, for projecting the data points of the same cluster cluster onto the same XY plane based on the data points of the clustering results of all different blocks, finding the first edge point on each XY plane of the block, and back-projecting the first edge point into the second edge point of the cluster cluster;

[0032] Based on the second edge points, determining a proximity relationship of the second edge points between clustering results of different blocks, wherein the proximity relationship represents the possibility that two stratigraphic sublayers corresponding to two clusters are continuous;

[0033] Based on the proximity relationship, confirm the connection mode between the clustering results of all different blocks;

[0034] Based on the connection method, a variety of possible formation interpretation results are obtained.

[0035] According to a third aspect of the present invention, an electronic device is provided, comprising:

[0036] at least one processor; and

[0037] a memory communicatively connected to at least one of the processors; wherein,

[0038] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the seismic stratigraphic interpretation method for the stratigraphic pinch-out problem.

[0039] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the seismic stratigraphic interpretation method for the above-mentioned stratigraphic pinch-out problem.

[0040] Beneficial effects of the present invention:

[0041] (1) The present invention divides the three-dimensional seismic data into different three-dimensional seismic data blocks by the number of overlapping jump points at each horizontal position, clusters each block separately, and then connects the clustering results, so as to determine multiple stratigraphic interpretation results with a probability of existence, thereby improving the accuracy of stratigraphic interpretation.

[0042] (2) Quantitatively reflect the multi-solution of seismic data. The stratigraphic interpretation of traditional seismic data is usually limited to a single solution. However, the present invention, through innovative stratigraphic division and evaluation methods, has for the first time realized the quantitative expression of the multi-solution of seismic data. Multi-solution is an important manifestation of the inherent uncertainty in seismic interpretation. By quantitatively analyzing multiple possibilities, it can help geological interpreters intuitively grasp the distribution and change laws of stratigraphic layers under different assumptions, thereby providing a scientific basis for more complex geological scenarios.

[0043] (3) Significantly improve the efficiency and accuracy of stratigraphic division. The present invention decomposes the calculation process of stratigraphic interpretation into smaller modular tasks through the algorithm innovation of block division and splicing, which greatly reduces the complexity of large-scale data processing. This method not only improves the interpretation efficiency, but also effectively reduces the interpretation error caused by complex structures. At the same time, the algorithm has a built-in multi-solution evaluation module, which can dynamically optimize the stratigraphic division to ensure that the stratigraphic division is more accurate and reliable.

[0044] (4) It is easy to obtain multiple stratigraphic interpretation results. In view of the uncertainty caused by the stratigraphic pinch-out problem, the present invention can generate a set of stratigraphic division results with multiple solutions and provide geological interpreters with multiple potential stratigraphic interpretation models. Through the rapid visualization of multiple solution results, interpreters can select the best solution according to specific geological background requirements, thereby avoiding the limitations of a single solution and improving the flexibility and applicability of stratigraphic interpretation.

[0045] (5) Effectively avoid the layer-crossing errors in traditional algorithms. Traditional stratigraphic interpretation algorithms often cause layer-crossing errors due to stratigraphic pinch-out, faults or complex structures, resulting in the geological model not being consistent with the actual situation. The present invention solves the layer-crossing problem at the data level through block division and splicing strategies, making the stratigraphic interpretation more continuous and consistent. Especially in complex structural areas, this method significantly reduces the error rate of the interpretation results, laying a solid foundation for subsequent reservoir prediction and oil and gas accumulation research. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0047] Figure 1 is a flow chart of a seismic stratum interpretation method for a stratum pinch-out problem in an embodiment of the present disclosure;

[0048] Figure 2 is a seismic profile in three-dimensional seismic data in an embodiment of the present disclosure;

[0049] Figure 3 is a phase attribute in three-dimensional seismic data in an embodiment of the present disclosure;

[0050] Figure 4 is a determined jump point distribution diagram in an embodiment of the present disclosure;

[0051] Figure 5 It is a conceptual diagram of the stratum conditions that can be represented by dividing the seismic data blocks based on the number of jump points at the same level in the embodiment of the present disclosure;

[0052] Figure 6 It is an effect diagram of the stratum conditions that can be represented by dividing the seismic data blocks based on the number of jump points at the same level in the embodiment of the present disclosure;

[0053] Figure 7 It is a diagram showing the clustering results of different seismic data blocks in the embodiment of the present disclosure.

[0054] Figure 8 It is an effect diagram of projecting data points of the same cluster onto the same XY plane in an embodiment of the present disclosure.

[0055] Fig. 9 It is a conceptual diagram of the stratigraphic interpretation that can be made for a block by dividing the seismic data into blocks based on the number of jump points at the same level in the embodiment of the present disclosure.

[0056] Fig.10 It is a schematic diagram of the effect of connecting the stratigraphic interpretation results of multiple blocks in the embodiment of the present disclosure.

[0057] Fig.11 It is a schematic diagram of the interpretation results of various formations with different probability of existence obtained in the embodiments of the present disclosure. DETAILED DESCRIPTION

[0058] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0059] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0060] Existing seismic stratigraphic interpretation methods can be roughly divided into three categories: (1) Image-based stratigraphic tracking methods. The seismic profile is processed as a series of two-dimensional images. For example, the seismic profile image edge detection method is used, and the neural network is combined with image classification technology. The CNN deep convolutional neural network realizes synchronous automatic multi-layer tracking, and the horizon is manually marked on the image. The neural network is trained to learn the characteristics of seismic data and then predict the stratigraphic layer. (2) Layer tracking methods based on seismic attributes. For example, the layer is tracked using seismic phase attributes. (3) Layer tracing methods based on seismic coherence. This method can automatically track the phase axis based on the similar amplitudes of adjacent channels in the same field of view. In this method, some layer points are manually selected as constraint points, and then the complete layer is obtained by interpolation.

[0061] In order to more clearly explain the seismic stratigraphic interpretation method for the stratigraphic pinch-out problem of the present invention, the following is combined with Figure 1 Each step in the embodiment of the present invention is described in detail.

[0062] The seismic stratigraphic interpretation method for the stratigraphic pinch-out problem of the first embodiment of the present invention includes steps S11 to S14, each of which is described in detail as follows:

[0063] In step S11, the coordinates of the phase attribute jump point in the three-dimensional seismic data are determined, wherein the jump point is used to mark the seismic reflection event axis, and the seismic reflection event axis reflects the distribution of the stratum;

[0064] The collected three-dimensional seismic data include n×n seismic waveform data, and each seismic waveform data is an m×1 vector.

[0065] For each seismic trace, the instantaneous phase attribute can be calculated by extracting the seismic waveform data seis(t) from the seismic data.

[0066] Compute Hilbert transform pairs based on seismic waveform data:

[0067]

[0068] * indicates convolution, and the integral is the Cauchy principal value integral.

[0069] The analytical signal for constructing seismic waveform data is:

[0070]

[0071] The instantaneous phase JX(t) is calculated based on the analytical signal:

[0072] JX(t)=AMP(t)e jθ(t) ;

[0073] t represents time, and AMP(t) represents instantaneous amplitude:

[0074]

[0075] θ(t) is the instantaneous phase:

[0076]

[0077] Each instantaneous phase is a discrete value, and the transition point time can be obtained through the differential algorithm:

[0078]

[0079] According to the plane coordinates (X, Y) of the seismic track, the three-dimensional coordinates (X, Y, TB(t)) of all the jump points of the seismic track can be obtained, X=1,2,3,…,n, Y=1,2,3,…,n.

[0080] Figure 2 and Figure 3 They are the seismic profile in 3D seismic data and the phase attributes in 3D seismic data, respectively.

[0081] In step S12, the number of overlapping jump points at each horizontal position is determined, and the three-dimensional seismic data block is confirmed according to the different numbers of the jump points, wherein the number of jump points in the same three-dimensional seismic data block is the same;

[0082] The coordinate distribution of the determined jump points is as follows: Figure 4 As shown. Figure 4From the content, we can see that in the phase attribute, a horizontal position may contain different numbers of phase attribute jump points in the seismic data. That is, it means that at this horizontal position (same X, Y coordinates), there may be different strata. Different strata may intersect. In order to determine the possible intersection, the three-dimensional seismic data can be divided into different seismic data blocks based on the number of overlapping jump points at each horizontal position. Different seismic data blocks have different numbers of jump points.

[0083] The data points of the clustering results for each block are represented by z i (z i1 =X,z i2 =Y,z i3 =TB(t)). Traverse each horizontal position and count the number of repetitions of the data point at the horizontal position. Take the case where the number of overlapping jump points at the horizontal position includes 1, 2, and 3 as an example.

[0084] When there is no other jump point z in all the jump point three-dimensional scattered coordinates i With z 1 Existence 11 =z i1 When 1 Insert the 3D seismic data block C with non-repeated scattered points 1 middle.

[0085] When among all the three-dimensional scattered coordinates of the jump points, there is only z 11 =z 21 And z 12 =z 22 When 1 、z 2 Insert 3D seismic data block C 2 middle.

[0086] When among all the three-dimensional scattered coordinates of the jump points, there is only z 11 =z 21 =z 31 And z 12 =z 22 =z 32 When 1 、z 2 、z 3 Put 3D seismic data block C 3 middle.

[0087] Different 3D seismic data blocks represent the possible number of strata at that horizontal position, such as Figure 5 and Figure 6 As shown, different situations of stratum distribution can be distinguished by dividing the seismic data into different three-dimensional seismic data blocks.

[0088] In step S13, a three-dimensional transformation is performed on the three-dimensional seismic data block;

[0089] In step S14, clustering the seismic trace data points after the three-dimensional transformation;

[0090] In this embodiment, the transformed landmarks can be clustered using the DBSCAN algorithm. Specifically:

[0091] Initialize the neighborhood of the DBSCAN algorithm ∈ = 0.1, MinPts = 10, and initialize the core object set Initialize the number of clusters k = 0, initialize the unvisited sample set Γ = D, and divide the clusters

[0092] Or use the adjusted clustering parameters to execute the subsequent DBSCAN algorithm.

[0093] Input transformed landmark point B = {B k＝1 ,B k＝2 ,…,B k＝shu} and execute it with the current clustering parameters:

[0094] Find the core object for each landmark:

[0095] For each transformed landmark point B k , find the corresponding neighborhood ∈ subsample set N ∈ (B k ):

[0096] N ∈ (B k )={B i ∈D|distance(B i , B j )≤∈};

[0097] If the number of samples in the subsample set satisfies |N ∈ (B k )|≥MinPts, sample B k Add core object sample set: Ω=Ω∪{B k};

[0098] If the core object collection Then the DBSCAN algorithm ends; otherwise, randomly select a core object B in the core object set Ω k , initialize the current cluster core object queue Ω cur = {B k}, initialize the category number p = p + 1, initialize the current cluster sample set C p = {B k}, update the unvisited sample set Γ = Γ-{B k}.

[0099] If the current cluster core object queue The current cluster C p After generation, update cluster partition C = {C 1 ,C 2 ,…,C p}, update the core object set Ω = Ω-C p , go to step (5). Otherwise update the core object set Ω = Ω - C p .

[0100] In the current cluster core object queue Ω cur Take out a core object o ′ , find all ∈ neighborhood subsample sets N through the neighborhood distance threshold ∈ ∈ (B k ′ ), let Δ=N ∈ (B k ′ )∩Γ, update the current cluster sample set C p =C p ∪Δ, update the unvisited sample set Γ=Γ-Δ, update Ω cur =Ω cur ∪(Δ∩Ω)-B k ′ .

[0101] Repeat the above steps to obtain cluster partition C = {C 1 ,C 2 ,…,C p}, get the current scatter point B according to C k Category L k , L k =C H , where B k ∈C H .

[0102] Output layer category vector: L.

[0103] If the further subdivision process has just started, b = 1, min(C 1 ,C 2 ,…,C p )=1;C={C 1 ,C 2 ,…,C p} is cluster division

[0104] If b>1, the new cluster partition Cnew={C 1 ,C 2 ,…,Cp}min(C 1 ,C 2 ,…,C p )=max(Lold)+1; L is the category vector corresponding to the scattered points. The clustering results of different seismic data blocks after division are as follows: Figure 7 shown.

[0105] In step S15, based on the data points of the clustering results of all different blocks, the data points of the same cluster are projected onto the same XY plane, the first edge point on each XY plane of the block is found, and the first edge point is back-projected as the second edge point of the cluster;

[0106] In step S16, based on the second edge point, a proximity relationship of the second edge point between the clustering results of different blocks is determined, wherein the proximity relationship represents the possibility that two stratigraphic sublayers corresponding to two clusters are continuous;

[0107] In step S17, based on the proximity relationship, the connection mode between the clustering results of all different blocks is confirmed;

[0108] In step S18, based on the connection mode, a plurality of interpretation results of formations with a high probability of existence are obtained.

[0109] In the embodiments of the present disclosure, different clusters are divided based on different properties, so it is impossible to connect the data points of different clusters in three-dimensional space. The present disclosure further illustrates the way of connecting the clustering results in the present disclosure through the following embodiments.

[0110] In one embodiment, the first edge point of each cluster is determined by the following method:

[0111] In step S21, based on the data points of the clustering results of all different blocks, the data points of the same cluster are projected onto the same XY plane. The effect of projecting the data points of the same cluster onto the same XY plane is as follows: Figure 8 As shown, from Figure 8 It can be seen that even if the data points of the clusters are projected on the same XY plane, there is a layer of edge points on the edge of the graph.

[0112] In step S22, in the clustering result of each block, the data points that do not have four adjacent data points at the same time are taken as the first edge points.

[0113] For example, for each block, the data point coordinate z in the clustering result i The first two dimensions of (z i1 ,z i2 )

[0114] Traverse each data point, for example, for point (z i1 ,z i2 ), determine whether there are four adjacent points in the p-th sublayer: (z i1 -1,z i2 )、(z i1 +1,z i2 )、(z i1 ,z i2 +1)、(z i1 ,z i2 -1)

[0115] If a data point has less than four neighboring points, then the data point is an edge point.

[0116] Through the above embodiments, it is possible to find the edge points of each stratum when clustering is completed according to phase attributes, which is helpful for subsequent connection of different stratum conditions so as to determine the spatial relationship between different strata and further determine whether there is a stratum pinch-out problem.

[0117] In one embodiment, the proximity relationship of the second edge point is determined by the following method:

[0118] In step S31, for the second edge point of each cluster, the Euclidean distance between the second edge point of each other cluster is calculated, and the Euclidean distance between the data points in the same cluster is calculated;

[0119] In step S32, for each pairwise combination of clusters, a set number of data point pairs with the shortest Euclidean distance are selected;

[0120] In step S33, if the Euclidean distance between the data point pairs is less than a set multiple of the maximum value of the Euclidean distance between data points in the same cluster, the proximity relationship of the second edge point is considered to be probabilistic proximity, otherwise the proximity relationship is considered to be non-proximal.

[0121] In one embodiment, the determining of the connection mode between the clustering results of all different blocks based on the proximity relationship includes:

[0122] The continuous states between all the stratigraphic clustering results with probabilistic proximity are expressed as continuous and discontinuous respectively;

[0123] The continuous state between the clustering results of all different blocks and the stratigraphic interpretation results under all permutations and combinations are obtained, and multiple stratigraphic interpretation results with a high probability of existence are obtained.

[0124] Through the above embodiments, the formation interpretation results that can be obtained include: Fig. 9 The concept of concentration in Fig. 9The result in the upper left corner is an intuitive result. Take each vertical strip area as an example, including 1, 2, 3, 2, 3, 2, 1 repeated strata. Then, in the corresponding position, the following may be made: Fig. 9 The possible stratigraphic interpretation results of the image other than the upper left image are shown in Figure 1. Fig.10 By finding the edge points and connecting them, we can finally get the following Fig.11 The described results include a variety of possible stratigraphic interpretations.

[0125] In one embodiment, after clustering the three-dimensionally transformed seismic trace data points, the method further includes:

[0126] Based on the clustering results, for each layer category, determine whether there are different scattered points at the same position on the XY plane;

[0127] If there are no different scattered points at the same position on the XY plane, it is determined that the pinch-out stratum is effectively identified, and a step-by-step division result of the first stratum is obtained, wherein the pinch-out stratum is effectively identified, indicating that the three-dimensional scattered point coordinates of the transformed marker point and the stratum category division result of the stratum marker point are credible;

[0128] If there are different scattered points at the same position on the XY plane, according to the clustering result, each cluster cluster in each clustering result with different scattered points at the same position on the XY plane is traversed, and the stratigraphic landmark points corresponding to each cluster cluster are re-transformed into three-dimensional coordinates, and the first stratigraphic level-by-level division result of each cluster cluster is obtained through the adjusted clustering parameters until the second cluster clusters of the first stratigraphic level-by-level division results of all cluster clusters do not have different scattered points at the same position on the XY plane.

[0129] In one embodiment, a three-dimensional transformation is performed on a three-dimensional seismic data block by using a PCA method.

[0130] Standardize the seismic data volume to obtain the standardized seismic data volume:

[0131]

[0132] BZ j represents the value of the jth dimension of the scattered points in the standardized seismic data volume, and shu represents the number of all scattered points.

[0133] Let Z represent the scattered points z in the seismic data volume ij The matrix composed of ZZ T The eigenvalue λ and eigenvector ξ of the 3*3 matrix

[0134] ZZ T ξ=λξ;

[0135] λ represents the eigenvalue matrix composed of three eigenvalues ​​along the diagonal, and ξ represents the eigenvector matrix composed of three eigenvectors arranged.

[0136] λ 1 ≥λ 2 ≥λ 3 Represent the eigenvalues ​​arranged from large to small, ξ 1 is the same as λ 1 The corresponding eigenvector, ξ 2 is the same as λ 2 The corresponding eigenvector, ξ 3 is the same as λ 3 The corresponding feature vector.

[0137] For each scattered point coordinate z i Perform coordinate projection;

[0138] B ik =z i ·ξ k ;

[0139] B ik Represents the coordinate of the kth dimension after the coordinate transformation of the i-th scattered point, z i represents the coordinates of the i-th scattered point in the original coordinate system, ξ k represents the kth eigenvector.

[0140] In the disclosed embodiment, compared with the method of clustering seismic data bodies to distinguish different strata in the related art, the present scheme can improve the accuracy of distinguishing different stratum categories by clustering data points that can clearly distinguish different stratum types after PCA conversion of stratum interface landmark points.

[0141] In an exemplary embodiment, the transformed landmarks are clustered using a DBSCAN algorithm.

[0142] Initialize the neighborhood of the DBSCAN algorithm ∈ = 0.1, MinPts = 10, and initialize the core object set Initialize the number of clusters k = 0, initialize the unvisited sample set Γ = D, and divide the clusters

[0143] Or use the adjusted clustering parameters to execute the subsequent DBSCAN algorithm.

[0144] Input transformed landmark point B = {B k＝1 ,B k＝2 ,…,B k＝shu} and execute it with the current clustering parameters:

[0145] Find the core object for each landmark:

[0146] For each transformed landmark point B k , find the corresponding neighborhood ∈ subsample set N ∈ (B k ):

[0147] N ∈ (B k )={B i ∈D|distance(B i , B j )≤∈};

[0148] If the number of samples in the subsample set satisfies |N ∈ (B k )|≥MinPts, sample B k Add core object sample set: Ω=Ω∪{B k};

[0149] If the core object collection Then the DBSCAN algorithm ends; otherwise, randomly select a core object B in the core object set Ω k , initialize the current cluster core object queue Ω cur = {B k}, initialize the category number p = p + 1, initialize the current cluster sample set C p = {B k}, update the unvisited sample set Γ = Γ-{B k}.

[0150] If the current cluster core object queue The current cluster C p After generation, update cluster partition C = {C 1 ,C 2 ,…,C p}, update the core object set Ω = Ω-C p , go to step (5). Otherwise update the core object set Ω = Ω - C p .

[0151] In the current cluster core object queue Ω cur Take out a core object o ′ , find all ∈ neighborhood subsample sets N through the neighborhood distance threshold ∈ ∈ (B k ′ ), let Δ=N ∈ (B k ′ )∩Γ, update the current cluster sample set C p =C p∪Δ, update the unvisited sample set Γ=Γ-Δ, update Ω cur =Ω cur ∪(Δ∩Ω)-B k ′ .

[0152] Repeat the above steps to obtain cluster partition C = {C 1 ,C 2 ,…,C p}, get the current scatter point B according to C k Category L k , L k =C H , where B k ∈C H .

[0153] Output layer category vector: L.

[0154] If the process of further subdivision has just begun, b = 1, min(C 1 ,C 2 ,…,C p )=1;C={C 1 ,C 2 ,…,C p} is cluster division

[0155] If b>1, the new cluster partition Cnew={C 1 ,C 2 ,…,C p}middle min(C 1 ,C 2 ,…,C p )=max(Lold)+1; L is the category vector corresponding to the scatter point.

[0156] In this embodiment, since it is difficult for the clustering algorithm to obtain accurate strata at one time, even if the processing method of this solution is adopted, two layers may still be clustered into one layer. By repeatedly adjusting the clustering parameters of this layer and clustering again, different stratum categories can be accurately divided into multiple layers. This solution determines whether there is a situation of mistaken clustering into one layer by the number of data points belonging to the same stratum category on the seismic trace.

[0157] Jump point coordinate z i (z i1 =X,z i2 =Y,z i3 =TB(t)), after coordinate transformation, it is B i (B i1 ,B i2 ,B i3 ), the corresponding category is L i =CH , where B i ∈C H .

[0158]

[0159]

[0160] In the formula, Q H is the number of scattered points on the same seismic trace in the Hth category.

[0161] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.

[0162] A seismic interpretation system for formation pinch-out problem according to a second embodiment of the present invention comprises: A jump point determination module is used to determine the coordinates of the phase attribute jump points in the three-dimensional seismic data, wherein the jump points are used to mark the seismic reflection event axes, and the seismic reflection event axes reflect the distribution of the strata;

[0163] A block division module is used to determine the number of overlapping jump points at each horizontal position, and confirm the three-dimensional seismic data block according to the different numbers of the jump points, wherein the number of jump points in the same three-dimensional seismic data block is the same;

[0164] A three-dimensional transformation module is used to perform three-dimensional transformation on three-dimensional seismic data blocks;

[0165] A clustering module is used to cluster the seismic trace data points after three-dimensional transformation;

[0166] A splicing module, for projecting the data points of the same cluster cluster onto the same XY plane based on the data points of the clustering results of all different blocks, finding the first edge point on each XY plane of the block, and back-projecting the first edge point into the second edge point of the cluster cluster;

[0167] Based on the second edge points, determining a proximity relationship of the second edge points between clustering results of different blocks, wherein the proximity relationship represents the possibility that two stratigraphic sublayers corresponding to two clusters are continuous;

[0168] Based on the proximity relationship, confirm the connection mode between the clustering results of all different blocks;

[0169] Based on the connection method, a variety of possible formation interpretation results are obtained.

[0170] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0171] It should be noted that the seismic interpretation system for the formation pinch-out problem provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations on the present invention.

[0172] An electronic device according to a third embodiment of the present invention includes:

[0173] at least one processor; and

[0174] a memory communicatively connected to at least one of the processors; wherein,

[0175] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the seismic interpretation method for the formation pinch-out problem.

[0176] A fourth embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the seismic interpretation method for the above-mentioned formation pinch-out problem.

[0177] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the storage device and processing device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0178] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0179] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.

[0180] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0181] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A seismic stratigraphic interpretation method for the stratigraphic pinch-out problem, characterized in that: Determine the coordinates of phase attribute jump points in three-dimensional seismic data, wherein the jump points are used to mark seismic reflection events, and the seismic reflection events reflect the distribution of strata; Determine the number of overlapping jump points at each horizontal position, and confirm the three-dimensional seismic data block according to the different numbers of the jump points, wherein the number of jump points in the same three-dimensional seismic data block is the same; Perform three-dimensional transformation on three-dimensional seismic data blocks; Clustering the seismic trace data points after three-dimensional transformation; Based on the data points of the clustering results of all different blocks, project the data points of the same cluster cluster onto the same XY plane, find the first edge point on each XY plane of the block, and back-project the first edge point into the second edge point of the cluster cluster; Based on the second edge points, determining a proximity relationship of the second edge points between clustering results of different blocks, wherein the proximity relationship represents the possibility that two stratigraphic sublayers corresponding to two clusters are continuous; Based on the proximity relationship, confirm the connection mode between the clustering results of all different blocks; Based on the connection method, a variety of possible formation interpretation results are obtained.

2. The seismic stratigraphic interpretation method for the stratigraphic pinch-out problem according to claim 1, characterized in that: The first edge point of each cluster is determined by the following method: In the clustering results of each block, the data points that do not have four adjacent data points at the same time are taken as the first edge points.

3. The seismic stratigraphic interpretation method for the stratigraphic pinch-out problem according to claim 1, characterized in that: The proximity relationship of the second edge point is determined by the following method: For the second edge point of each cluster, calculate the Euclidean distance between the second edge point of each other cluster, and calculate the Euclidean distance between the data points in the same cluster; For each pairwise combination of clusters, select a set number of data point pairs with the shortest Euclidean distance; If the Euclidean distance between the data point pair is less than a set multiple of the maximum value of the Euclidean distance between data points in the same cluster, the proximity relationship of the second edge point is considered to be probabilistic proximity, otherwise the proximity relationship is considered to be non-proximal.

4. The seismic stratigraphic interpretation method for the stratigraphic pinch-out problem according to claim 3, characterized in that: The method of confirming the connection between the clustering results of all different blocks based on the proximity relationship includes: The continuous states between all the stratigraphic clustering results with probabilistic proximity are expressed as continuous and discontinuous respectively; The continuous state between the clustering results of all different blocks and the stratigraphic interpretation results under all permutations and combinations are obtained, and multiple stratigraphic interpretation results with a high probability of existence are obtained.

5. The seismic stratigraphic interpretation method for the stratigraphic pinch-out problem according to claim 1, characterized in that: After clustering the three-dimensionally transformed seismic trace data points, the method further includes: Based on the clustering results, for each layer category, determine whether there are different scattered points at the same position on the XY plane; If there are no different scattered points at the same position on the XY plane, it is determined that the pinch-out stratum is effectively identified, and a step-by-step division result of the first stratum is obtained, wherein the pinch-out stratum is effectively identified, indicating that the three-dimensional scattered point coordinates of the transformed marker point and the stratum category division result of the stratum marker point are credible; If there are different scattered points at the same position on the XY plane, according to the clustering result, each cluster cluster in each clustering result with different scattered points at the same position on the XY plane is traversed, and the stratigraphic landmark points corresponding to each cluster cluster are re-transformed into three-dimensional coordinates, and the first stratigraphic level-by-level division result of each cluster cluster is obtained through the adjusted clustering parameters until the second cluster clusters of the first stratigraphic level-by-level division results of all cluster clusters do not have different scattered points at the same position on the XY plane.

6. The seismic stratigraphic interpretation method for the stratigraphic pinch-out problem according to claim 1, characterized in that: The three-dimensional seismic data blocks are transformed into three dimensions using the PCA method.

7. A seismic interpretation system for formation pinch-out problem, characterized in that: The system comprises: A jump point determination module is used to determine the coordinates of the phase attribute jump points in the three-dimensional seismic data, wherein the jump points are used to mark the seismic reflection event axes, and the seismic reflection event axes reflect the distribution of the strata; A block division module is used to determine the number of overlapping jump points at each horizontal position, and confirm the three-dimensional seismic data block according to the different numbers of the jump points, wherein the number of jump points in the same three-dimensional seismic data block is the same; A three-dimensional transformation module is used to perform three-dimensional transformation on three-dimensional seismic data blocks; A clustering module is used to cluster the seismic trace data points after three-dimensional transformation; A splicing module, for projecting the data points of the same cluster cluster onto the same XY plane based on the data points of the clustering results of all different blocks, finding the first edge point on each XY plane of the block, and back-projecting the first edge point into the second edge point of the cluster cluster; Based on the second edge points, determining a proximity relationship of the second edge points between clustering results of different blocks, wherein the proximity relationship represents the possibility that two stratigraphic sublayers corresponding to two clusters are continuous; Based on the proximity relationship, confirm the connection mode between the clustering results of all different blocks; Based on the connection method, a variety of possible formation interpretation results are obtained.

8. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to at least one of the processors; wherein, The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the seismic stratigraphic interpretation method for the stratigraphic pinch-out problem described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the seismic stratigraphic interpretation method for the stratigraphic pinch-out problem described in any one of claims 1-6.

10. A computer software product, characterized in that: The computer software product includes codes or computer instructions, and the codes or computer instructions are used to enable a seismic stratigraphic interpretation device for the formation pinch-out problem to execute the seismic stratigraphic interpretation method for the formation pinch-out problem described in any one of claims 1-6.

Images