Multiple-Wave Suppression Method and Device Based on Data Association and Long Short-Term Memory Network

Abstract

The present invention discloses a multiple wave suppression method and device based on data association and long short-term memory network. The method includes: representing a CMP gather as a two-dimensional array, where the amplitude value positions of the CMP gather satisfy the time-distance curve relationship; performing interpolation operation on the CMP gather to obtain interpolation data; weighting the interpolation data by interpolation coefficients to obtain a velocity spectrum; according to the two-dimensional array, the interpolation data, and the velocity spectrum, recording and storing the position index information corresponding to the primary wave and the multiple wave in the CMP gather, and extracting the multiple wave two-dimensional data set; training a long short-term memory network according to the multiple wave two-dimensional data set, inputting the original multiple wave into the long short-term memory network for prediction to obtain the multiple wave signal in the cross region; matching the multiple wave signal with the original multiple wave according to the position index information. The present invention combines data correlation and long short-term memory neural network algorithm to achieve precise suppression of multiple waves and effectively protect the primary wave signal.

Description

Technical Field

[0001] The present invention relates to the technical field of seismic exploration, and particularly relates to a multiple suppression method and device, a computing device, and a computer storage medium based on data association and long short-term memory network. Background Art

[0002] In seismic data processing, the presence of multiples significantly affects the accuracy and reliability of seismic imaging. Multiples are generated by different underground interfaces (such as low-velocity zones, coal seams, and igneous rocks), often interfering with the reflection signals of primary waves, thus posing challenges to the interpretation of seismic data and even potentially leading to misleading results. Traditional multiple suppression methods mainly include filtering methods and predictive subtraction techniques. Among them, the Radon transform method is one of the most mature and widely used. However, when dealing with complex geological structures, these methods face problems such as frequency aliasing and damage to primary wave signals, and it is difficult to meet the requirements of high-precision exploration.

[0003] To solve the above problems, the present invention proposes a multiple suppression method based on data correlation and LSTM algorithm, which has better signal fidelity and amplitude preservation characteristics compared with the traditional Radon filtering method. Summary of the Invention

[0004] In view of the above problems, the present invention is proposed to provide a multiple suppression method and device, a computing device, and a computer storage medium based on data association and long short-term memory network to achieve precise suppression of multiples and effectively protect primary wave signals.

[0005] According to one aspect of the present invention, there is provided a multiple suppression method based on data association and long short-term memory network, including:

[0006] Representing a CMP gather as a two-dimensional array, wherein the amplitude value positions of the CMP gather satisfy a time-distance curve relationship;

[0007] Performing interpolation operation on the CMP gather to obtain interpolation data; weighting the interpolation data by an interpolation coefficient to obtain a velocity spectrum;

[0008] According to the two-dimensional array, the interpolation data, and the velocity spectrum, recording and storing the position index information corresponding to primary waves and multiples in the CMP gather; extracting a multiple two-dimensional data set through the position index information;

[0009] Training a long short-term memory network according to the multiple two-dimensional data set, inputting the original multiples into the long short-term memory network for prediction to obtain multiple signals including the cross region of primary waves and multiples;

[0010] Match the multiple wave signal with the original multiple wave according to the position index information to achieve multiple wave suppression of the original multiple wave.

[0011] In an alternative manner, the time-distance curve relationship is:

[0012]

[0013] where t is the propagation time from the source to each observation point on the survey line; t o is the zero-offset time; x is the offset distance of the observation point relative to the excitation point; v is the propagation speed.

[0014] In an alternative manner, the calculation formula of the velocity spectrum is:

[0015]

[0016] where is the data value after interpolation, located in the (ig + L + 1)-th row and the ih-th column of the two-dimensional array; L is the smoothing window size parameter; it is the time index; iv is the spatial index; nb is the number of seismic traces.

[0017] In an alternative manner, the data value after interpolation is:

[0018]

[0019] where α is the interpolation coefficient; , is the interpolation point; , are respectively the data values at the interpolation point under the index ih , at the interpolation point.

[0020] In an alternative manner, the long short-term memory network includes an input gate, a forget gate, and an output gate;

[0021] where the input gate is used to control the importance of the current information and save it in the cell state;

[0022] the forget gate is used to control the importance of the historical information and the quantity of the previous cell state;

[0023] the output gate is used to output the current cell state.

[0024] In an alternative manner, the expression of the input gate is:

[0025] C t ~ = tanh( W c .[ h t − 1 , x t ] + b c )

[0026] where The weight matrix for the candidate state; The bias term for the candidate state; The output state at the previous moment; The input at the current moment;

[0027] The expression of the forgetting gate is:

[0028] f t = σ ( W f .[ h t − 1 , x t ] + b f )

[0029] Among them, is the weight matrix of the forgetting gate; is the bias term of the forgetting gate; is the sigmoid activation function;

[0030] The expression of the output gate is:

[0031] o t = σ ( W o .[ h t − 1 , x t ] + b o ) h t = O t × tanh( C t )

[0032] Among them, is the weight matrix of the output gate; is the bias term of the output gate; is the output state at the current moment; is the output of the output gate; is the cell state, , i t = σ ( W i .[ h t − 1 , x t ] + b i ) , is the weight matrix of the input gate, is the bias term of the input gate.

[0033] In an alternative manner, extracting the multiple wave two-dimensional dataset includes a fixed time window method and an adaptive time window method.

[0034] According to another aspect of the present invention, there is provided a multiple wave suppression device based on data association and long short-term memory network, including:

[0035] A two-dimensional array representation module for representing the CMP gather as a two-dimensional array, wherein the amplitude value positions of the CMP gather satisfy the time-distance curve relationship;

[0036] A velocity spectrum calculation module for performing interpolation operation on the CMP gather to obtain interpolation data; weighting the interpolation data by an interpolation coefficient to obtain a velocity spectrum;

[0037] A dataset generation module for recording and storing the position index information corresponding to the primary wave and the multiple wave in the CMP gather according to the two-dimensional array, the interpolation data, and the velocity spectrum; extracting the multiple wave two-dimensional dataset through the position index information;

[0038] The multiple - wave prediction module is used to train a long - short - term memory network according to the multiple - wave two - dimensional data set, input the original multiple waves into the long - short - term memory network for prediction, and obtain multiple - wave signals including the cross - region of primary waves and multiple waves.

[0039] The matching and suppression module is used to match the multiple - wave signals with the original multiple waves according to the position index information to achieve suppression of the multiple waves of the original multiple waves.

[0040] According to another aspect of the present invention, there is provided a computing device, including: a processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete communication with each other through the communication bus.

[0041] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the above - mentioned multiple - wave suppression method based on data association and long - short - term memory network.

[0042] According to still another aspect of the present invention, there is provided a computer storage medium, in which at least one executable instruction is stored, and the executable instruction causes a processor to perform operations corresponding to the above - mentioned multiple - wave suppression method based on data association and long - short - term memory network.

[0043] According to the solution provided by the present invention, the CMP gather is represented as a two - dimensional array, wherein the amplitude value positions of the CMP gather satisfy the time - distance curve relationship; interpolation operation is performed on the CMP gather to obtain interpolation data; the interpolation data is weighted by an interpolation coefficient to obtain a velocity spectrum; according to the two - dimensional array, the interpolation data, and the velocity spectrum, the position index information corresponding to the primary waves and multiple waves in the CMP gather is recorded and stored; a multiple - wave two - dimensional data set is extracted through the position index information; a long - short - term memory network is trained according to the multiple - wave two - dimensional data set, and the original multiple waves are input into the long - short - term memory network for prediction to obtain multiple - wave signals including the cross - region of primary waves and multiple waves; the multiple - wave signals are matched with the original multiple waves according to the position index information to achieve suppression of the multiple waves of the original multiple waves. The present invention effectively solves the suppression problem in the cross - region of primary waves and multiple waves by recording and storing the position indexes of multiple waves in the CMP gather, and using the LSTM neural network to train and predict the extracted multiple - wave data, realizes accurate suppression of multiple waves, and at the same time protects the primary - wave signals. It performs excellently in the processing of comprehensive complex geological models and has better signal fidelity and amplitude - preservation characteristics compared with the traditional Radon filtering method.

[0044] The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented in accordance with the content of the specification. And in order to make the above and other objects, features, and advantages of the present invention more obvious and understandable, the following specific embodiments of the present invention are specifically given. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0046] Figure 1 FIG. shows a schematic flow chart of the multiple wave suppression method based on data association and long short-term memory network according to an embodiment of the present invention;

[0047] Figure 2 FIG. shows a schematic flow chart of data processing in a part of seismic exploration according to an embodiment of the present invention;

[0048] Figure 3 FIG. shows a schematic diagram of the DC-LSTM algorithm processing framework according to an embodiment of the present invention;

[0049] Figure 4 FIG. shows a schematic diagram of the data correlation between the CMP gather, velocity spectrum, and stacked section according to an embodiment of the present invention;

[0050] Figure 5 FIG. shows a schematic diagram of the DC-LSTM algorithm for extracting and predicting multiple waves according to an embodiment of the present invention;

[0051] Figure 6 FIG. shows a schematic diagram of suppressing multiple waves of synthetic data according to an embodiment of the present invention;

[0052] Figure 7 FIG. shows a schematic diagram of suppressing multiple waves of complex synthetic data according to an embodiment of the present invention;

[0053] Figure 8 FIG. shows a schematic diagram of an actual production data experiment according to an embodiment of the present invention;

[0054] Figure 9 FIG. shows a schematic diagram of the structure of a multiple wave suppression device based on data association and long short-term memory network according to an embodiment of the present invention;

[0055] Figure 10 FIG. shows a schematic diagram of the structure of a computing device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be fully communicated to those skilled in the art.

[0057] Figure 1 The flowchart of the multiple wave suppression method based on data association and long short-term memory network according to an embodiment of the present invention is shown. Specifically, as Figure 1 shown, it includes the following steps:

[0058] Step S101, represent the CMP gather as a two-dimensional array, where the amplitude value positions of the CMP gather satisfy the time-distance curve relationship.

[0059] In this embodiment, the processing of the shot gather records collected in the field into seismic result data generally requires three steps: preprocessing, pre-stack processing, and post-stack processing. In seismic data processing, the intermediate data of each operation step has a certain correlation. The process of multiple wave suppression is as Figure 2 shown. In the above processing process, there is a close association among the CMP (common midpoint) gather, the velocity spectrum, and the stacked section. The multiple waves on the CMP gather (as Figure 4 shown in a) form energy clusters on the velocity spectrum (as Figure 4 shown in b). By obtaining the time-velocity from the energy clusters, and then after the normal moveout (NMO) operation, the CMP gather is flattened, and a stacked section (as Figure 4 shown in c) is formed through stacking (Stack). Based on the data association relationship in the above process, when performing velocity analysis, record and store the position indexes of the multiple waves and the primary waves in the CMP gather. Specifically, first, the CMP gather can be regarded as a two-dimensional array, and its amplitude value positions satisfy the time-distance curve relationship as:

[0060]

[0061] where t is the propagation time from the source to each observation point on the survey line; t o is the self-excitation and self-reception time; x is the offset distance of the observation point relative to the excitation point; v is the propagation speed.

[0062] Step S102, perform interpolation operation on the CMP gather to obtain interpolation data; weight the interpolation data by an interpolation coefficient to obtain a velocity spectrum.

[0063] Specifically, interpolation processing is performed on the CMP gather. Assuming that d(i,j) is the value at the i-th time point and the j-th spatial point in the seismic data, the interpolated data value s at the (i + L + 1)-th row and the ih-th column can be expressed as:

[0064]

[0065] where ɑ is the interpolation coefficient; , is the interpolation point; , are respectively the data values at the interpolation points under the index ih , at the interpolation points.

[0066] Then, the interpolation coefficient is used to perform weighted calculation on the interpolated data to obtain the velocity spectrum, and its calculation formula is:

[0067]

[0068] where is the interpolated data value, located at the (ig + L + 1)-th row and the ih-th column of the two-dimensional array; L is the smoothing window size parameter; it is the time index; iv is the spatial index; nb is the number of seismic traces.

[0069] Step S103: Record and store the position index information corresponding to the primary wave and the multiple wave in the CMP gather according to the two-dimensional array, the interpolated data, and the velocity spectrum; extract the multiple-wave two-dimensional data set through the position index information.

[0070] In this embodiment, a fixed time window (such as Figure 5 shown in a) and an adaptive time window (such as Figure 5 shown) can be used to accurately obtain the multiple-wave two-dimensional data set. Among them, Figure 5 b is the result of predicting the multiple wave with the fixed time window (signal-to-noise ratio = 5), Figure 5 d is the result of predicting the multiple wave with the adaptive time window.

[0071] Step S104: Train a long short-term memory network according to the multiple-wave two-dimensional data set, input the original multiple wave into the long short-term memory network for prediction, and obtain the multiple-wave signal including the cross region of the primary wave and the multiple wave.

[0072] In this embodiment, there is often an overlapping region between the primary wave and the multiple wave in the extracted multiple waves. To address the issue of the overlapping region between the primary wave and the multiple wave, the LSTM neural network algorithm is used to train and predict the multiple wave data. Through its unique Input gate, Forget gate, and Output gate mechanisms, the LSTM neural network algorithm can effectively predict the multiple wave signals in the overlapping region, thereby achieving the precise extraction and suppression of the multiple waves. As Figure 3 shown, first, after performing velocity analysis on the data (Input Data) of the input layer, the cdp (common depth point) and index positioning data are recorded, and the extra 2D data (extra2Ddata) is obtained based on the positioning data. Then, dimension processing and feature extraction are performed. Next, the Long Short Term Memory Forecast (LSTM prediction) is used to handle the long-term dependencies in the sequence data and obtain the prediction result. Finally, data correlation processing is carried out, and NMO (normal moveout) and stack processing are performed.

[0073] In this embodiment, the input gate is used to control the importance of the current information and store it in the cell state; the forget gate is used to control the importance of the historical information and the quantity of the previous cell state; the output gate is used to output the current cell state.

[0074] Among them, the expression of the input gate is:

[0075] C t ~ = tanh( W c .[ h t − 1 , x t ] + b c )

[0076] Among them, is the weight matrix of the candidate state; is the bias term of the candidate state; is the output state of the previous moment; is the input of the current moment;

[0077] The expression of the forget gate is:

[0078] f t = σ ( W f .[ h t − 1 , x t ] + b f )

[0079] Among them, is the weight matrix of the forget gate; is the bias term of the forget gate; is the sigmoid activation function;

[0080] The expression of the output gate is as follows:

[0081] o t = σ ( W o .[ h t − 1 , x t ] + b o ) h t = O t × tanh( C t )

[0082] Wherein, is the weight matrix of the output gate; is the bias term of the output gate; is the output state at the current moment; is the output of the output gate; is the cell state, , i t = σ ( W i .[ h t − 1 , x t ] + b i ) , is the weight matrix of the input gate, is the bias term of the input gate.

[0083] This embodiment is based on the close correlation in seismic data processing and utilizes the accurate prediction ability of the long short-term memory (LSTM) neural network algorithm. By recording and storing the position indices of the multiple waves collected by CMP, a multi-wave dataset is accurately obtained, and then the LSTM neural network algorithm is used to train the extracted multiple-wave data to achieve accurate extraction and suppression of the multiple waves.

[0084] Step S105: Match the multiple-wave signal with the original multiple wave according to the position index information to achieve multiple-wave suppression of the original multiple wave.

[0085] For example, align the multiple-wave signal with the original multiple wave in the time domain to match the time delay with the original multiple wave. In addition to the time delay, the spatial position of the multiple-wave signal can also be adjusted according to the propagation path of the seismic wave to align it with the original multiple wave spatially. After the multiple-wave signal and the original multiple wave are accurately matched both in time and space, the multiple wave is suppressed by means such as signal subtraction (subtracting the matched multiple-wave signal from the original seismic data to retain the effective reflected wave).

[0086] To verify the effectiveness of the method proposed in this embodiment, the following processing experiments on synthetic data and actual data are carried out.

[0087] Figure 6 Show the multiple-wave suppression of synthetic data by different methods. Figure 6 a. Input data containing multiple waves and noise (signal-to-noise ratio = 5); Figure 6 b. Result of multiple-wave removal by Radon transform; Figure 6 c. Result of multiple-wave removal by DC-LSTM algorithm; Figure 6d is the difference between (b) and (a) (the black solid arrow represents the multiple wave; the black dashed arrow represents the primary wave; the white arrow represents aliasing). Figure 6 e is the difference between (c) and (a) (the black solid arrow represents the multiple wave).

[0088] Figure 7 Suppressing multiple waves of complex synthetic data by different methods. Figure 7 a is the stacked section of the original data; Figure 7 b is the result of suppressing multiple waves by Radon transform (the black arrow points to the multiple wave; the white arrow represents aliasing); Figure 7 c is the result of suppressing multiple waves by the DC-LSTM algorithm.

[0089] Figure 8 is the processing result of actual production data; Figure 8 a is the input data of the multiple wave; Figure 8 b is the result of suppressing multiple waves by Radon transform; Figure 8 c is the result of suppressing multiple waves by the DC-LSTM algorithm (the black solid arrow points to the multiple wave; the black dashed arrow represents the primary wave; the white arrow points to aliasing).

[0090] The above experimental results show that compared with the traditional method of suppressing multiple waves by Radon transform, the method DC-LSTM proposed in this embodiment can effectively protect the primary wave signal while effectively suppressing multiple waves, avoid the phenomenon of aliasing, and has better amplitude preservation characteristics and higher processing accuracy.

[0091] The solution provided by the above embodiments of the present invention represents the CMP gather as a two-dimensional array, where the amplitude value positions of the CMP gather satisfy the time-distance curve relationship; performs interpolation operations on the CMP gather to obtain interpolation data; weights the interpolation data through interpolation coefficients to obtain a velocity spectrum; records and stores the position index information corresponding to the primary wave and multiple waves in the CMP gather according to the two-dimensional array, the interpolation data, and the velocity spectrum; extracts the multiple-wave two-dimensional data set through the position index information; trains a long short-term memory network according to the multiple-wave two-dimensional data set, inputs the original multiple waves into the long short-term memory network for prediction, and obtains a multiple-wave signal including the cross region of the primary wave and multiple waves; matches the multiple-wave signal with the original multiple waves according to the position index information to achieve multiple-wave suppression of the original multiple waves. The present invention effectively solves the suppression problem in the cross region between the primary wave and multiple waves by recording and storing the position indexes of multiple waves in the CMP gather, and using the LSTM neural network to train and predict the extracted multiple-wave data, realizes accurate suppression of multiple waves, and protects the primary wave signal at the same time. It performs excellently in the processing of complex comprehensive geological models and has better signal fidelity and amplitude preservation characteristics compared with the traditional Radon filtering method.

[0092] Figure 9 FIG. shows a schematic structural diagram of a multiple-wave suppression device based on data association and long short-term memory network according to an embodiment of the present invention, including:

[0093] A two-dimensional array representation module 910, configured to represent the CMP gather as a two-dimensional array, where the amplitude value positions of the CMP gather satisfy the time-distance curve relationship;

[0094] A velocity spectrum calculation module 920, configured to perform interpolation operations on the CMP gather to obtain interpolation data; weight the interpolation data through interpolation coefficients to obtain a velocity spectrum;

[0095] A data set generation module 930, configured to record and store the position index information corresponding to the primary wave and multiple waves in the CMP gather according to the two-dimensional array, the interpolation data, and the velocity spectrum; extract the multiple-wave two-dimensional data set through the position index information;

[0096] A multiple-wave prediction module 940, configured to train a long short-term memory network according to the multiple-wave two-dimensional data set, input the original multiple waves into the long short-term memory network for prediction, and obtain a multiple-wave signal including the cross region of the primary wave and multiple waves;

[0097] A matching and suppression module 950, configured to match the multiple-wave signal with the original multiple waves according to the position index information to achieve multiple-wave suppression of the original multiple waves.

[0098] The solution provided by the above embodiments of the present invention represents the CMP gather as a two-dimensional array, wherein the amplitude value positions of the CMP gather satisfy the time-distance curve relationship; perform interpolation operation on the CMP gather to obtain interpolation data; weight the interpolation data by an interpolation coefficient to obtain a velocity spectrum; record and store the position index information corresponding to the primary wave and the multiple wave in the CMP gather according to the two-dimensional array, the interpolation data, and the velocity spectrum; extract the two-dimensional data set of the multiple wave through the position index information; train a long short-term memory network according to the two-dimensional data set of the multiple wave, input the original multiple wave into the long short-term memory network for prediction to obtain a multiple wave signal including the intersection area of the primary wave and the multiple wave; match the multiple wave signal with the original multiple wave according to the position index information to achieve suppression of the multiple wave of the original multiple wave. The present invention effectively solves the suppression problem in the intersection area of the primary wave and the multiple wave by recording and storing the position index of the multiple wave in the CMP gather and using the LSTM neural network to train and predict the extracted multiple wave data, realizes accurate suppression of the multiple wave, and protects the primary wave signal at the same time. It performs excellently in the processing of comprehensive complex geological models and has better signal fidelity and amplitude preservation characteristics compared with the traditional Radon filtering method.

[0099] Figure 10 The structural schematic diagram of the computing device embodiment of the present invention is shown. The specific implementation of the computing device is not limited in the specific embodiments of the present invention.

[0100] As Figure 10 shown, the computing device may include: a processor 1002, a communications interface 1004, a memory 1006, and a communication bus 1008.

[0101] Among them: The processor 1002, the communications interface 1004, and the memory 1006 communicate with each other through the communication bus 1008. The communications interface 1004 is used to communicate with network elements of other devices such as clients or other servers. The processor 1002 is used to execute the program 1010, and specifically can execute the relevant steps in the above embodiments of the multiple wave suppression method based on data association and long short-term memory network.

[0102] Specifically, the program 1010 may include program codes, and the program codes include computer operation instructions.

[0103] The processor 1002 may be a central processing unit (CPU), or a specific application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the computing device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0104] A memory 1006 for storing a program 1010. The memory 1006 may include a high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0105] Embodiments of the present invention provide a non-volatile computer storage medium storing at least one executable instruction, and the computer executable instruction can execute the multiple wave suppression method based on data association and long short-term memory network in any of the above method embodiments.

[0106] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems may also be used in conjunction with the teachings provided herein. The structure required to construct such systems will be apparent from the above description. In addition, embodiments of the present invention are not directed to any particular programming language. It should be understood that the content of the present invention described herein can be implemented using various programming languages, and the description of a particular language above is for the purpose of disclosing the best mode of the present invention.

[0107] In the specification provided herein, a large number of specific details are set forth. However, it can be understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0108] Similarly, it should be understood that, in order to streamline the present invention and assist in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting the intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, the inventive aspects lie in less than all the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate embodiment of the present invention.

[0109] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise explicitly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature that provides the same, equivalent, or similar purpose.

[0110] In addition, those skilled in the art can understand that although some of the embodiments herein include certain features included in other embodiments rather than other features, the combination of the features of different embodiments means that it is within the scope of the present invention and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

[0111] Each component embodiment of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0112] It should be noted that the above embodiments illustrate the present invention rather than limit the present invention, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A multiple wave suppression method based on data association and long short-term memory network, characterized in that: include: The CMP gather is represented as a two-dimensional array, wherein the amplitude value position of the CMP gather satisfies the time-distance curve relationship; Performing interpolation operation on the CMP gather to obtain interpolation data; weighting the interpolation data by an interpolation coefficient to obtain a velocity spectrum; According to the two-dimensional array, the interpolation data and the velocity spectrum, the position index information corresponding to the primary wave and the multiple waves in the CMP gather is recorded and stored; and the two-dimensional data set of the multiple waves is extracted through the position index information; Training a long short-term memory network according to the two-dimensional multiple wave data set, inputting the original multiple waves into the long short-term memory network for prediction, and obtaining multiple wave signals in the intersection area including the primary wave and the multiple waves; The multiple wave signals are matched with the original multiple waves according to the position index information to achieve multiple wave suppression of the original multiple waves.

2. The multiple wave suppression method based on data association and long short-term memory network according to claim 1 is characterized in that: The time-distance curve relationship is: ； in, t is the propagation time from the source to each observation point on the survey line; t 0 is the self-excitation and self-collection time; x is the offset distance of the observation point relative to the excitation point; v is the propagation speed.

3. The multiple wave suppression method based on data association and long short-term memory network according to claim 1 or 2, characterized in that: The calculation formula of the velocity spectrum is: ； in, is the interpolated data value, located in the ig+L+1th row and the i List; L is the smoothing window size parameter; it is the time index; iv is the spatial index; nb is the number of seismic traces.

4. The multiple wave suppression method based on data association and long short-term memory network according to claim 3 is characterized in that: The interpolated data value is: s(ig+L +1, i )=(1- a )· d(i 1 ,ih)+a · d(i 2 ,ih )； in, a is the interpolation coefficient; , is the interpolation point; , Under index ih , The data value at the interpolation point.

5. The multiple wave suppression method based on data association and long short-term memory network according to claim 1 is characterized in that: The long short-term memory network includes an input gate, a forget gate and an output gate; Wherein, the input gate is used to control the importance of current information and save it in the cell state; The forget gate is used to control the importance of historical information and the number of previous cell states; The output gate is used to output the current cell state.

6. The multiple wave suppression method based on data association and long short-term memory network according to claim 5, characterized in that: The expression of the input gate is: ； in, is a candidate status; is the weight matrix of the candidate state; is the bias term of the candidate state; is the output status at the previous moment; is the input at the current moment; The expression of the forget gate is: ； in, is the weight matrix of the forget gate; is the bias term of the forget gate; is the sigmoid activation function; is the output of the forget gate; The expression of the output gate is: ； ； in, is the weight matrix of the output gate; is the bias term of the output gate; is the output status at the current moment; is the output of the output gate; is the unit state, ; is the unit state at the previous moment, is the output of the input gate, ； in, is the weight matrix of the input gate, is the bias term of the input gate.

7. The multiple wave suppression method based on data association and long short-term memory network according to claim 1 is characterized in that: Extraction of multiple wave two-dimensional data sets includes fixed time window method and adaptive time window method.

8. A multiple wave suppression device based on data association and long short-term memory network, characterized in that: include: A two-dimensional array representation module, used for representing the CMP gather as a two-dimensional array, wherein the amplitude value position of the CMP gather satisfies the time-distance curve relationship; A velocity spectrum calculation module is used to perform interpolation operation on the CMP gather to obtain interpolation data; and to weight the interpolation data by an interpolation coefficient to obtain a velocity spectrum; A data set generation module is used to record and store position index information corresponding to the primary wave and the multiple waves in the CMP gather according to the two-dimensional array, the interpolation data and the velocity spectrum; and extract the two-dimensional data set of the multiple waves through the position index information; A multiple wave prediction module, used for training a long short-term memory network according to the two-dimensional multiple wave data set, inputting the original multiple waves into the long short-term memory network for prediction, and obtaining a multiple wave signal of the intersection area containing the primary wave and the multiple waves; A matching and suppression module is used to match the multiple wave signal with the original multiple wave according to the position index information to achieve multiple wave suppression of the original multiple wave.

9. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the multiple wave suppression method based on data association and long short-term memory network as described in any one of claims 1 to 7.

10. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, wherein the executable instruction enables a processor to perform operations corresponding to the multiple wave suppression method based on data association and long short-term memory network as described in any one of claims 1 to 7.

Images