Multiple wave suppression method and device, electronic equipment and storage medium

Abstract

The application provides a multiple wave suppression method and device, electronic equipment and storage medium. The method comprises the following steps: establishing a trained suppression model in advance; acquiring pre-stack common shot data; determining multiple wave data in the pre-stack common shot data; inputting the pre-stack common shot data and the predicted multiple wave model data into the trained suppression model to obtain primary wave data, thereby realizing suppression of the multiple wave and improving the suppression precision of the multiple wave.

Description

Technical Field

[0001] This application relates to the field of geophysical exploration technology, and in particular to a method, apparatus, electronic device and storage medium for suppressing multiple waves. Background Technology

[0002] Multiple suppression techniques for seismic data have long been a key research area in geophysics. The presence of multiples reduces the signal-to-noise ratio of seismic data, creates tectonic artifacts, and severely affects the accuracy and reliability of seismic imaging. Current software technologies still face practical problems in application, such as unsatisfactory multiple suppression and difficulty in suppressing inter-layer multiples. Summary of the Invention

[0003] To address the aforementioned problems, this application provides a method, apparatus, electronic device, and storage medium for suppressing multiple waves, which can suppress multiple waves and improve the accuracy of multiple wave suppression.

[0004] This application provides a method for suppressing multiple waves, including:

[0005] Obtain pre-stack common shot set data;

[0006] Determine the predicted multiple wave model data in the pre-stack common shot set data;

[0007] The pre-stack common shot set data and the predicted multiple wave model data are input into a pre-trained suppression model to obtain primary wave data.

[0008] In some embodiments, the method further includes:

[0009] Acquire synthetic data and the primary wave data corresponding to the synthetic data, wherein the synthetic data includes: sample pre-stack common shot set data and sample pre-stack common shot set data of multiple wave model prediction;

[0010] A sample training set is determined based on the synthetic data and the primary wave data corresponding to the synthetic data.

[0011] The target sample training set is obtained by performing data augmentation processing on the sample training set.

[0012] The network model is trained based on the target sample training set to obtain a trained suppression model.

[0013] In some embodiments, the network model includes an input terminal, which includes a first channel and a second channel. The first channel is used to input pre-stack common shot set data of the samples, and the second channel is used to input multiple wave model data predicted by the samples. The output terminal of the network model is used to output the primary wave data corresponding to the synthetic data.

[0014] In some embodiments, the network model is a fully convolutional neural network, and the structure of the fully convolutional neural network model includes: the Unet network structure.

[0015] In some embodiments, the loss function of the network model includes the L1 loss function.

[0016] This application provides a multiple wave suppression device, including:

[0017] The acquisition module is used to acquire pre-stack common shot set data;

[0018] The determination module is used to determine the predicted multiple wave model data in the pre-stack common shot set data;

[0019] The suppression module is used to input the pre-stack common shot set data and the predicted multiple wave model data into a pre-trained suppression model to obtain primary wave data.

[0020] In some embodiments, the multiple wave suppression device is further configured to:

[0021] Acquire synthetic data and the primary wave data corresponding to the synthetic data, wherein the synthetic data includes: sample pre-stack common shot set data and sample pre-stack common shot set data of multiple wave model prediction;

[0022] A sample training set is determined based on the synthetic data and the primary wave data corresponding to the synthetic data.

[0023] The target sample training set is obtained by performing data augmentation processing on the sample training set.

[0024] The network model is trained based on the target sample training set to obtain a trained suppression model.

[0025] In some embodiments, the network model includes: an input terminal, the input terminal including: a first channel and a second channel, the first channel being used to input pre-stack common shot set data of samples, the second channel being used to input multiple wave model data predicted by samples, the output terminal of the network model being used to output primary wave data corresponding to the synthetic data, the network model being a fully convolutional neural network, the structure of the fully convolutional neural network model including: a Unet network structure, and the loss function of the network model including: an L1 loss function.

[0026] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, performs any of the above-described multiple wave suppression methods.

[0027] This application provides a storage medium storing a computer program that can be executed by one or more processors and can be used to implement the multiple wave suppression method described above.

[0028] This application provides a method, apparatus, electronic device, and storage medium for suppressing multiple waves. By establishing a pre-trained suppression model, the method acquires pre-stack common shot set data; determines the predicted multiple wave model data in the pre-stack common shot set data; and inputs the pre-stack common shot set data and the multiple wave data into the pre-trained suppression model to obtain primary wave data, thereby achieving suppression of multiple waves and improving the suppression accuracy of multiple waves. Attached Figure Description

[0029] The present application will be described in more detail below based on embodiments and with reference to the accompanying drawings.

[0030] Figure 1 A schematic diagram illustrating the implementation process of a multiple wave suppression method provided in this application embodiment;

[0031] Figure 2 A schematic diagram illustrating the implementation process of another multiple wave suppression method provided in this application embodiment;

[0032] Figure 3 A schematic diagram of a network model provided in an embodiment of this application;

[0033] Figure 4 A schematic diagram of pre-processed data provided in an embodiment of this application;

[0034] Figure 5 A schematic diagram of predicted multiple wave model data provided in an embodiment of this application;

[0035] Figure 6 A schematic diagram of primary wave data provided in an embodiment of this application;

[0036] Figure 7 This is a schematic diagram of the composition structure of the electronic device provided in the embodiments of this application.

[0037] In the accompanying drawings, the same parts are referred to by the same reference numerals, and the drawings are not drawn to scale. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0039] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0040] If the application documents contain similar descriptions such as "first, second, third", the following explanation shall be added: In the following description, the terms "first, second, third" are used only to distinguish similar objects and do not represent a specific order of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0042] Before introducing the embodiments of this application, a brief introduction to related technologies will be given:

[0043] Currently, with the increasing demands of exploration, the technology for suppressing multiples is also gradually developing both domestically and internationally. The main multiple suppression technologies abroad can be summarized into two categories: (1) Filtering methods based on signal analysis. Among them, the predictive deconvolution method uses the periodic characteristics of multiples to predict the pure interference part based on the information of primary reflection and interference in the seismic record. The physical meaning is clear, but the period of multiples is difficult to determine. The Ladon transform method uses the velocity difference between multiples and effective waves to transform the wave field to the Ladon domain to eliminate multiples. There are three transformation methods: linear, hyperbolic, and parabolic Ladon. The advantages of this type of method are small computational load, high efficiency, and easy implementation. However, the removal effect of multiples at near offsets is not good and it is easy to damage the effective signal. (2) Predictive subtraction method based on wave theory. Among them, the wave field extrapolation method suppresses water layer multiples on the CDP gather through wave field extension and adaptive subtraction, and has achieved significant results. The Feedback Iteration Method (SRME) is based on an accurate multiple model and wave theory. It constructs surface-related multiples using wavefield propagation information of seismic waves on the free surface and between layer interfaces of the model, and then subtracts the calculated multiples from the acquired seismic data. The advantage of this method is that it can adapt to arbitrarily complex subsurface structures, but its disadvantages are high computational cost and demanding data preprocessing requirements.

[0044] To address the problems existing in related technologies, this application provides a multiple wave suppression method, which is applied to electronic devices such as computers and mobile terminals. The functionality of the multiple wave suppression method provided in this application can be implemented by the processor of the electronic device calling program code, wherein the program code can be stored in a computer storage medium.

[0045] Example 1

[0046] This application provides a method for suppressing multiple waves. Figure 1 This is a schematic diagram illustrating the implementation process of a multiple wave suppression method provided in an embodiment of this application, as shown below. Figure 1 As shown, it includes:

[0047] Step S1: Obtain the pre-stack common shot set data.

[0048] In this embodiment of the application, the pre-stack common shot set data includes: multiple waves and primary waves.

[0049] In this embodiment of the application, pre-stack common shot gather data can be acquired through input from testing equipment, storage devices, etc. The testing equipment can be a shot gather acquisition device.

[0050] In some embodiments, the electronic device can communicate with a database to obtain pre-stack common shot set data from the database.

[0051] Step S2: Determine the predicted multiple wave model data in the pre-stack common shot set data.

[0052] In this embodiment, the pure interference portion can be predicted based on the information of primary reflection and interference recorded in the pre-stack common shot set data, thus obtaining multiple wave data.

[0053] In some embodiments, the Ladon transformation method can be used to transform the wave field to the Ladon domain by utilizing the velocity difference between the multiple wave and the effective wave, thereby obtaining the predicted multiple wave model data.

[0054] Step S3: Input the pre-stack common shot set data and the multiple wave data into the pre-trained suppression model to obtain the primary wave data.

[0055] In this embodiment of the application, the pre-trained suppression model can be a neural network model.

[0056] This application provides a multiple wave suppression method, which involves pre-establishing a trained suppression model, acquiring pre-stack common shot set data, determining multiple wave data in the pre-stack common shot set data, and inputting the pre-stack common shot set data and the multiple wave data into the pre-trained suppression model to obtain primary wave data, thereby achieving multiple wave suppression and improving the multiple wave suppression accuracy.

[0057] Example 2

[0058] Based on the foregoing embodiments, this application further provides a multiple wave suppression method. Figure 2 A schematic diagram illustrating the implementation process of a multiple wave suppression method provided as an example in this application is shown below. Figure 2 As shown, the method includes:

[0059] Step S11: Obtain the synthetic data and the primary wave data corresponding to the synthetic data, wherein the synthetic data includes: sample pre-stack common shot set data and sample predicted multiple wave model data from the sample pre-stack common shot set data.

[0060] Step S12: Determine the sample training set based on the synthetic data and the primary wave data corresponding to the synthetic data.

[0061] Step S13: Perform data augmentation processing on the sample training set to obtain the target sample training set.

[0062] In this embodiment of the application, the enhancement process may be to divide the sample data in the sample training set into blocks, for example, into data of size 256*256.

[0063] Step S14: Train the network model based on the target sample training set to obtain the trained suppression model.

[0064] In the embodiments of this application, Figure 3 This is a schematic diagram of the structure of a network model provided in an embodiment of this application, such as... Figure 3 As shown, the network model includes an input terminal, which includes a first channel and a second channel. The first channel is used to input pre-stack common shot set data of the samples, and the second channel is used to input multiple wave model data predicted by the samples. The output terminal of the network model is used to output the primary wave data corresponding to the synthetic data.

[0065] The network model is a fully convolutional neural network, and the structure of the fully convolutional neural network model includes: the Unet network structure. The loss function of the network model includes: the L1 loss function.

[0066] In this embodiment, the network model is divided into two parts: downsampling and upsampling. The basic structural units in the downsampling path consist of one convolutional layer (4x4 kernel), one BatchNorm layer, and one LeaklyReLU layer, totaling five groups. The number of channels in the convolutional layers increases from the initial 64 to 512, with each group having twice the number of channels as the previous group. In the upsampling path, a deconvolution algorithm is used for image upsampling. Its basic structural units are one deconvolutional layer (4x4 kernel), one BatchNorm layer, and one ReLU layer. Furthermore, a copying method is used to short-circuit the data from the downsampling on the left, improving the richness of data information during the upsampling process.

[0067] In this embodiment, the network model is a dual-channel input, single-channel output structure, with the input and output data maintaining the same size. Based on the sparse characteristics of the suppressed first wave, the objective function uses the L1 norm as the loss function, and the Adam optimizer is used for iterative updates.

[0068] Step S15: Obtain the pre-stack common shot set data.

[0069] In this embodiment of the application, the pre-stack common shot set data includes: predicted multiple wave model data and primary wave.

[0070] In this embodiment of the application, pre-stack common shot gather data can be acquired through input from testing equipment, storage devices, etc. The testing equipment can be a shot gather acquisition device.

[0071] In some embodiments, the electronic device can communicate with a database to obtain pre-stack common shot set data from the database.

[0072] Step S16: Determine the predicted multiple wave model data in the pre-stack common shot set data.

[0073] In this embodiment, the pure interference component can be predicted based on the information of primary reflection and interference recorded in the pre-stack common shot set data, thus obtaining multiple wave model data.

[0074] In some embodiments, the Ladon transformation method can be used to transform the wave field to the Ladon domain by utilizing the velocity difference between the multiple wave and the effective wave, thereby obtaining multiple wave model data.

[0075] Step S17: Input the pre-stack common shot set data and the multiple wave data into the pre-trained suppression model to obtain the primary wave data.

[0076] In this embodiment of the application, the pre-trained suppression model can be a neural network model.

[0077] This application provides a multiple wave suppression method, which involves pre-establishing a trained suppression model, acquiring pre-stack common shot set data, determining multiple wave data in the pre-stack common shot set data, and inputting the pre-stack common shot set data and the multiple wave data into the pre-trained suppression model to obtain primary wave data, thereby achieving multiple wave suppression and improving the multiple wave suppression accuracy.

[0078] Example 3

[0079] Based on the foregoing embodiments, this application further provides a multiple wave suppression method. This invention improves the stability and accuracy of network training by introducing multiple wave model information constraints into a conventional end-to-end data-driven multiple wave suppression deep learning network that uses pre-suppression data as input and primary wave data as labels. The network input data is dual-channel data, consisting of full-wavefield data containing multiple waves and corresponding multiple wave model data. The network output is the primary wave data of the corresponding trace set. The network is a UNET network structure of a fully convolutional neural network, divided into downsampling and upsampling parts. The basic structural units in the downsampling path consist of one convolutional layer (4x4 kernel size), one BatchNorm layer, and one LeaklyReLU layer, totaling five groups. The number of channels in the convolutional layers increases from the initial 64 to 512, with each group having twice the number of channels as the previous group. The upsampling path employs a deconvolution algorithm for image upsampling. Its basic structural unit consists of one deconvolution layer (4x4 kernel size), one BatchNorm layer, and one ReLU layer. Furthermore, a copying method is used to short-circuit the data from the downsampling on the left, thereby enhancing the richness of data information during the upsampling process.

[0080] In this embodiment, the designed network is a dual-channel input, single-channel output structure, with the input and output data having the same size. Based on the sparse characteristics of the suppressed first wave, the objective function uses the L1 norm as the loss function, and the Adam optimizer is used for iterative updates.

[0081] In this embodiment of the application, the basic flow of the algorithm includes:

[0082] Data preparation and data screening: Data preparation involves both synthetic data and actual data to ultimately form the sample label set required for this invention. Synthetic data can enhance the accuracy of multiple wave suppression, while actual data, by selecting data with good suppression effect as sample labels, can enhance the network's generalization ability.

[0083] Target sample training set preparation: Addressing the small sample problem of seismic data, the selected and prepared dataset is divided into blocks. The input data and corresponding label data are divided into 256*256 blocks to achieve data augmentation, improve sample diversity, and enhance the network's generalization ability. Sample label data pairs are generated according to the network's input and output data requirements.

[0084] Network training: Set the network training hyperparameters, feed the prepared training dataset into the network for training, and finally obtain a high-precision intelligent multiple wave suppression network.

[0085] Network inference: Reload the saved network and perform multiple wave suppression processes on the test data to verify the effectiveness of the trained network.

[0086] The method provided in this application establishes a multi-channel input network architecture and introduces multiple wave data constraints to enhance the learning information richness of the network. Through network training, the inherent relationship between the two input channels is fully explored, thereby realizing intelligent and high-precision suppression of multiple waves.

[0087] Based on the multiple wave suppression method provided in the foregoing embodiments, this application provides a specific example application. The training input data size is 256x256. The aforementioned network is established, with a learning rate of 0.0002, a batch size of 5, and 30 training epochs. Furthermore, the cluster GPU used in this test is an RTX 2080Ti with 11GB of video memory.

[0088] The network was trained based on the above parameters, and the trained model was saved. During testing, the data size was 266*2001, and the input data before processing was as follows: Figure 4 As shown, the multiple wave data used are as follows: Figure 5 As shown, the data compressed using the method provided in this application embodiment is as follows: Figure 6 As shown in the figure, it can be clearly seen that the method of the present invention has a good effect on multiple wave suppression. The processed result shows that the multiple waves are suppressed cleanly and there is no loss of effective waves.

[0089] Example 4

[0090] Based on the foregoing embodiments, this application provides a multiple wave suppression device. The various modules and units included in the device can be implemented by a processor in a computer device; of course, they can also be implemented by specific logic circuits. In the implementation process, the processor can be a central processing unit (CPU), a microprocessor unit (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0091] This application provides a multiple wave suppression device, which includes:

[0092] The acquisition module is used to acquire pre-stack common shot set data;

[0093] The determination module is used to determine the predicted multiple wave model data in the pre-stack common shot set data;

[0094] The suppression module is used to input the pre-stack common shot set data and the multiple wave data into a pre-trained suppression model to obtain the primary wave data.

[0095] In this embodiment of the application, the pre-stack common shot set data includes: multiple wave model data and primary wave.

[0096] In this embodiment of the application, pre-stack common shot gather data can be acquired through input from testing equipment, storage devices, etc. The testing equipment can be a shot gather acquisition device.

[0097] In some embodiments, the electronic device can communicate with a database to obtain pre-stack common shot set data from the database.

[0098] In this embodiment, the pure interference portion can be predicted based on the information of primary reflection and interference recorded in the pre-stack common shot set data, thus obtaining multiple wave data.

[0099] In some embodiments, the Ladon transformation method can be used to transform the wave field to the Ladon domain by utilizing the velocity difference between the multiple wave and the effective wave, thereby obtaining multiple wave model data.

[0100] In some embodiments, the multiple wave suppression device is further configured to:

[0101] The multiple wave suppression device is also used for:

[0102] Acquire synthetic data and the primary wave data corresponding to the synthetic data, wherein the synthetic data includes: sample pre-stack common shot set data and sample multiple wave model data in the sample pre-stack common shot set data;

[0103] A sample training set is determined based on the synthetic data and the primary wave data corresponding to the synthetic data.

[0104] The target sample training set is obtained by performing data augmentation processing on the sample training set.

[0105] The network model is trained based on the target sample training set to obtain a trained suppression model.

[0106] In this embodiment of the application, the enhancement process may be to divide the sample data in the sample training set into blocks, for example, into data of size 256*256.

[0107] In this embodiment, the network model is divided into two parts: downsampling and upsampling. The basic structural units in the downsampling path consist of one convolutional layer (4x4 kernel), one BatchNorm layer, and one LeaklyReLU layer, totaling five groups. The number of channels in the convolutional layers increases from the initial 64 to 512, with each group having twice the number of channels as the previous group. In the upsampling path, a deconvolution algorithm is used for image upsampling. Its basic structural units are one deconvolutional layer (4x4 kernel), one BatchNorm layer, and one ReLU layer. Furthermore, a copying method is used to short-circuit the data from the downsampling on the left, improving the richness of data information during the upsampling process.

[0108] In this embodiment, the network model is a dual-channel input, single-channel output structure, with the input and output data maintaining the same size. Based on the sparse characteristics of the suppressed first wave, the objective function uses the L1 norm as the loss function, and the Adam optimizer is used for iterative updates.

[0109] In some embodiments, the network model includes: an input terminal, the input terminal including: a first channel and a second channel, the first channel being used to input sample pre-stack common shot set data, the second channel being used to input sample multiple wave data, the output terminal of the network model being used to output the primary wave data corresponding to the synthetic data, the network model being a fully convolutional neural network, the structure of the fully convolutional neural network model including: a Unet network structure, and the loss function of the network model including: an L1 loss function.

[0110] This application provides a multiple wave suppression device that, by pre-establishing a trained suppression model, acquires pre-stack common shot set data; determines multiple wave data in the pre-stack common shot set data; and inputs the pre-stack common shot set data and the multiple wave model data into the pre-trained suppression model to obtain primary wave data, thereby achieving suppression of multiple waves and improving the suppression accuracy of multiple waves.

[0111] It should be noted that, in the embodiments of this application, if the above-described multiple wave suppression method is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.

[0112] Accordingly, this application provides a storage medium storing a computer program thereon, characterized in that the computer program, when executed by a processor, implements the steps in the multiple wave suppression method provided in the above embodiments.

[0113] Example 5

[0114] This application provides an electronic device; Figure 7 This is a schematic diagram of the composition structure of the electronic device provided in the embodiments of this application, such as... Figure 7 As shown, the electronic device 700 includes: a processor 701, at least one communication bus 702, a user interface 703, at least one external communication interface 704, and a memory 705. The communication bus 702 is configured to enable communication between these components. The user interface 703 may include a display screen, and the external communication interface 704 may include standard wired and wireless interfaces. The processor 701 is configured to execute a program of a multiple wave suppression method stored in the memory to implement the steps of the multiple wave suppression method provided in the above embodiment.

[0115] The multiple wave suppression method includes:

[0116] Obtain pre-stack common shot set data;

[0117] Determine the multiple wave model data in the pre-stack common shot set data;

[0118] The pre-stack common shot set data and the multiple wave model data are input into a pre-trained suppression model to obtain primary wave data.

[0119] In this embodiment of the application, the pre-stack common shot set data includes: multiple wave model data and primary wave.

[0120] In this embodiment of the application, pre-stack common shot gather data can be acquired through input from testing equipment, storage devices, etc. The testing equipment can be a shot gather acquisition device.

[0121] In some embodiments, the electronic device can communicate with a database to obtain pre-stack common shot set data from the database.

[0122] In this embodiment, the pure interference component can be predicted based on the information of primary reflection and interference recorded in the pre-stack common shot set data, thus obtaining multiple wave model data.

[0123] In some embodiments, the Ladon transformation method can be used to transform the wave field to the Ladon domain by utilizing the velocity difference between the multiple wave and the effective wave, thereby obtaining multiple wave model data.

[0124] In some embodiments, the method further includes:

[0125] Acquire synthetic data and the primary wave data corresponding to the synthetic data, wherein the synthetic data includes: sample pre-stack common shot set data and sample pre-stack common shot set data of multiple wave model prediction;

[0126] A sample training set is determined based on the synthetic data and the primary wave data corresponding to the synthetic data.

[0127] The target sample training set is obtained by performing data augmentation processing on the sample training set.

[0128] The network model is trained based on the target sample training set to obtain a trained suppression model.

[0129] In some embodiments, the network model includes an input terminal, which includes a first channel and a second channel. The first channel is used to input pre-stack common shot set data of the samples, and the second channel is used to input multiple wave model data predicted by the samples. The output terminal of the network model is used to output the primary wave data corresponding to the synthetic data.

[0130] In some embodiments, the network model is a fully convolutional neural network, and the structure of the fully convolutional neural network model includes: the Unet network structure.

[0131] In some embodiments, the loss function of the network model includes the L1 loss function.

[0132] The network model is a fully convolutional neural network, and the structure of the fully convolutional neural network model includes: the Unet network structure. The loss function of the network model includes: the L1 loss function.

[0133] In this embodiment, the network model is divided into two parts: downsampling and upsampling. The basic structural units in the downsampling path consist of one convolutional layer (4x4 kernel), one BatchNorm layer, and one LeaklyReLU layer, totaling five groups. The number of channels in the convolutional layers increases from the initial 64 to 512, with each group having twice the number of channels as the previous group. In the upsampling path, a deconvolution algorithm is used for image upsampling. Its basic structural units are one deconvolutional layer (4x4 kernel), one BatchNorm layer, and one ReLU layer. Furthermore, a copying method is used to short-circuit the data from the downsampling on the left, improving the richness of data information during the upsampling process.

[0134] In this embodiment, the network model is a dual-channel input, single-channel output structure, with the input and output data maintaining the same size. Based on the sparse characteristics of the suppressed first wave, the objective function uses the L1 norm as the loss function, and the Adam optimizer is used for iterative updates.

[0135] The descriptions of the above embodiments of the electronic devices and storage media are similar to those of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the embodiments of the computer devices and storage media of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0136] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0137] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0138] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0139] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0140] In addition, each functional unit in the various embodiments of this application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0141] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0142] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a controller to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0143] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for suppressing multiple waves, characterized in that, include: Obtain pre-stack common shot set data; Determine the predicted multiple wave model data in the pre-stack common shot set data; The pre-stack common shot set data and the predicted multiple wave model data are input into a pre-trained suppression model to obtain the primary wave data; The method further includes: acquiring synthetic data and primary wave data corresponding to the synthetic data, wherein the synthetic data includes: sample pre-stack common shot set data and multiple wave model data predicted from the sample pre-stack common shot set data; determining a sample training set based on the synthetic data and the primary wave data corresponding to the synthetic data; performing data augmentation processing on the sample training set to obtain a target sample training set; and training the network model based on the target sample training set to obtain a trained suppression model. The network model includes an input terminal, which includes a first channel and a second channel. The first channel is used to input pre-stack common shot set data of the samples, and the second channel is used to input multiple wave model data predicted by the samples. The output terminal of the network model is used to output the primary wave data corresponding to the synthetic data.

2. A multiple wave suppression device, characterized in that, include: The acquisition module is used to acquire pre-stack common shot set data; The determination module is used to determine the predicted multiple wave model data in the pre-stack common shot set data; The suppression module is used to input the pre-stack common shot set data and the predicted multiple wave model data into the pre-trained suppression model to obtain the primary wave data. The multiple wave suppression device is further configured to: acquire synthetic data and primary wave data corresponding to the synthetic data, wherein the synthetic data includes: sample pre-stack common shot set data and sample multiple wave model data predicted from the sample pre-stack common shot set data; determine a sample training set based on the synthetic data and the primary wave data corresponding to the synthetic data; perform data augmentation processing on the sample training set to obtain a target sample training set; and train the network model based on the target sample training set to obtain a trained suppression model. The network model includes an input terminal, which includes a first channel and a second channel. The first channel is used to input pre-stack common shot set data of the samples, and the second channel is used to input multiple wave model data predicted by the samples. The output terminal of the network model is used to output the primary wave data corresponding to the synthetic data.

3. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, performs the multiple wave suppression method as described in claim 1.

4. A storage medium, characterized in that, The computer program stored in the storage medium can be executed by one or more processors and can be used to implement the multiple wave suppression method as described in claim 1.

Images